Upload folder using huggingface_hub

checkpoint-12208/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/Qwen2.5-7B-Instruct-ta-madlad-mean/",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 161672
+}

checkpoint-12208/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.44.0.dev0"
+}

checkpoint-12208/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fa565e7b382e1a84abd84c651b721edcbe771a9fa800301c7c4589d1c48df16
+size 4842817304

checkpoint-12208/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:becf3c41c7359877372d1f9bdba9efe52cb2b8dab7330b346e831a36665b8f0e
+size 4998852224

checkpoint-12208/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad9da13aef49ef9aa84ff7ac6ae375fc2f8c339648214e7663e44e16a6763847
+size 4984124304

checkpoint-12208/model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc2c86e34819a46908bfe3ad42f3986e7efdfc34f67e43f40f690f77c7b0672
+size 4932743992

checkpoint-12208/model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:891f86a74d6b1791b98b581ff94cbedb16bfdb78595b9697dc3fd2ecc5974ba2
+size 4998852296

checkpoint-12208/model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f08b54070dfa6c45f340df1d29ef384bf94764af021157fc1fd8e8a4b6f5b8a1
+size 3662865184

checkpoint-12208/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09dd2baa00d523a1cf8349a86fde8c1bd0d35b90c14b50cfb9f20b910e91b82a
+size 2317729920

checkpoint-12208/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 30737946624
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00006-of-00007.safetensors"
+  }
+}

checkpoint-12208/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4d788d89e3ec9643b38a1466a4f2470ce06eee3435b156d17afabd9eb8aa291
+size 16728842070

checkpoint-12208/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
+size 14244

checkpoint-12208/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abe644ed33a3c4139223f0857a985127f3e6fbaa8c89fa14b57671b49ca52c21
+size 1064

checkpoint-12208/trainer_state.json

@@ -0,0 +1,2784 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.4024659611644084,
+  "eval_steps": 500,
+  "global_step": 12208,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0010219892526291499,
+      "grad_norm": 52.572940826416016,
+      "learning_rate": 1.0157273918741808e-06,
+      "loss": 9.6136,
+      "step": 31
+    },
+    {
+      "epoch": 0.0020439785052582997,
+      "grad_norm": 26.900487899780273,
+      "learning_rate": 2.0314547837483616e-06,
+      "loss": 7.35,
+      "step": 62
+    },
+    {
+      "epoch": 0.003065967757887449,
+      "grad_norm": 15.413382530212402,
+      "learning_rate": 3.0471821756225426e-06,
+      "loss": 5.872,
+      "step": 93
+    },
+    {
+      "epoch": 0.0040879570105165994,
+      "grad_norm": 9.475220680236816,
+      "learning_rate": 4.062909567496723e-06,
+      "loss": 4.8148,
+      "step": 124
+    },
+    {
+      "epoch": 0.005109946263145749,
+      "grad_norm": 16.33511734008789,
+      "learning_rate": 5.078636959370905e-06,
+      "loss": 4.2357,
+      "step": 155
+    },
+    {
+      "epoch": 0.006131935515774898,
+      "grad_norm": 17.79788589477539,
+      "learning_rate": 6.094364351245085e-06,
+      "loss": 3.9005,
+      "step": 186
+    },
+    {
+      "epoch": 0.007153924768404049,
+      "grad_norm": 7.385252952575684,
+      "learning_rate": 7.110091743119267e-06,
+      "loss": 3.6349,
+      "step": 217
+    },
+    {
+      "epoch": 0.008175914021033199,
+      "grad_norm": 7.6574835777282715,
+      "learning_rate": 8.125819134993446e-06,
+      "loss": 3.4197,
+      "step": 248
+    },
+    {
+      "epoch": 0.009197903273662348,
+      "grad_norm": 10.027671813964844,
+      "learning_rate": 9.141546526867629e-06,
+      "loss": 3.2883,
+      "step": 279
+    },
+    {
+      "epoch": 0.010219892526291498,
+      "grad_norm": 7.447092056274414,
+      "learning_rate": 1.015727391874181e-05,
+      "loss": 3.1606,
+      "step": 310
+    },
+    {
+      "epoch": 0.011241881778920647,
+      "grad_norm": 8.796594619750977,
+      "learning_rate": 1.117300131061599e-05,
+      "loss": 3.0724,
+      "step": 341
+    },
+    {
+      "epoch": 0.012263871031549797,
+      "grad_norm": 8.47999382019043,
+      "learning_rate": 1.218872870249017e-05,
+      "loss": 3.0249,
+      "step": 372
+    },
+    {
+      "epoch": 0.013285860284178948,
+      "grad_norm": 11.703062057495117,
+      "learning_rate": 1.3204456094364351e-05,
+      "loss": 2.9383,
+      "step": 403
+    },
+    {
+      "epoch": 0.014307849536808097,
+      "grad_norm": 7.270478248596191,
+      "learning_rate": 1.4220183486238533e-05,
+      "loss": 2.8753,
+      "step": 434
+    },
+    {
+      "epoch": 0.015329838789437247,
+      "grad_norm": 5.699134349822998,
+      "learning_rate": 1.5235910878112714e-05,
+      "loss": 2.8226,
+      "step": 465
+    },
+    {
+      "epoch": 0.016351828042066398,
+      "grad_norm": 6.3912529945373535,
+      "learning_rate": 1.6251638269986893e-05,
+      "loss": 2.7754,
+      "step": 496
+    },
+    {
+      "epoch": 0.017373817294695545,
+      "grad_norm": 8.240257263183594,
+      "learning_rate": 1.7267365661861077e-05,
+      "loss": 2.7351,
+      "step": 527
+    },
+    {
+      "epoch": 0.018395806547324697,
+      "grad_norm": 9.017704010009766,
+      "learning_rate": 1.8283093053735257e-05,
+      "loss": 2.7084,
+      "step": 558
+    },
+    {
+      "epoch": 0.019417795799953844,
+      "grad_norm": 6.017426013946533,
+      "learning_rate": 1.9298820445609438e-05,
+      "loss": 2.6741,
+      "step": 589
+    },
+    {
+      "epoch": 0.020439785052582995,
+      "grad_norm": 3.789416790008545,
+      "learning_rate": 2.031454783748362e-05,
+      "loss": 2.6605,
+      "step": 620
+    },
+    {
+      "epoch": 0.021461774305212147,
+      "grad_norm": 4.747366428375244,
+      "learning_rate": 2.13302752293578e-05,
+      "loss": 2.6245,
+      "step": 651
+    },
+    {
+      "epoch": 0.022483763557841294,
+      "grad_norm": 3.8344268798828125,
+      "learning_rate": 2.234600262123198e-05,
+      "loss": 2.5791,
+      "step": 682
+    },
+    {
+      "epoch": 0.023505752810470446,
+      "grad_norm": 4.5539116859436035,
+      "learning_rate": 2.336173001310616e-05,
+      "loss": 2.5648,
+      "step": 713
+    },
+    {
+      "epoch": 0.024527742063099593,
+      "grad_norm": 4.216089248657227,
+      "learning_rate": 2.437745740498034e-05,
+      "loss": 2.5125,
+      "step": 744
+    },
+    {
+      "epoch": 0.025549731315728744,
+      "grad_norm": 4.225554466247559,
+      "learning_rate": 2.5393184796854525e-05,
+      "loss": 2.4973,
+      "step": 775
+    },
+    {
+      "epoch": 0.026571720568357896,
+      "grad_norm": 3.357351541519165,
+      "learning_rate": 2.6408912188728702e-05,
+      "loss": 2.4532,
+      "step": 806
+    },
+    {
+      "epoch": 0.027593709820987043,
+      "grad_norm": 4.109170436859131,
+      "learning_rate": 2.7424639580602886e-05,
+      "loss": 2.4504,
+      "step": 837
+    },
+    {
+      "epoch": 0.028615699073616194,
+      "grad_norm": 17.247940063476562,
+      "learning_rate": 2.8440366972477066e-05,
+      "loss": 2.4226,
+      "step": 868
+    },
+    {
+      "epoch": 0.029637688326245342,
+      "grad_norm": 3.2851662635803223,
+      "learning_rate": 2.9456094364351244e-05,
+      "loss": 2.4053,
+      "step": 899
+    },
+    {
+      "epoch": 0.030659677578874493,
+      "grad_norm": 3.3796141147613525,
+      "learning_rate": 3.0471821756225428e-05,
+      "loss": 2.3977,
+      "step": 930
+    },
+    {
+      "epoch": 0.03168166683150364,
+      "grad_norm": 3.0984764099121094,
+      "learning_rate": 3.148754914809961e-05,
+      "loss": 2.3622,
+      "step": 961
+    },
+    {
+      "epoch": 0.032703656084132796,
+      "grad_norm": 2.5464305877685547,
+      "learning_rate": 3.2503276539973785e-05,
+      "loss": 2.348,
+      "step": 992
+    },
+    {
+      "epoch": 0.03372564533676194,
+      "grad_norm": 2.848860263824463,
+      "learning_rate": 3.351900393184797e-05,
+      "loss": 2.3208,
+      "step": 1023
+    },
+    {
+      "epoch": 0.03474763458939109,
+      "grad_norm": 2.5870606899261475,
+      "learning_rate": 3.453473132372215e-05,
+      "loss": 2.3023,
+      "step": 1054
+    },
+    {
+      "epoch": 0.03576962384202024,
+      "grad_norm": 2.6556804180145264,
+      "learning_rate": 3.555045871559633e-05,
+      "loss": 2.2698,
+      "step": 1085
+    },
+    {
+      "epoch": 0.03679161309464939,
+      "grad_norm": 2.779650926589966,
+      "learning_rate": 3.6566186107470514e-05,
+      "loss": 2.2614,
+      "step": 1116
+    },
+    {
+      "epoch": 0.03781360234727854,
+      "grad_norm": 2.624191999435425,
+      "learning_rate": 3.7581913499344695e-05,
+      "loss": 2.2422,
+      "step": 1147
+    },
+    {
+      "epoch": 0.03883559159990769,
+      "grad_norm": 2.5255484580993652,
+      "learning_rate": 3.8597640891218876e-05,
+      "loss": 2.2419,
+      "step": 1178
+    },
+    {
+      "epoch": 0.03985758085253684,
+      "grad_norm": 2.3195745944976807,
+      "learning_rate": 3.9613368283093056e-05,
+      "loss": 2.2468,
+      "step": 1209
+    },
+    {
+      "epoch": 0.04087957010516599,
+      "grad_norm": 2.4712162017822266,
+      "learning_rate": 4.062909567496724e-05,
+      "loss": 2.2072,
+      "step": 1240
+    },
+    {
+      "epoch": 0.04190155935779514,
+      "grad_norm": 4.451296806335449,
+      "learning_rate": 4.164482306684142e-05,
+      "loss": 2.2136,
+      "step": 1271
+    },
+    {
+      "epoch": 0.04292354861042429,
+      "grad_norm": 2.4180150032043457,
+      "learning_rate": 4.26605504587156e-05,
+      "loss": 2.1843,
+      "step": 1302
+    },
+    {
+      "epoch": 0.04394553786305344,
+      "grad_norm": 2.395840883255005,
+      "learning_rate": 4.367627785058978e-05,
+      "loss": 2.1447,
+      "step": 1333
+    },
+    {
+      "epoch": 0.04496752711568259,
+      "grad_norm": 3.072429895401001,
+      "learning_rate": 4.469200524246396e-05,
+      "loss": 2.1405,
+      "step": 1364
+    },
+    {
+      "epoch": 0.045989516368311736,
+      "grad_norm": 1.9566724300384521,
+      "learning_rate": 4.570773263433814e-05,
+      "loss": 2.1321,
+      "step": 1395
+    },
+    {
+      "epoch": 0.04701150562094089,
+      "grad_norm": 23.60377311706543,
+      "learning_rate": 4.672346002621232e-05,
+      "loss": 2.1289,
+      "step": 1426
+    },
+    {
+      "epoch": 0.04803349487357004,
+      "grad_norm": 2.117250919342041,
+      "learning_rate": 4.77391874180865e-05,
+      "loss": 2.1239,
+      "step": 1457
+    },
+    {
+      "epoch": 0.049055484126199186,
+      "grad_norm": 2.361362934112549,
+      "learning_rate": 4.875491480996068e-05,
+      "loss": 2.0838,
+      "step": 1488
+    },
+    {
+      "epoch": 0.05007747337882834,
+      "grad_norm": 2.1867992877960205,
+      "learning_rate": 4.977064220183487e-05,
+      "loss": 2.0622,
+      "step": 1519
+    },
+    {
+      "epoch": 0.05109946263145749,
+      "grad_norm": 1.9326456785202026,
+      "learning_rate": 4.9999915451558777e-05,
+      "loss": 2.0441,
+      "step": 1550
+    },
+    {
+      "epoch": 0.052121451884086636,
+      "grad_norm": 2.076503038406372,
+      "learning_rate": 4.999955597496219e-05,
+      "loss": 2.0503,
+      "step": 1581
+    },
+    {
+      "epoch": 0.05314344113671579,
+      "grad_norm": 3.051212787628174,
+      "learning_rate": 4.9998914381774255e-05,
+      "loss": 2.0357,
+      "step": 1612
+    },
+    {
+      "epoch": 0.05416543038934494,
+      "grad_norm": 1.7924102544784546,
+      "learning_rate": 4.999799067923527e-05,
+      "loss": 2.0326,
+      "step": 1643
+    },
+    {
+      "epoch": 0.055187419641974086,
+      "grad_norm": 1.8103365898132324,
+      "learning_rate": 4.999678487776908e-05,
+      "loss": 2.0023,
+      "step": 1674
+    },
+    {
+      "epoch": 0.056209408894603234,
+      "grad_norm": 1.913725733757019,
+      "learning_rate": 4.9995296990983006e-05,
+      "loss": 2.0035,
+      "step": 1705
+    },
+    {
+      "epoch": 0.05723139814723239,
+      "grad_norm": 1.7415859699249268,
+      "learning_rate": 4.999352703566763e-05,
+      "loss": 2.0063,
+      "step": 1736
+    },
+    {
+      "epoch": 0.058253387399861536,
+      "grad_norm": 1.8145827054977417,
+      "learning_rate": 4.999147503179668e-05,
+      "loss": 1.9731,
+      "step": 1767
+    },
+    {
+      "epoch": 0.059275376652490684,
+      "grad_norm": 1.8761731386184692,
+      "learning_rate": 4.998914100252672e-05,
+      "loss": 1.9883,
+      "step": 1798
+    },
+    {
+      "epoch": 0.06029736590511984,
+      "grad_norm": 6.824073791503906,
+      "learning_rate": 4.998652497419696e-05,
+      "loss": 1.9713,
+      "step": 1829
+    },
+    {
+      "epoch": 0.061319355157748986,
+      "grad_norm": 1.7231906652450562,
+      "learning_rate": 4.9983626976328927e-05,
+      "loss": 1.9492,
+      "step": 1860
+    },
+    {
+      "epoch": 0.062341344410378134,
+      "grad_norm": 1.6888827085494995,
+      "learning_rate": 4.998044704162613e-05,
+      "loss": 1.9449,
+      "step": 1891
+    },
+    {
+      "epoch": 0.06336333366300728,
+      "grad_norm": 1.5924124717712402,
+      "learning_rate": 4.9976985205973705e-05,
+      "loss": 1.938,
+      "step": 1922
+    },
+    {
+      "epoch": 0.06438532291563644,
+      "grad_norm": 1.7029409408569336,
+      "learning_rate": 4.997324150843799e-05,
+      "loss": 1.9285,
+      "step": 1953
+    },
+    {
+      "epoch": 0.06540731216826559,
+      "grad_norm": 1.5554330348968506,
+      "learning_rate": 4.99692159912661e-05,
+      "loss": 1.9091,
+      "step": 1984
+    },
+    {
+      "epoch": 0.06642930142089473,
+      "grad_norm": 1.5639121532440186,
+      "learning_rate": 4.996490869988546e-05,
+      "loss": 1.9105,
+      "step": 2015
+    },
+    {
+      "epoch": 0.06745129067352389,
+      "grad_norm": 1.6262747049331665,
+      "learning_rate": 4.996031968290326e-05,
+      "loss": 1.9164,
+      "step": 2046
+    },
+    {
+      "epoch": 0.06847327992615304,
+      "grad_norm": 1.5408495664596558,
+      "learning_rate": 4.995544899210594e-05,
+      "loss": 1.8728,
+      "step": 2077
+    },
+    {
+      "epoch": 0.06949526917878218,
+      "grad_norm": 1.5183970928192139,
+      "learning_rate": 4.9950296682458583e-05,
+      "loss": 1.8854,
+      "step": 2108
+    },
+    {
+      "epoch": 0.07051725843141134,
+      "grad_norm": 1.9362810850143433,
+      "learning_rate": 4.994486281210429e-05,
+      "loss": 1.8811,
+      "step": 2139
+    },
+    {
+      "epoch": 0.07153924768404048,
+      "grad_norm": 1.5646640062332153,
+      "learning_rate": 4.9939147442363566e-05,
+      "loss": 1.8744,
+      "step": 2170
+    },
+    {
+      "epoch": 0.07256123693666963,
+      "grad_norm": 1.5929124355316162,
+      "learning_rate": 4.9933150637733574e-05,
+      "loss": 1.867,
+      "step": 2201
+    },
+    {
+      "epoch": 0.07358322618929879,
+      "grad_norm": 1.7689995765686035,
+      "learning_rate": 4.992687246588743e-05,
+      "loss": 1.8659,
+      "step": 2232
+    },
+    {
+      "epoch": 0.07460521544192793,
+      "grad_norm": 1.375406265258789,
+      "learning_rate": 4.992031299767347e-05,
+      "loss": 1.8477,
+      "step": 2263
+    },
+    {
+      "epoch": 0.07562720469455708,
+      "grad_norm": 1.3596042394638062,
+      "learning_rate": 4.9913472307114386e-05,
+      "loss": 1.8498,
+      "step": 2294
+    },
+    {
+      "epoch": 0.07664919394718624,
+      "grad_norm": 1.3918544054031372,
+      "learning_rate": 4.9906350471406446e-05,
+      "loss": 1.8538,
+      "step": 2325
+    },
+    {
+      "epoch": 0.07767118319981538,
+      "grad_norm": 1.4614112377166748,
+      "learning_rate": 4.989894757091861e-05,
+      "loss": 1.8359,
+      "step": 2356
+    },
+    {
+      "epoch": 0.07869317245244453,
+      "grad_norm": 1.563186764717102,
+      "learning_rate": 4.989126368919158e-05,
+      "loss": 1.821,
+      "step": 2387
+    },
+    {
+      "epoch": 0.07971516170507369,
+      "grad_norm": 1.3217226266860962,
+      "learning_rate": 4.988329891293693e-05,
+      "loss": 1.8345,
+      "step": 2418
+    },
+    {
+      "epoch": 0.08073715095770283,
+      "grad_norm": 1.3906276226043701,
+      "learning_rate": 4.987505333203608e-05,
+      "loss": 1.8313,
+      "step": 2449
+    },
+    {
+      "epoch": 0.08175914021033198,
+      "grad_norm": 1.2736890316009521,
+      "learning_rate": 4.9866527039539276e-05,
+      "loss": 1.8234,
+      "step": 2480
+    },
+    {
+      "epoch": 0.08278112946296114,
+      "grad_norm": 1.3050850629806519,
+      "learning_rate": 4.9857720131664594e-05,
+      "loss": 1.8181,
+      "step": 2511
+    },
+    {
+      "epoch": 0.08380311871559028,
+      "grad_norm": 1.3847019672393799,
+      "learning_rate": 4.9848632707796773e-05,
+      "loss": 1.8128,
+      "step": 2542
+    },
+    {
+      "epoch": 0.08482510796821943,
+      "grad_norm": 1.3893433809280396,
+      "learning_rate": 4.9839264870486155e-05,
+      "loss": 1.7871,
+      "step": 2573
+    },
+    {
+      "epoch": 0.08584709722084859,
+      "grad_norm": 1.3469080924987793,
+      "learning_rate": 4.9829616725447526e-05,
+      "loss": 1.8212,
+      "step": 2604
+    },
+    {
+      "epoch": 0.08686908647347773,
+      "grad_norm": 1.269865870475769,
+      "learning_rate": 4.981968838155888e-05,
+      "loss": 1.7868,
+      "step": 2635
+    },
+    {
+      "epoch": 0.08789107572610688,
+      "grad_norm": 1.2972242832183838,
+      "learning_rate": 4.980947995086024e-05,
+      "loss": 1.7987,
+      "step": 2666
+    },
+    {
+      "epoch": 0.08891306497873604,
+      "grad_norm": 1.3488340377807617,
+      "learning_rate": 4.979899154855234e-05,
+      "loss": 1.7859,
+      "step": 2697
+    },
+    {
+      "epoch": 0.08993505423136518,
+      "grad_norm": 1.3487133979797363,
+      "learning_rate": 4.9788223292995386e-05,
+      "loss": 1.7851,
+      "step": 2728
+    },
+    {
+      "epoch": 0.09095704348399433,
+      "grad_norm": 1.2412410974502563,
+      "learning_rate": 4.977717530570768e-05,
+      "loss": 1.7802,
+      "step": 2759
+    },
+    {
+      "epoch": 0.09197903273662347,
+      "grad_norm": 1.3017562627792358,
+      "learning_rate": 4.976584771136425e-05,
+      "loss": 1.775,
+      "step": 2790
+    },
+    {
+      "epoch": 0.09300102198925263,
+      "grad_norm": 1.2923076152801514,
+      "learning_rate": 4.975424063779547e-05,
+      "loss": 1.76,
+      "step": 2821
+    },
+    {
+      "epoch": 0.09402301124188178,
+      "grad_norm": 1.2735223770141602,
+      "learning_rate": 4.974235421598557e-05,
+      "loss": 1.7604,
+      "step": 2852
+    },
+    {
+      "epoch": 0.09504500049451092,
+      "grad_norm": 1.303673505783081,
+      "learning_rate": 4.973018858007122e-05,
+      "loss": 1.7685,
+      "step": 2883
+    },
+    {
+      "epoch": 0.09606698974714008,
+      "grad_norm": 1.5336410999298096,
+      "learning_rate": 4.9717743867339963e-05,
+      "loss": 1.7682,
+      "step": 2914
+    },
+    {
+      "epoch": 0.09708897899976923,
+      "grad_norm": 5.014227867126465,
+      "learning_rate": 4.9705020218228695e-05,
+      "loss": 1.7617,
+      "step": 2945
+    },
+    {
+      "epoch": 0.09811096825239837,
+      "grad_norm": 1.2603938579559326,
+      "learning_rate": 4.969201777632205e-05,
+      "loss": 1.7621,
+      "step": 2976
+    },
+    {
+      "epoch": 0.09913295750502753,
+      "grad_norm": 1.32491934299469,
+      "learning_rate": 4.9678736688350846e-05,
+      "loss": 1.7411,
+      "step": 3007
+    },
+    {
+      "epoch": 0.10015494675765668,
+      "grad_norm": 1.206735372543335,
+      "learning_rate": 4.966517710419033e-05,
+      "loss": 1.7262,
+      "step": 3038
+    },
+    {
+      "epoch": 0.10117693601028582,
+      "grad_norm": 1.254231572151184,
+      "learning_rate": 4.965133917685858e-05,
+      "loss": 1.7454,
+      "step": 3069
+    },
+    {
+      "epoch": 0.10219892526291498,
+      "grad_norm": 1.3085408210754395,
+      "learning_rate": 4.9637223062514714e-05,
+      "loss": 1.7517,
+      "step": 3100
+    },
+    {
+      "epoch": 0.10322091451554413,
+      "grad_norm": 1.3184605836868286,
+      "learning_rate": 4.962282892045718e-05,
+      "loss": 1.7542,
+      "step": 3131
+    },
+    {
+      "epoch": 0.10424290376817327,
+      "grad_norm": 1.2284983396530151,
+      "learning_rate": 4.9608156913121904e-05,
+      "loss": 1.738,
+      "step": 3162
+    },
+    {
+      "epoch": 0.10526489302080243,
+      "grad_norm": 1.3870880603790283,
+      "learning_rate": 4.959320720608049e-05,
+      "loss": 1.7358,
+      "step": 3193
+    },
+    {
+      "epoch": 0.10628688227343158,
+      "grad_norm": 1.1335322856903076,
+      "learning_rate": 4.9577979968038354e-05,
+      "loss": 1.742,
+      "step": 3224
+    },
+    {
+      "epoch": 0.10730887152606072,
+      "grad_norm": 1.1794465780258179,
+      "learning_rate": 4.956247537083282e-05,
+      "loss": 1.7357,
+      "step": 3255
+    },
+    {
+      "epoch": 0.10833086077868988,
+      "grad_norm": 1.1701149940490723,
+      "learning_rate": 4.9546693589431145e-05,
+      "loss": 1.7289,
+      "step": 3286
+    },
+    {
+      "epoch": 0.10935285003131903,
+      "grad_norm": 1.169094443321228,
+      "learning_rate": 4.9530634801928595e-05,
+      "loss": 1.7238,
+      "step": 3317
+    },
+    {
+      "epoch": 0.11037483928394817,
+      "grad_norm": 1.2735379934310913,
+      "learning_rate": 4.9514299189546395e-05,
+      "loss": 1.7275,
+      "step": 3348
+    },
+    {
+      "epoch": 0.11139682853657733,
+      "grad_norm": 1.2806981801986694,
+      "learning_rate": 4.949768693662973e-05,
+      "loss": 1.7135,
+      "step": 3379
+    },
+    {
+      "epoch": 0.11241881778920647,
+      "grad_norm": 1.208024263381958,
+      "learning_rate": 4.948079823064559e-05,
+      "loss": 1.7251,
+      "step": 3410
+    },
+    {
+      "epoch": 0.11344080704183562,
+      "grad_norm": 1.275516152381897,
+      "learning_rate": 4.946363326218074e-05,
+      "loss": 1.7259,
+      "step": 3441
+    },
+    {
+      "epoch": 0.11446279629446478,
+      "grad_norm": 1.1761465072631836,
+      "learning_rate": 4.9446192224939525e-05,
+      "loss": 1.7024,
+      "step": 3472
+    },
+    {
+      "epoch": 0.11548478554709392,
+      "grad_norm": 1.1216075420379639,
+      "learning_rate": 4.942847531574167e-05,
+      "loss": 1.6849,
+      "step": 3503
+    },
+    {
+      "epoch": 0.11650677479972307,
+      "grad_norm": 1.1286563873291016,
+      "learning_rate": 4.941048273452008e-05,
+      "loss": 1.7004,
+      "step": 3534
+    },
+    {
+      "epoch": 0.11752876405235223,
+      "grad_norm": 1.1531614065170288,
+      "learning_rate": 4.9392214684318605e-05,
+      "loss": 1.7101,
+      "step": 3565
+    },
+    {
+      "epoch": 0.11855075330498137,
+      "grad_norm": 1.143051266670227,
+      "learning_rate": 4.93736713712897e-05,
+      "loss": 1.7127,
+      "step": 3596
+    },
+    {
+      "epoch": 0.11957274255761052,
+      "grad_norm": 1.1483272314071655,
+      "learning_rate": 4.9354853004692124e-05,
+      "loss": 1.6968,
+      "step": 3627
+    },
+    {
+      "epoch": 0.12059473181023968,
+      "grad_norm": 1.1267555952072144,
+      "learning_rate": 4.93357597968886e-05,
+      "loss": 1.7023,
+      "step": 3658
+    },
+    {
+      "epoch": 0.12161672106286882,
+      "grad_norm": 1.1552249193191528,
+      "learning_rate": 4.931639196334338e-05,
+      "loss": 1.7171,
+      "step": 3689
+    },
+    {
+      "epoch": 0.12263871031549797,
+      "grad_norm": 1.1388061046600342,
+      "learning_rate": 4.9296749722619826e-05,
+      "loss": 1.7061,
+      "step": 3720
+    },
+    {
+      "epoch": 0.12366069956812713,
+      "grad_norm": 1.127455234527588,
+      "learning_rate": 4.9276833296377966e-05,
+      "loss": 1.6879,
+      "step": 3751
+    },
+    {
+      "epoch": 0.12468268882075627,
+      "grad_norm": 1.1534373760223389,
+      "learning_rate": 4.925664290937196e-05,
+      "loss": 1.7091,
+      "step": 3782
+    },
+    {
+      "epoch": 0.12570467807338542,
+      "grad_norm": 1.2369154691696167,
+      "learning_rate": 4.9236178789447576e-05,
+      "loss": 1.6923,
+      "step": 3813
+    },
+    {
+      "epoch": 0.12672666732601456,
+      "grad_norm": 1.074436068534851,
+      "learning_rate": 4.921544116753962e-05,
+      "loss": 1.6805,
+      "step": 3844
+    },
+    {
+      "epoch": 0.12774865657864373,
+      "grad_norm": 1.112226963043213,
+      "learning_rate": 4.919443027766935e-05,
+      "loss": 1.6527,
+      "step": 3875
+    },
+    {
+      "epoch": 0.12877064583127287,
+      "grad_norm": 1.0999863147735596,
+      "learning_rate": 4.91731463569418e-05,
+      "loss": 1.6614,
+      "step": 3906
+    },
+    {
+      "epoch": 0.129792635083902,
+      "grad_norm": 1.098036527633667,
+      "learning_rate": 4.915158964554312e-05,
+      "loss": 1.6826,
+      "step": 3937
+    },
+    {
+      "epoch": 0.13081462433653118,
+      "grad_norm": 1.1108450889587402,
+      "learning_rate": 4.912976038673786e-05,
+      "loss": 1.6886,
+      "step": 3968
+    },
+    {
+      "epoch": 0.13183661358916032,
+      "grad_norm": 1.0916872024536133,
+      "learning_rate": 4.9107658826866254e-05,
+      "loss": 1.6782,
+      "step": 3999
+    },
+    {
+      "epoch": 0.13285860284178946,
+      "grad_norm": 1.0818581581115723,
+      "learning_rate": 4.908528521534139e-05,
+      "loss": 1.6796,
+      "step": 4030
+    },
+    {
+      "epoch": 0.13388059209441863,
+      "grad_norm": 1.0908610820770264,
+      "learning_rate": 4.906263980464644e-05,
+      "loss": 1.6662,
+      "step": 4061
+    },
+    {
+      "epoch": 0.13490258134704777,
+      "grad_norm": 1.0384143590927124,
+      "learning_rate": 4.903972285033178e-05,
+      "loss": 1.6811,
+      "step": 4092
+    },
+    {
+      "epoch": 0.1359245705996769,
+      "grad_norm": 1.0998533964157104,
+      "learning_rate": 4.901653461101213e-05,
+      "loss": 1.6817,
+      "step": 4123
+    },
+    {
+      "epoch": 0.13694655985230608,
+      "grad_norm": 1.1726231575012207,
+      "learning_rate": 4.8993075348363626e-05,
+      "loss": 1.6532,
+      "step": 4154
+    },
+    {
+      "epoch": 0.13796854910493522,
+      "grad_norm": 1.075464129447937,
+      "learning_rate": 4.896934532712084e-05,
+      "loss": 1.671,
+      "step": 4185
+    },
+    {
+      "epoch": 0.13899053835756436,
+      "grad_norm": 1.0557868480682373,
+      "learning_rate": 4.8945344815073846e-05,
+      "loss": 1.6548,
+      "step": 4216
+    },
+    {
+      "epoch": 0.14001252761019353,
+      "grad_norm": 1.0531095266342163,
+      "learning_rate": 4.892107408306516e-05,
+      "loss": 1.6526,
+      "step": 4247
+    },
+    {
+      "epoch": 0.14103451686282267,
+      "grad_norm": 1.138203501701355,
+      "learning_rate": 4.889653340498669e-05,
+      "loss": 1.678,
+      "step": 4278
+    },
+    {
+      "epoch": 0.1420565061154518,
+      "grad_norm": 1.0668121576309204,
+      "learning_rate": 4.8871723057776664e-05,
+      "loss": 1.6552,
+      "step": 4309
+    },
+    {
+      "epoch": 0.14307849536808095,
+      "grad_norm": 1.0312261581420898,
+      "learning_rate": 4.8846643321416476e-05,
+      "loss": 1.6731,
+      "step": 4340
+    },
+    {
+      "epoch": 0.14410048462071012,
+      "grad_norm": 1.0868667364120483,
+      "learning_rate": 4.882129447892753e-05,
+      "loss": 1.6713,
+      "step": 4371
+    },
+    {
+      "epoch": 0.14512247387333926,
+      "grad_norm": 1.0213130712509155,
+      "learning_rate": 4.8795676816368076e-05,
+      "loss": 1.6515,
+      "step": 4402
+    },
+    {
+      "epoch": 0.1461444631259684,
+      "grad_norm": 1.190875768661499,
+      "learning_rate": 4.876979062282995e-05,
+      "loss": 1.651,
+      "step": 4433
+    },
+    {
+      "epoch": 0.14716645237859757,
+      "grad_norm": 1.0551568269729614,
+      "learning_rate": 4.8743636190435325e-05,
+      "loss": 1.6751,
+      "step": 4464
+    },
+    {
+      "epoch": 0.1481884416312267,
+      "grad_norm": 1.0654323101043701,
+      "learning_rate": 4.871721381433344e-05,
+      "loss": 1.6499,
+      "step": 4495
+    },
+    {
+      "epoch": 0.14921043088385585,
+      "grad_norm": 1.04425048828125,
+      "learning_rate": 4.869052379269719e-05,
+      "loss": 1.6401,
+      "step": 4526
+    },
+    {
+      "epoch": 0.15023242013648502,
+      "grad_norm": 1.3416290283203125,
+      "learning_rate": 4.866356642671985e-05,
+      "loss": 1.6553,
+      "step": 4557
+    },
+    {
+      "epoch": 0.15125440938911416,
+      "grad_norm": 1.073529601097107,
+      "learning_rate": 4.8636342020611634e-05,
+      "loss": 1.6413,
+      "step": 4588
+    },
+    {
+      "epoch": 0.1522763986417433,
+      "grad_norm": 1.0386462211608887,
+      "learning_rate": 4.860885088159626e-05,
+      "loss": 1.6595,
+      "step": 4619
+    },
+    {
+      "epoch": 0.15329838789437247,
+      "grad_norm": 1.0544514656066895,
+      "learning_rate": 4.858109331990751e-05,
+      "loss": 1.6387,
+      "step": 4650
+    },
+    {
+      "epoch": 0.15432037714700161,
+      "grad_norm": 1.088112473487854,
+      "learning_rate": 4.855306964878567e-05,
+      "loss": 1.628,
+      "step": 4681
+    },
+    {
+      "epoch": 0.15534236639963075,
+      "grad_norm": 0.9930492639541626,
+      "learning_rate": 4.8524780184474084e-05,
+      "loss": 1.6554,
+      "step": 4712
+    },
+    {
+      "epoch": 0.15636435565225992,
+      "grad_norm": 0.9864984154701233,
+      "learning_rate": 4.8496225246215496e-05,
+      "loss": 1.6558,
+      "step": 4743
+    },
+    {
+      "epoch": 0.15738634490488906,
+      "grad_norm": 1.0170128345489502,
+      "learning_rate": 4.8467405156248505e-05,
+      "loss": 1.6289,
+      "step": 4774
+    },
+    {
+      "epoch": 0.1584083341575182,
+      "grad_norm": 1.0360223054885864,
+      "learning_rate": 4.843832023980392e-05,
+      "loss": 1.6314,
+      "step": 4805
+    },
+    {
+      "epoch": 0.15943032341014737,
+      "grad_norm": 1.0165129899978638,
+      "learning_rate": 4.840897082510106e-05,
+      "loss": 1.6294,
+      "step": 4836
+    },
+    {
+      "epoch": 0.16045231266277651,
+      "grad_norm": 1.079991102218628,
+      "learning_rate": 4.8379357243344084e-05,
+      "loss": 1.6204,
+      "step": 4867
+    },
+    {
+      "epoch": 0.16147430191540565,
+      "grad_norm": 1.0515645742416382,
+      "learning_rate": 4.8349479828718236e-05,
+      "loss": 1.6322,
+      "step": 4898
+    },
+    {
+      "epoch": 0.16249629116803482,
+      "grad_norm": 1.0226655006408691,
+      "learning_rate": 4.8319338918386075e-05,
+      "loss": 1.6476,
+      "step": 4929
+    },
+    {
+      "epoch": 0.16351828042066396,
+      "grad_norm": 1.0581114292144775,
+      "learning_rate": 4.828893485248369e-05,
+      "loss": 1.6302,
+      "step": 4960
+    },
+    {
+      "epoch": 0.1645402696732931,
+      "grad_norm": 1.0156742334365845,
+      "learning_rate": 4.825826797411682e-05,
+      "loss": 1.6292,
+      "step": 4991
+    },
+    {
+      "epoch": 0.16556225892592227,
+      "grad_norm": 1.0153559446334839,
+      "learning_rate": 4.822733862935702e-05,
+      "loss": 1.6367,
+      "step": 5022
+    },
+    {
+      "epoch": 0.16658424817855141,
+      "grad_norm": 1.0488505363464355,
+      "learning_rate": 4.819614716723775e-05,
+      "loss": 1.644,
+      "step": 5053
+    },
+    {
+      "epoch": 0.16760623743118055,
+      "grad_norm": 1.092781901359558,
+      "learning_rate": 4.8164693939750425e-05,
+      "loss": 1.6318,
+      "step": 5084
+    },
+    {
+      "epoch": 0.16862822668380972,
+      "grad_norm": 0.9972744584083557,
+      "learning_rate": 4.813297930184042e-05,
+      "loss": 1.6206,
+      "step": 5115
+    },
+    {
+      "epoch": 0.16965021593643886,
+      "grad_norm": 1.0455750226974487,
+      "learning_rate": 4.810100361140314e-05,
+      "loss": 1.6296,
+      "step": 5146
+    },
+    {
+      "epoch": 0.170672205189068,
+      "grad_norm": 0.9624122977256775,
+      "learning_rate": 4.8068767229279885e-05,
+      "loss": 1.6307,
+      "step": 5177
+    },
+    {
+      "epoch": 0.17169419444169717,
+      "grad_norm": 1.4828526973724365,
+      "learning_rate": 4.8036270519253854e-05,
+      "loss": 1.6377,
+      "step": 5208
+    },
+    {
+      "epoch": 0.17271618369432631,
+      "grad_norm": 1.0732771158218384,
+      "learning_rate": 4.8003513848046e-05,
+      "loss": 1.6148,
+      "step": 5239
+    },
+    {
+      "epoch": 0.17373817294695545,
+      "grad_norm": 1.0065757036209106,
+      "learning_rate": 4.79704975853109e-05,
+      "loss": 1.6192,
+      "step": 5270
+    },
+    {
+      "epoch": 0.17476016219958462,
+      "grad_norm": 1.7071099281311035,
+      "learning_rate": 4.793722210363262e-05,
+      "loss": 1.6205,
+      "step": 5301
+    },
+    {
+      "epoch": 0.17578215145221376,
+      "grad_norm": 1.009507417678833,
+      "learning_rate": 4.7903687778520414e-05,
+      "loss": 1.6261,
+      "step": 5332
+    },
+    {
+      "epoch": 0.1768041407048429,
+      "grad_norm": 1.0593280792236328,
+      "learning_rate": 4.7869894988404593e-05,
+      "loss": 1.6286,
+      "step": 5363
+    },
+    {
+      "epoch": 0.17782612995747207,
+      "grad_norm": 1.0053679943084717,
+      "learning_rate": 4.783584411463221e-05,
+      "loss": 1.6424,
+      "step": 5394
+    },
+    {
+      "epoch": 0.17884811921010121,
+      "grad_norm": 0.983214795589447,
+      "learning_rate": 4.780153554146274e-05,
+      "loss": 1.6292,
+      "step": 5425
+    },
+    {
+      "epoch": 0.17987010846273035,
+      "grad_norm": 0.9617491960525513,
+      "learning_rate": 4.7766969656063766e-05,
+      "loss": 1.6182,
+      "step": 5456
+    },
+    {
+      "epoch": 0.18089209771535952,
+      "grad_norm": 1.0862797498703003,
+      "learning_rate": 4.773214684850662e-05,
+      "loss": 1.6213,
+      "step": 5487
+    },
+    {
+      "epoch": 0.18191408696798866,
+      "grad_norm": 1.0468218326568604,
+      "learning_rate": 4.769706751176193e-05,
+      "loss": 1.6176,
+      "step": 5518
+    },
+    {
+      "epoch": 0.1829360762206178,
+      "grad_norm": 0.9474911093711853,
+      "learning_rate": 4.7661732041695264e-05,
+      "loss": 1.5864,
+      "step": 5549
+    },
+    {
+      "epoch": 0.18395806547324695,
+      "grad_norm": 0.9839109778404236,
+      "learning_rate": 4.762614083706258e-05,
+      "loss": 1.6177,
+      "step": 5580
+    },
+    {
+      "epoch": 0.18498005472587611,
+      "grad_norm": 1.9305601119995117,
+      "learning_rate": 4.759029429950581e-05,
+      "loss": 1.6132,
+      "step": 5611
+    },
+    {
+      "epoch": 0.18600204397850525,
+      "grad_norm": 0.9609850645065308,
+      "learning_rate": 4.7554192833548235e-05,
+      "loss": 1.6115,
+      "step": 5642
+    },
+    {
+      "epoch": 0.1870240332311344,
+      "grad_norm": 1.0501559972763062,
+      "learning_rate": 4.751783684659e-05,
+      "loss": 1.6017,
+      "step": 5673
+    },
+    {
+      "epoch": 0.18804602248376356,
+      "grad_norm": 0.9933464527130127,
+      "learning_rate": 4.748122674890348e-05,
+      "loss": 1.6136,
+      "step": 5704
+    },
+    {
+      "epoch": 0.1890680117363927,
+      "grad_norm": 0.9463350772857666,
+      "learning_rate": 4.7444362953628654e-05,
+      "loss": 1.6102,
+      "step": 5735
+    },
+    {
+      "epoch": 0.19009000098902185,
+      "grad_norm": 0.9974256753921509,
+      "learning_rate": 4.7407245876768424e-05,
+      "loss": 1.6101,
+      "step": 5766
+    },
+    {
+      "epoch": 0.19111199024165101,
+      "grad_norm": 0.9747878313064575,
+      "learning_rate": 4.736987593718397e-05,
+      "loss": 1.5967,
+      "step": 5797
+    },
+    {
+      "epoch": 0.19213397949428015,
+      "grad_norm": 0.9755719900131226,
+      "learning_rate": 4.733225355658999e-05,
+      "loss": 1.5987,
+      "step": 5828
+    },
+    {
+      "epoch": 0.1931559687469093,
+      "grad_norm": 0.9605233669281006,
+      "learning_rate": 4.7294379159549926e-05,
+      "loss": 1.6238,
+      "step": 5859
+    },
+    {
+      "epoch": 0.19417795799953846,
+      "grad_norm": 0.9777940511703491,
+      "learning_rate": 4.725625317347119e-05,
+      "loss": 1.5976,
+      "step": 5890
+    },
+    {
+      "epoch": 0.1951999472521676,
+      "grad_norm": 0.9619265198707581,
+      "learning_rate": 4.7217876028600374e-05,
+      "loss": 1.5985,
+      "step": 5921
+    },
+    {
+      "epoch": 0.19622193650479675,
+      "grad_norm": 0.970813512802124,
+      "learning_rate": 4.717924815801832e-05,
+      "loss": 1.6097,
+      "step": 5952
+    },
+    {
+      "epoch": 0.19724392575742591,
+      "grad_norm": 1.1910721063613892,
+      "learning_rate": 4.714036999763532e-05,
+      "loss": 1.6156,
+      "step": 5983
+    },
+    {
+      "epoch": 0.19826591501005505,
+      "grad_norm": 1.1106246709823608,
+      "learning_rate": 4.7101241986186116e-05,
+      "loss": 1.5761,
+      "step": 6014
+    },
+    {
+      "epoch": 0.1992879042626842,
+      "grad_norm": 1.0065436363220215,
+      "learning_rate": 4.7061864565225e-05,
+      "loss": 1.5857,
+      "step": 6045
+    },
+    {
+      "epoch": 0.20030989351531336,
+      "grad_norm": 0.9245477914810181,
+      "learning_rate": 4.702223817912081e-05,
+      "loss": 1.6099,
+      "step": 6076
+    },
+    {
+      "epoch": 0.2013318827679425,
+      "grad_norm": 0.9705063104629517,
+      "learning_rate": 4.698236327505195e-05,
+      "loss": 1.5995,
+      "step": 6107
+    },
+    {
+      "epoch": 0.20235387202057165,
+      "grad_norm": 0.9455100893974304,
+      "learning_rate": 4.694224030300127e-05,
+      "loss": 1.6302,
+      "step": 6138
+    },
+    {
+      "epoch": 0.20337586127320081,
+      "grad_norm": 0.9505909085273743,
+      "learning_rate": 4.690186971575107e-05,
+      "loss": 1.5799,
+      "step": 6169
+    },
+    {
+      "epoch": 0.20439785052582995,
+      "grad_norm": 0.9440078139305115,
+      "learning_rate": 4.6861251968877916e-05,
+      "loss": 1.5889,
+      "step": 6200
+    },
+    {
+      "epoch": 0.2054198397784591,
+      "grad_norm": 0.9610021710395813,
+      "learning_rate": 4.68203875207476e-05,
+      "loss": 1.6049,
+      "step": 6231
+    },
+    {
+      "epoch": 0.20644182903108826,
+      "grad_norm": 0.9686371684074402,
+      "learning_rate": 4.677927683250983e-05,
+      "loss": 1.5985,
+      "step": 6262
+    },
+    {
+      "epoch": 0.2074638182837174,
+      "grad_norm": 0.9532095789909363,
+      "learning_rate": 4.6737920368093156e-05,
+      "loss": 1.5763,
+      "step": 6293
+    },
+    {
+      "epoch": 0.20848580753634655,
+      "grad_norm": 0.9185531139373779,
+      "learning_rate": 4.669631859419965e-05,
+      "loss": 1.5719,
+      "step": 6324
+    },
+    {
+      "epoch": 0.20950779678897571,
+      "grad_norm": 0.917314350605011,
+      "learning_rate": 4.6654471980299676e-05,
+      "loss": 1.5634,
+      "step": 6355
+    },
+    {
+      "epoch": 0.21052978604160485,
+      "grad_norm": 0.9497798681259155,
+      "learning_rate": 4.661238099862658e-05,
+      "loss": 1.5836,
+      "step": 6386
+    },
+    {
+      "epoch": 0.211551775294234,
+      "grad_norm": 0.939011812210083,
+      "learning_rate": 4.657004612417138e-05,
+      "loss": 1.601,
+      "step": 6417
+    },
+    {
+      "epoch": 0.21257376454686316,
+      "grad_norm": 0.981315016746521,
+      "learning_rate": 4.6527467834677374e-05,
+      "loss": 1.5896,
+      "step": 6448
+    },
+    {
+      "epoch": 0.2135957537994923,
+      "grad_norm": 0.9485774636268616,
+      "learning_rate": 4.648464661063478e-05,
+      "loss": 1.5912,
+      "step": 6479
+    },
+    {
+      "epoch": 0.21461774305212145,
+      "grad_norm": 0.9504795670509338,
+      "learning_rate": 4.6441582935275264e-05,
+      "loss": 1.5827,
+      "step": 6510
+    },
+    {
+      "epoch": 0.21563973230475061,
+      "grad_norm": 0.9627436399459839,
+      "learning_rate": 4.6398277294566586e-05,
+      "loss": 1.5858,
+      "step": 6541
+    },
+    {
+      "epoch": 0.21666172155737976,
+      "grad_norm": 0.9468591809272766,
+      "learning_rate": 4.6354730177207e-05,
+      "loss": 1.5884,
+      "step": 6572
+    },
+    {
+      "epoch": 0.2176837108100089,
+      "grad_norm": 0.9847991466522217,
+      "learning_rate": 4.6310942074619787e-05,
+      "loss": 1.5744,
+      "step": 6603
+    },
+    {
+      "epoch": 0.21870570006263806,
+      "grad_norm": 0.9207347631454468,
+      "learning_rate": 4.626691348094777e-05,
+      "loss": 1.5675,
+      "step": 6634
+    },
+    {
+      "epoch": 0.2197276893152672,
+      "grad_norm": 0.9114487171173096,
+      "learning_rate": 4.622264489304762e-05,
+      "loss": 1.5726,
+      "step": 6665
+    },
+    {
+      "epoch": 0.22074967856789635,
+      "grad_norm": 0.9141913652420044,
+      "learning_rate": 4.617813681048434e-05,
+      "loss": 1.5757,
+      "step": 6696
+    },
+    {
+      "epoch": 0.2217716678205255,
+      "grad_norm": 0.9770637154579163,
+      "learning_rate": 4.61333897355256e-05,
+      "loss": 1.5819,
+      "step": 6727
+    },
+    {
+      "epoch": 0.22279365707315466,
+      "grad_norm": 0.9790964126586914,
+      "learning_rate": 4.608840417313604e-05,
+      "loss": 1.5793,
+      "step": 6758
+    },
+    {
+      "epoch": 0.2238156463257838,
+      "grad_norm": 0.9311193227767944,
+      "learning_rate": 4.6043180630971646e-05,
+      "loss": 1.5823,
+      "step": 6789
+    },
+    {
+      "epoch": 0.22483763557841294,
+      "grad_norm": 0.934339165687561,
+      "learning_rate": 4.599771961937391e-05,
+      "loss": 1.5643,
+      "step": 6820
+    },
+    {
+      "epoch": 0.2258596248310421,
+      "grad_norm": 0.9052058458328247,
+      "learning_rate": 4.5952021651364204e-05,
+      "loss": 1.5752,
+      "step": 6851
+    },
+    {
+      "epoch": 0.22688161408367125,
+      "grad_norm": 0.9528570175170898,
+      "learning_rate": 4.590608724263786e-05,
+      "loss": 1.5603,
+      "step": 6882
+    },
+    {
+      "epoch": 0.2279036033363004,
+      "grad_norm": 0.9073063135147095,
+      "learning_rate": 4.585991691155845e-05,
+      "loss": 1.555,
+      "step": 6913
+    },
+    {
+      "epoch": 0.22892559258892956,
+      "grad_norm": 0.9537662267684937,
+      "learning_rate": 4.581351117915188e-05,
+      "loss": 1.5662,
+      "step": 6944
+    },
+    {
+      "epoch": 0.2299475818415587,
+      "grad_norm": 0.9296181201934814,
+      "learning_rate": 4.5766870569100534e-05,
+      "loss": 1.5649,
+      "step": 6975
+    },
+    {
+      "epoch": 0.23096957109418784,
+      "grad_norm": 0.947211503982544,
+      "learning_rate": 4.571999560773736e-05,
+      "loss": 1.5834,
+      "step": 7006
+    },
+    {
+      "epoch": 0.231991560346817,
+      "grad_norm": 0.9705089330673218,
+      "learning_rate": 4.5672886824039915e-05,
+      "loss": 1.5817,
+      "step": 7037
+    },
+    {
+      "epoch": 0.23301354959944615,
+      "grad_norm": 0.9289253950119019,
+      "learning_rate": 4.5625544749624435e-05,
+      "loss": 1.5792,
+      "step": 7068
+    },
+    {
+      "epoch": 0.2340355388520753,
+      "grad_norm": 0.9166892766952515,
+      "learning_rate": 4.5577969918739794e-05,
+      "loss": 1.559,
+      "step": 7099
+    },
+    {
+      "epoch": 0.23505752810470446,
+      "grad_norm": 0.9205060601234436,
+      "learning_rate": 4.5530162868261486e-05,
+      "loss": 1.5564,
+      "step": 7130
+    },
+    {
+      "epoch": 0.2360795173573336,
+      "grad_norm": 0.9769343733787537,
+      "learning_rate": 4.548212413768558e-05,
+      "loss": 1.5499,
+      "step": 7161
+    },
+    {
+      "epoch": 0.23710150660996274,
+      "grad_norm": 1.0154651403427124,
+      "learning_rate": 4.543385426912261e-05,
+      "loss": 1.5832,
+      "step": 7192
+    },
+    {
+      "epoch": 0.2381234958625919,
+      "grad_norm": 0.9247255325317383,
+      "learning_rate": 4.53853538072915e-05,
+      "loss": 1.5844,
+      "step": 7223
+    },
+    {
+      "epoch": 0.23914548511522105,
+      "grad_norm": 0.8840001225471497,
+      "learning_rate": 4.533662329951336e-05,
+      "loss": 1.5456,
+      "step": 7254
+    },
+    {
+      "epoch": 0.2401674743678502,
+      "grad_norm": 0.986392080783844,
+      "learning_rate": 4.528766329570536e-05,
+      "loss": 1.5743,
+      "step": 7285
+    },
+    {
+      "epoch": 0.24118946362047936,
+      "grad_norm": 0.8750962615013123,
+      "learning_rate": 4.523847434837447e-05,
+      "loss": 1.5751,
+      "step": 7316
+    },
+    {
+      "epoch": 0.2422114528731085,
+      "grad_norm": 0.9039379954338074,
+      "learning_rate": 4.518905701261128e-05,
+      "loss": 1.5603,
+      "step": 7347
+    },
+    {
+      "epoch": 0.24323344212573764,
+      "grad_norm": 0.9081151485443115,
+      "learning_rate": 4.5139411846083715e-05,
+      "loss": 1.5542,
+      "step": 7378
+    },
+    {
+      "epoch": 0.2442554313783668,
+      "grad_norm": 1.532193899154663,
+      "learning_rate": 4.508953940903073e-05,
+      "loss": 1.5693,
+      "step": 7409
+    },
+    {
+      "epoch": 0.24527742063099595,
+      "grad_norm": 0.9598657488822937,
+      "learning_rate": 4.5039440264255994e-05,
+      "loss": 1.5672,
+      "step": 7440
+    },
+    {
+      "epoch": 0.2462994098836251,
+      "grad_norm": 1.3318407535552979,
+      "learning_rate": 4.498911497712155e-05,
+      "loss": 1.5739,
+      "step": 7471
+    },
+    {
+      "epoch": 0.24732139913625426,
+      "grad_norm": 0.9309579730033875,
+      "learning_rate": 4.493856411554142e-05,
+      "loss": 1.5504,
+      "step": 7502
+    },
+    {
+      "epoch": 0.2483433883888834,
+      "grad_norm": 0.9426462650299072,
+      "learning_rate": 4.4887788249975206e-05,
+      "loss": 1.5529,
+      "step": 7533
+    },
+    {
+      "epoch": 0.24936537764151254,
+      "grad_norm": 0.9388718605041504,
+      "learning_rate": 4.4836787953421656e-05,
+      "loss": 1.5589,
+      "step": 7564
+    },
+    {
+      "epoch": 0.2503873668941417,
+      "grad_norm": 0.8922486901283264,
+      "learning_rate": 4.478556380141218e-05,
+      "loss": 1.5453,
+      "step": 7595
+    },
+    {
+      "epoch": 0.25140935614677085,
+      "grad_norm": 0.9597366452217102,
+      "learning_rate": 4.4734116372004375e-05,
+      "loss": 1.5565,
+      "step": 7626
+    },
+    {
+      "epoch": 0.2524313453994,
+      "grad_norm": 0.880445659160614,
+      "learning_rate": 4.4682446245775477e-05,
+      "loss": 1.5429,
+      "step": 7657
+    },
+    {
+      "epoch": 0.2534533346520291,
+      "grad_norm": 0.8895862102508545,
+      "learning_rate": 4.463055400581586e-05,
+      "loss": 1.5462,
+      "step": 7688
+    },
+    {
+      "epoch": 0.25447532390465827,
+      "grad_norm": 0.8859049677848816,
+      "learning_rate": 4.4578440237722374e-05,
+      "loss": 1.5678,
+      "step": 7719
+    },
+    {
+      "epoch": 0.25549731315728746,
+      "grad_norm": 0.9074852466583252,
+      "learning_rate": 4.452610552959183e-05,
+      "loss": 1.5695,
+      "step": 7750
+    },
+    {
+      "epoch": 0.2565193024099166,
+      "grad_norm": 0.9472444653511047,
+      "learning_rate": 4.447355047201428e-05,
+      "loss": 1.5527,
+      "step": 7781
+    },
+    {
+      "epoch": 0.25754129166254575,
+      "grad_norm": 0.901016891002655,
+      "learning_rate": 4.4420775658066414e-05,
+      "loss": 1.5523,
+      "step": 7812
+    },
+    {
+      "epoch": 0.2585632809151749,
+      "grad_norm": 0.8963896632194519,
+      "learning_rate": 4.436778168330484e-05,
+      "loss": 1.5623,
+      "step": 7843
+    },
+    {
+      "epoch": 0.259585270167804,
+      "grad_norm": 0.9571655988693237,
+      "learning_rate": 4.4314569145759353e-05,
+      "loss": 1.5446,
+      "step": 7874
+    },
+    {
+      "epoch": 0.26060725942043317,
+      "grad_norm": 0.9321922659873962,
+      "learning_rate": 4.42611386459262e-05,
+      "loss": 1.5514,
+      "step": 7905
+    },
+    {
+      "epoch": 0.26162924867306236,
+      "grad_norm": 0.8753949403762817,
+      "learning_rate": 4.420749078676133e-05,
+      "loss": 1.5524,
+      "step": 7936
+    },
+    {
+      "epoch": 0.2626512379256915,
+      "grad_norm": 0.8667870759963989,
+      "learning_rate": 4.4153626173673516e-05,
+      "loss": 1.5435,
+      "step": 7967
+    },
+    {
+      "epoch": 0.26367322717832065,
+      "grad_norm": 0.926670491695404,
+      "learning_rate": 4.409954541451762e-05,
+      "loss": 1.5448,
+      "step": 7998
+    },
+    {
+      "epoch": 0.2646952164309498,
+      "grad_norm": 0.9438245892524719,
+      "learning_rate": 4.404524911958764e-05,
+      "loss": 1.5706,
+      "step": 8029
+    },
+    {
+      "epoch": 0.2657172056835789,
+      "grad_norm": 0.9131088256835938,
+      "learning_rate": 4.399073790160989e-05,
+      "loss": 1.5361,
+      "step": 8060
+    },
+    {
+      "epoch": 0.26673919493620807,
+      "grad_norm": 0.914857804775238,
+      "learning_rate": 4.393601237573607e-05,
+      "loss": 1.5588,
+      "step": 8091
+    },
+    {
+      "epoch": 0.26776118418883726,
+      "grad_norm": 0.9113429188728333,
+      "learning_rate": 4.388107315953628e-05,
+      "loss": 1.5603,
+      "step": 8122
+    },
+    {
+      "epoch": 0.2687831734414664,
+      "grad_norm": 0.8804867267608643,
+      "learning_rate": 4.382592087299212e-05,
+      "loss": 1.5577,
+      "step": 8153
+    },
+    {
+      "epoch": 0.26980516269409555,
+      "grad_norm": 0.8368428349494934,
+      "learning_rate": 4.377055613848964e-05,
+      "loss": 1.5369,
+      "step": 8184
+    },
+    {
+      "epoch": 0.2708271519467247,
+      "grad_norm": 0.9133582711219788,
+      "learning_rate": 4.3714979580812355e-05,
+      "loss": 1.5522,
+      "step": 8215
+    },
+    {
+      "epoch": 0.2718491411993538,
+      "grad_norm": 0.902574360370636,
+      "learning_rate": 4.365919182713416e-05,
+      "loss": 1.5572,
+      "step": 8246
+    },
+    {
+      "epoch": 0.27287113045198297,
+      "grad_norm": 0.9236746430397034,
+      "learning_rate": 4.360319350701226e-05,
+      "loss": 1.5477,
+      "step": 8277
+    },
+    {
+      "epoch": 0.27389311970461216,
+      "grad_norm": 0.8866250514984131,
+      "learning_rate": 4.3546985252380115e-05,
+      "loss": 1.5576,
+      "step": 8308
+    },
+    {
+      "epoch": 0.2749151089572413,
+      "grad_norm": 0.8597050905227661,
+      "learning_rate": 4.349056769754021e-05,
+      "loss": 1.5454,
+      "step": 8339
+    },
+    {
+      "epoch": 0.27593709820987045,
+      "grad_norm": 0.9166654348373413,
+      "learning_rate": 4.3433941479156994e-05,
+      "loss": 1.5342,
+      "step": 8370
+    },
+    {
+      "epoch": 0.2769590874624996,
+      "grad_norm": 0.8913152813911438,
+      "learning_rate": 4.3377107236249647e-05,
+      "loss": 1.5489,
+      "step": 8401
+    },
+    {
+      "epoch": 0.2779810767151287,
+      "grad_norm": 0.9009787440299988,
+      "learning_rate": 4.332006561018488e-05,
+      "loss": 1.5617,
+      "step": 8432
+    },
+    {
+      "epoch": 0.27900306596775787,
+      "grad_norm": 0.8625615239143372,
+      "learning_rate": 4.3262817244669683e-05,
+      "loss": 1.5545,
+      "step": 8463
+    },
+    {
+      "epoch": 0.28002505522038706,
+      "grad_norm": 0.8483917713165283,
+      "learning_rate": 4.3205362785744083e-05,
+      "loss": 1.5287,
+      "step": 8494
+    },
+    {
+      "epoch": 0.2810470444730162,
+      "grad_norm": 0.8959261178970337,
+      "learning_rate": 4.314770288177384e-05,
+      "loss": 1.5503,
+      "step": 8525
+    },
+    {
+      "epoch": 0.28206903372564535,
+      "grad_norm": 0.9090222716331482,
+      "learning_rate": 4.308983818344313e-05,
+      "loss": 1.5469,
+      "step": 8556
+    },
+    {
+      "epoch": 0.2830910229782745,
+      "grad_norm": 0.9215665459632874,
+      "learning_rate": 4.3031769343747206e-05,
+      "loss": 1.519,
+      "step": 8587
+    },
+    {
+      "epoch": 0.2841130122309036,
+      "grad_norm": 0.8699467778205872,
+      "learning_rate": 4.297349701798505e-05,
+      "loss": 1.5507,
+      "step": 8618
+    },
+    {
+      "epoch": 0.28513500148353277,
+      "grad_norm": 0.9755619764328003,
+      "learning_rate": 4.2915021863751916e-05,
+      "loss": 1.5542,
+      "step": 8649
+    },
+    {
+      "epoch": 0.2861569907361619,
+      "grad_norm": 0.8612878918647766,
+      "learning_rate": 4.285634454093198e-05,
+      "loss": 1.55,
+      "step": 8680
+    },
+    {
+      "epoch": 0.2871789799887911,
+      "grad_norm": 0.8708077073097229,
+      "learning_rate": 4.279746571169086e-05,
+      "loss": 1.5239,
+      "step": 8711
+    },
+    {
+      "epoch": 0.28820096924142025,
+      "grad_norm": 0.8952695727348328,
+      "learning_rate": 4.2738386040468136e-05,
+      "loss": 1.5275,
+      "step": 8742
+    },
+    {
+      "epoch": 0.2892229584940494,
+      "grad_norm": 0.8305310010910034,
+      "learning_rate": 4.2679106193969866e-05,
+      "loss": 1.5419,
+      "step": 8773
+    },
+    {
+      "epoch": 0.2902449477466785,
+      "grad_norm": 0.9172886610031128,
+      "learning_rate": 4.261962684116106e-05,
+      "loss": 1.5266,
+      "step": 8804
+    },
+    {
+      "epoch": 0.29126693699930767,
+      "grad_norm": 0.8972066044807434,
+      "learning_rate": 4.2559948653258145e-05,
+      "loss": 1.5428,
+      "step": 8835
+    },
+    {
+      "epoch": 0.2922889262519368,
+      "grad_norm": 0.8838576078414917,
+      "learning_rate": 4.250007230372134e-05,
+      "loss": 1.5685,
+      "step": 8866
+    },
+    {
+      "epoch": 0.293310915504566,
+      "grad_norm": 0.8614609241485596,
+      "learning_rate": 4.2439998468247126e-05,
+      "loss": 1.5624,
+      "step": 8897
+    },
+    {
+      "epoch": 0.29433290475719515,
+      "grad_norm": 0.8305181860923767,
+      "learning_rate": 4.2379727824760566e-05,
+      "loss": 1.5424,
+      "step": 8928
+    },
+    {
+      "epoch": 0.2953548940098243,
+      "grad_norm": 0.8790427446365356,
+      "learning_rate": 4.231926105340768e-05,
+      "loss": 1.5316,
+      "step": 8959
+    },
+    {
+      "epoch": 0.2963768832624534,
+      "grad_norm": 0.8905590772628784,
+      "learning_rate": 4.225859883654776e-05,
+      "loss": 1.5136,
+      "step": 8990
+    },
+    {
+      "epoch": 0.29739887251508257,
+      "grad_norm": 0.8998729586601257,
+      "learning_rate": 4.219774185874569e-05,
+      "loss": 1.5372,
+      "step": 9021
+    },
+    {
+      "epoch": 0.2984208617677117,
+      "grad_norm": 0.8840643763542175,
+      "learning_rate": 4.213669080676418e-05,
+      "loss": 1.5371,
+      "step": 9052
+    },
+    {
+      "epoch": 0.2994428510203409,
+      "grad_norm": 0.9000579714775085,
+      "learning_rate": 4.2075446369556056e-05,
+      "loss": 1.5369,
+      "step": 9083
+    },
+    {
+      "epoch": 0.30046484027297005,
+      "grad_norm": 0.9541018009185791,
+      "learning_rate": 4.201400923825648e-05,
+      "loss": 1.5537,
+      "step": 9114
+    },
+    {
+      "epoch": 0.3014868295255992,
+      "grad_norm": 0.8957076072692871,
+      "learning_rate": 4.195238010617511e-05,
+      "loss": 1.5409,
+      "step": 9145
+    },
+    {
+      "epoch": 0.30250881877822833,
+      "grad_norm": 0.8320883512496948,
+      "learning_rate": 4.1890559668788344e-05,
+      "loss": 1.5178,
+      "step": 9176
+    },
+    {
+      "epoch": 0.30353080803085747,
+      "grad_norm": 0.8729486465454102,
+      "learning_rate": 4.1828548623731405e-05,
+      "loss": 1.5498,
+      "step": 9207
+    },
+    {
+      "epoch": 0.3045527972834866,
+      "grad_norm": 0.8582361936569214,
+      "learning_rate": 4.1766347670790506e-05,
+      "loss": 1.5209,
+      "step": 9238
+    },
+    {
+      "epoch": 0.3055747865361158,
+      "grad_norm": 0.890997052192688,
+      "learning_rate": 4.170395751189495e-05,
+      "loss": 1.5423,
+      "step": 9269
+    },
+    {
+      "epoch": 0.30659677578874495,
+      "grad_norm": 0.9070558547973633,
+      "learning_rate": 4.164137885110921e-05,
+      "loss": 1.5519,
+      "step": 9300
+    },
+    {
+      "epoch": 0.3076187650413741,
+      "grad_norm": 0.9573651552200317,
+      "learning_rate": 4.157861239462495e-05,
+      "loss": 1.5439,
+      "step": 9331
+    },
+    {
+      "epoch": 0.30864075429400323,
+      "grad_norm": 0.9029926061630249,
+      "learning_rate": 4.1515658850753114e-05,
+      "loss": 1.539,
+      "step": 9362
+    },
+    {
+      "epoch": 0.30966274354663237,
+      "grad_norm": 0.8370001316070557,
+      "learning_rate": 4.145251892991588e-05,
+      "loss": 1.5401,
+      "step": 9393
+    },
+    {
+      "epoch": 0.3106847327992615,
+      "grad_norm": 0.8818012475967407,
+      "learning_rate": 4.138919334463868e-05,
+      "loss": 1.5166,
+      "step": 9424
+    },
+    {
+      "epoch": 0.3117067220518907,
+      "grad_norm": 0.8851699233055115,
+      "learning_rate": 4.1325682809542124e-05,
+      "loss": 1.5334,
+      "step": 9455
+    },
+    {
+      "epoch": 0.31272871130451985,
+      "grad_norm": 0.8938205242156982,
+      "learning_rate": 4.126198804133398e-05,
+      "loss": 1.5408,
+      "step": 9486
+    },
+    {
+      "epoch": 0.313750700557149,
+      "grad_norm": 0.8480469584465027,
+      "learning_rate": 4.1198109758801055e-05,
+      "loss": 1.5149,
+      "step": 9517
+    },
+    {
+      "epoch": 0.31477268980977813,
+      "grad_norm": 0.8756515383720398,
+      "learning_rate": 4.113404868280107e-05,
+      "loss": 1.5174,
+      "step": 9548
+    },
+    {
+      "epoch": 0.31579467906240727,
+      "grad_norm": 0.8261292576789856,
+      "learning_rate": 4.106980553625457e-05,
+      "loss": 1.5295,
+      "step": 9579
+    },
+    {
+      "epoch": 0.3168166683150364,
+      "grad_norm": 0.9329167604446411,
+      "learning_rate": 4.100538104413674e-05,
+      "loss": 1.5151,
+      "step": 9610
+    },
+    {
+      "epoch": 0.3178386575676656,
+      "grad_norm": 0.8843585848808289,
+      "learning_rate": 4.09407759334692e-05,
+      "loss": 1.5241,
+      "step": 9641
+    },
+    {
+      "epoch": 0.31886064682029475,
+      "grad_norm": 0.8441824316978455,
+      "learning_rate": 4.087599093331186e-05,
+      "loss": 1.5293,
+      "step": 9672
+    },
+    {
+      "epoch": 0.3198826360729239,
+      "grad_norm": 0.8727023005485535,
+      "learning_rate": 4.081102677475462e-05,
+      "loss": 1.5332,
+      "step": 9703
+    },
+    {
+      "epoch": 0.32090462532555303,
+      "grad_norm": 0.8603296279907227,
+      "learning_rate": 4.0745884190909194e-05,
+      "loss": 1.5205,
+      "step": 9734
+    },
+    {
+      "epoch": 0.32192661457818217,
+      "grad_norm": 0.8445816040039062,
+      "learning_rate": 4.0680563916900796e-05,
+      "loss": 1.541,
+      "step": 9765
+    },
+    {
+      "epoch": 0.3229486038308113,
+      "grad_norm": 0.8408164978027344,
+      "learning_rate": 4.0615066689859815e-05,
+      "loss": 1.5106,
+      "step": 9796
+    },
+    {
+      "epoch": 0.32397059308344045,
+      "grad_norm": 0.901888370513916,
+      "learning_rate": 4.0549393248913584e-05,
+      "loss": 1.5376,
+      "step": 9827
+    },
+    {
+      "epoch": 0.32499258233606965,
+      "grad_norm": 0.878149688243866,
+      "learning_rate": 4.048354433517794e-05,
+      "loss": 1.5197,
+      "step": 9858
+    },
+    {
+      "epoch": 0.3260145715886988,
+      "grad_norm": 0.8681669235229492,
+      "learning_rate": 4.0417520691748916e-05,
+      "loss": 1.524,
+      "step": 9889
+    },
+    {
+      "epoch": 0.32703656084132793,
+      "grad_norm": 0.8651006817817688,
+      "learning_rate": 4.035132306369438e-05,
+      "loss": 1.5257,
+      "step": 9920
+    },
+    {
+      "epoch": 0.32805855009395707,
+      "grad_norm": 0.8485890030860901,
+      "learning_rate": 4.028495219804555e-05,
+      "loss": 1.5325,
+      "step": 9951
+    },
+    {
+      "epoch": 0.3290805393465862,
+      "grad_norm": 0.8644028902053833,
+      "learning_rate": 4.021840884378864e-05,
+      "loss": 1.5432,
+      "step": 9982
+    },
+    {
+      "epoch": 0.33010252859921535,
+      "grad_norm": 0.9188100695610046,
+      "learning_rate": 4.015169375185633e-05,
+      "loss": 1.5381,
+      "step": 10013
+    },
+    {
+      "epoch": 0.33112451785184455,
+      "grad_norm": 0.9121026396751404,
+      "learning_rate": 4.0084807675119396e-05,
+      "loss": 1.5157,
+      "step": 10044
+    },
+    {
+      "epoch": 0.3321465071044737,
+      "grad_norm": 0.8835768699645996,
+      "learning_rate": 4.0017751368378106e-05,
+      "loss": 1.527,
+      "step": 10075
+    },
+    {
+      "epoch": 0.33316849635710283,
+      "grad_norm": 0.8608120679855347,
+      "learning_rate": 3.995052558835377e-05,
+      "loss": 1.5326,
+      "step": 10106
+    },
+    {
+      "epoch": 0.33419048560973197,
+      "grad_norm": 0.8970103859901428,
+      "learning_rate": 3.988313109368017e-05,
+      "loss": 1.5241,
+      "step": 10137
+    },
+    {
+      "epoch": 0.3352124748623611,
+      "grad_norm": 0.832877516746521,
+      "learning_rate": 3.981556864489504e-05,
+      "loss": 1.5093,
+      "step": 10168
+    },
+    {
+      "epoch": 0.33623446411499025,
+      "grad_norm": 0.8215609788894653,
+      "learning_rate": 3.974783900443142e-05,
+      "loss": 1.5243,
+      "step": 10199
+    },
+    {
+      "epoch": 0.33725645336761945,
+      "grad_norm": 0.8891729712486267,
+      "learning_rate": 3.9679942936609095e-05,
+      "loss": 1.527,
+      "step": 10230
+    },
+    {
+      "epoch": 0.3382784426202486,
+      "grad_norm": 0.8482518196105957,
+      "learning_rate": 3.961188120762596e-05,
+      "loss": 1.5171,
+      "step": 10261
+    },
+    {
+      "epoch": 0.33930043187287773,
+      "grad_norm": 0.8347421288490295,
+      "learning_rate": 3.954365458554938e-05,
+      "loss": 1.5209,
+      "step": 10292
+    },
+    {
+      "epoch": 0.34032242112550687,
+      "grad_norm": 0.8662514686584473,
+      "learning_rate": 3.947526384030751e-05,
+      "loss": 1.5225,
+      "step": 10323
+    },
+    {
+      "epoch": 0.341344410378136,
+      "grad_norm": 0.8288858532905579,
+      "learning_rate": 3.9406709743680624e-05,
+      "loss": 1.4988,
+      "step": 10354
+    },
+    {
+      "epoch": 0.34236639963076515,
+      "grad_norm": 0.8532800674438477,
+      "learning_rate": 3.9337993069292366e-05,
+      "loss": 1.5292,
+      "step": 10385
+    },
+    {
+      "epoch": 0.34338838888339435,
+      "grad_norm": 0.8530318140983582,
+      "learning_rate": 3.926911459260109e-05,
+      "loss": 1.5439,
+      "step": 10416
+    },
+    {
+      "epoch": 0.3444103781360235,
+      "grad_norm": 0.8556480407714844,
+      "learning_rate": 3.920007509089102e-05,
+      "loss": 1.502,
+      "step": 10447
+    },
+    {
+      "epoch": 0.34543236738865263,
+      "grad_norm": 0.834280252456665,
+      "learning_rate": 3.913087534326357e-05,
+      "loss": 1.5359,
+      "step": 10478
+    },
+    {
+      "epoch": 0.34645435664128177,
+      "grad_norm": 0.8753178119659424,
+      "learning_rate": 3.9061516130628475e-05,
+      "loss": 1.5247,
+      "step": 10509
+    },
+    {
+      "epoch": 0.3474763458939109,
+      "grad_norm": 0.8129472732543945,
+      "learning_rate": 3.8991998235695025e-05,
+      "loss": 1.509,
+      "step": 10540
+    },
+    {
+      "epoch": 0.34849833514654005,
+      "grad_norm": 0.8485814929008484,
+      "learning_rate": 3.8922322442963224e-05,
+      "loss": 1.5155,
+      "step": 10571
+    },
+    {
+      "epoch": 0.34952032439916925,
+      "grad_norm": 0.8839988708496094,
+      "learning_rate": 3.885248953871491e-05,
+      "loss": 1.5076,
+      "step": 10602
+    },
+    {
+      "epoch": 0.3505423136517984,
+      "grad_norm": 0.8462734818458557,
+      "learning_rate": 3.8782500311004915e-05,
+      "loss": 1.5016,
+      "step": 10633
+    },
+    {
+      "epoch": 0.35156430290442753,
+      "grad_norm": 0.8573621511459351,
+      "learning_rate": 3.871235554965218e-05,
+      "loss": 1.5418,
+      "step": 10664
+    },
+    {
+      "epoch": 0.35258629215705667,
+      "grad_norm": 0.8314201235771179,
+      "learning_rate": 3.864205604623078e-05,
+      "loss": 1.5167,
+      "step": 10695
+    },
+    {
+      "epoch": 0.3536082814096858,
+      "grad_norm": 0.8317237496376038,
+      "learning_rate": 3.857160259406107e-05,
+      "loss": 1.5121,
+      "step": 10726
+    },
+    {
+      "epoch": 0.35463027066231495,
+      "grad_norm": 0.8582017421722412,
+      "learning_rate": 3.8500995988200674e-05,
+      "loss": 1.5137,
+      "step": 10757
+    },
+    {
+      "epoch": 0.35565225991494415,
+      "grad_norm": 0.8427022695541382,
+      "learning_rate": 3.843023702543556e-05,
+      "loss": 1.5248,
+      "step": 10788
+    },
+    {
+      "epoch": 0.3566742491675733,
+      "grad_norm": 0.8414435386657715,
+      "learning_rate": 3.8359326504270984e-05,
+      "loss": 1.4923,
+      "step": 10819
+    },
+    {
+      "epoch": 0.35769623842020243,
+      "grad_norm": 0.8638574481010437,
+      "learning_rate": 3.828826522492255e-05,
+      "loss": 1.4947,
+      "step": 10850
+    },
+    {
+      "epoch": 0.35871822767283157,
+      "grad_norm": 0.8254904747009277,
+      "learning_rate": 3.821705398930713e-05,
+      "loss": 1.524,
+      "step": 10881
+    },
+    {
+      "epoch": 0.3597402169254607,
+      "grad_norm": 0.8651305437088013,
+      "learning_rate": 3.814569360103385e-05,
+      "loss": 1.5034,
+      "step": 10912
+    },
+    {
+      "epoch": 0.36076220617808985,
+      "grad_norm": 0.8567565679550171,
+      "learning_rate": 3.807418486539499e-05,
+      "loss": 1.4971,
+      "step": 10943
+    },
+    {
+      "epoch": 0.36178419543071905,
+      "grad_norm": 0.8213040828704834,
+      "learning_rate": 3.80025285893569e-05,
+      "loss": 1.5095,
+      "step": 10974
+    },
+    {
+      "epoch": 0.3628061846833482,
+      "grad_norm": 0.8153424859046936,
+      "learning_rate": 3.793072558155093e-05,
+      "loss": 1.5168,
+      "step": 11005
+    },
+    {
+      "epoch": 0.36382817393597733,
+      "grad_norm": 0.8211629390716553,
+      "learning_rate": 3.785877665226426e-05,
+      "loss": 1.5208,
+      "step": 11036
+    },
+    {
+      "epoch": 0.36485016318860647,
+      "grad_norm": 0.8744972348213196,
+      "learning_rate": 3.778668261343079e-05,
+      "loss": 1.5133,
+      "step": 11067
+    },
+    {
+      "epoch": 0.3658721524412356,
+      "grad_norm": 0.8211522698402405,
+      "learning_rate": 3.771444427862192e-05,
+      "loss": 1.5042,
+      "step": 11098
+    },
+    {
+      "epoch": 0.36689414169386475,
+      "grad_norm": 0.8390249609947205,
+      "learning_rate": 3.7642062463037465e-05,
+      "loss": 1.5214,
+      "step": 11129
+    },
+    {
+      "epoch": 0.3679161309464939,
+      "grad_norm": 0.8379174470901489,
+      "learning_rate": 3.7569537983496373e-05,
+      "loss": 1.5164,
+      "step": 11160
+    },
+    {
+      "epoch": 0.3689381201991231,
+      "grad_norm": 0.8449585437774658,
+      "learning_rate": 3.749687165842753e-05,
+      "loss": 1.5049,
+      "step": 11191
+    },
+    {
+      "epoch": 0.36996010945175223,
+      "grad_norm": 0.7959738969802856,
+      "learning_rate": 3.7424064307860536e-05,
+      "loss": 1.4941,
+      "step": 11222
+    },
+    {
+      "epoch": 0.37098209870438137,
+      "grad_norm": 0.8311371207237244,
+      "learning_rate": 3.735111675341645e-05,
+      "loss": 1.513,
+      "step": 11253
+    },
+    {
+      "epoch": 0.3720040879570105,
+      "grad_norm": 0.828087329864502,
+      "learning_rate": 3.7278029818298524e-05,
+      "loss": 1.4983,
+      "step": 11284
+    },
+    {
+      "epoch": 0.37302607720963965,
+      "grad_norm": 0.8467016220092773,
+      "learning_rate": 3.720480432728287e-05,
+      "loss": 1.5167,
+      "step": 11315
+    },
+    {
+      "epoch": 0.3740480664622688,
+      "grad_norm": 0.8619351983070374,
+      "learning_rate": 3.71314411067092e-05,
+      "loss": 1.5065,
+      "step": 11346
+    },
+    {
+      "epoch": 0.375070055714898,
+      "grad_norm": 0.8230463862419128,
+      "learning_rate": 3.70579409844715e-05,
+      "loss": 1.4987,
+      "step": 11377
+    },
+    {
+      "epoch": 0.37609204496752713,
+      "grad_norm": 0.8631263971328735,
+      "learning_rate": 3.698430479000865e-05,
+      "loss": 1.5023,
+      "step": 11408
+    },
+    {
+      "epoch": 0.37711403422015627,
+      "grad_norm": 0.8831419348716736,
+      "learning_rate": 3.691053335429509e-05,
+      "loss": 1.5046,
+      "step": 11439
+    },
+    {
+      "epoch": 0.3781360234727854,
+      "grad_norm": 0.8332011103630066,
+      "learning_rate": 3.683662750983147e-05,
+      "loss": 1.5002,
+      "step": 11470
+    },
+    {
+      "epoch": 0.37915801272541455,
+      "grad_norm": 0.8661298751831055,
+      "learning_rate": 3.676258809063518e-05,
+      "loss": 1.51,
+      "step": 11501
+    },
+    {
+      "epoch": 0.3801800019780437,
+      "grad_norm": 0.8714830279350281,
+      "learning_rate": 3.6688415932231004e-05,
+      "loss": 1.5031,
+      "step": 11532
+    },
+    {
+      "epoch": 0.3812019912306729,
+      "grad_norm": 0.8633294701576233,
+      "learning_rate": 3.661411187164166e-05,
+      "loss": 1.4854,
+      "step": 11563
+    },
+    {
+      "epoch": 0.38222398048330203,
+      "grad_norm": 0.8436555862426758,
+      "learning_rate": 3.65396767473784e-05,
+      "loss": 1.5213,
+      "step": 11594
+    },
+    {
+      "epoch": 0.38324596973593117,
+      "grad_norm": 0.8612047433853149,
+      "learning_rate": 3.6465111399431465e-05,
+      "loss": 1.5002,
+      "step": 11625
+    },
+    {
+      "epoch": 0.3842679589885603,
+      "grad_norm": 0.8069844245910645,
+      "learning_rate": 3.6390416669260674e-05,
+      "loss": 1.5034,
+      "step": 11656
+    },
+    {
+      "epoch": 0.38528994824118945,
+      "grad_norm": 0.8230804204940796,
+      "learning_rate": 3.63155933997859e-05,
+      "loss": 1.5155,
+      "step": 11687
+    },
+    {
+      "epoch": 0.3863119374938186,
+      "grad_norm": 0.8166376352310181,
+      "learning_rate": 3.624064243537758e-05,
+      "loss": 1.487,
+      "step": 11718
+    },
+    {
+      "epoch": 0.3873339267464478,
+      "grad_norm": 0.8213214874267578,
+      "learning_rate": 3.616556462184716e-05,
+      "loss": 1.5178,
+      "step": 11749
+    },
+    {
+      "epoch": 0.38835591599907693,
+      "grad_norm": 0.8418950438499451,
+      "learning_rate": 3.609036080643755e-05,
+      "loss": 1.5173,
+      "step": 11780
+    },
+    {
+      "epoch": 0.38937790525170607,
+      "grad_norm": 0.839227020740509,
+      "learning_rate": 3.60150318378136e-05,
+      "loss": 1.51,
+      "step": 11811
+    },
+    {
+      "epoch": 0.3903998945043352,
+      "grad_norm": 0.8407977819442749,
+      "learning_rate": 3.5939578566052465e-05,
+      "loss": 1.4967,
+      "step": 11842
+    },
+    {
+      "epoch": 0.39142188375696435,
+      "grad_norm": 0.8286086320877075,
+      "learning_rate": 3.586400184263408e-05,
+      "loss": 1.4817,
+      "step": 11873
+    },
+    {
+      "epoch": 0.3924438730095935,
+      "grad_norm": 0.8609039783477783,
+      "learning_rate": 3.578830252043148e-05,
+      "loss": 1.4842,
+      "step": 11904
+    },
+    {
+      "epoch": 0.3934658622622227,
+      "grad_norm": 0.8497804403305054,
+      "learning_rate": 3.571248145370125e-05,
+      "loss": 1.509,
+      "step": 11935
+    },
+    {
+      "epoch": 0.39448785151485183,
+      "grad_norm": 0.8288097977638245,
+      "learning_rate": 3.5636539498073794e-05,
+      "loss": 1.4914,
+      "step": 11966
+    },
+    {
+      "epoch": 0.39550984076748097,
+      "grad_norm": 0.8199227452278137,
+      "learning_rate": 3.556047751054378e-05,
+      "loss": 1.4754,
+      "step": 11997
+    },
+    {
+      "epoch": 0.3965318300201101,
+      "grad_norm": 0.8441981077194214,
+      "learning_rate": 3.548429634946039e-05,
+      "loss": 1.4826,
+      "step": 12028
+    },
+    {
+      "epoch": 0.39755381927273925,
+      "grad_norm": 0.7997297048568726,
+      "learning_rate": 3.540799687451768e-05,
+      "loss": 1.4804,
+      "step": 12059
+    },
+    {
+      "epoch": 0.3985758085253684,
+      "grad_norm": 0.8018672466278076,
+      "learning_rate": 3.533157994674485e-05,
+      "loss": 1.4995,
+      "step": 12090
+    },
+    {
+      "epoch": 0.3995977977779976,
+      "grad_norm": 0.8712153434753418,
+      "learning_rate": 3.5255046428496546e-05,
+      "loss": 1.5044,
+      "step": 12121
+    },
+    {
+      "epoch": 0.40061978703062673,
+      "grad_norm": 0.852215588092804,
+      "learning_rate": 3.517839718344311e-05,
+      "loss": 1.4931,
+      "step": 12152
+    },
+    {
+      "epoch": 0.40164177628325587,
+      "grad_norm": 0.8421558141708374,
+      "learning_rate": 3.510163307656086e-05,
+      "loss": 1.4967,
+      "step": 12183
+    }
+  ],
+  "logging_steps": 31,
+  "max_steps": 30517,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 3052,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.526741678122336e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-12208/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:653df926fe7b7d8bc5bd05f93f711031a6b8f6cec15c51d661d79c0b0841d6f1
+size 5304

checkpoint-15260/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/Qwen2.5-7B-Instruct-ta-madlad-mean/",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 161672
+}

checkpoint-15260/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.44.0.dev0"
+}

checkpoint-15260/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:103ed5218f2f666bf89450e88bfd7f71cd7c8e211d6bfe40881e4615e342fe8b
+size 4842817304

checkpoint-15260/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:becf3c41c7359877372d1f9bdba9efe52cb2b8dab7330b346e831a36665b8f0e
+size 4998852224

checkpoint-15260/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad9da13aef49ef9aa84ff7ac6ae375fc2f8c339648214e7663e44e16a6763847
+size 4984124304

checkpoint-15260/model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc2c86e34819a46908bfe3ad42f3986e7efdfc34f67e43f40f690f77c7b0672
+size 4932743992

checkpoint-15260/model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:891f86a74d6b1791b98b581ff94cbedb16bfdb78595b9697dc3fd2ecc5974ba2
+size 4998852296

checkpoint-15260/model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0872a599654c7e07f1ad7a644d8308b0ec760d6eaa176981e1875d10e6230d76
+size 3662865184

checkpoint-15260/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0253a633d732fdae0d41fd7baa334ffcead420f606ca4b2e92242cc76ec64287
+size 2317729920

checkpoint-15260/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 30737946624
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00006-of-00007.safetensors"
+  }
+}

checkpoint-15260/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d742f7621286bd9eabfba87e5c10e575a4780dd884b933fb055648377b05089
+size 16728842070

checkpoint-15260/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
+size 14244

checkpoint-15260/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ce335347efaebf038b8915bc0a8d2d587a4a1aa08ad0e015b4bc7cc4fba634e
+size 1064

checkpoint-15260/trainer_state.json

@@ -0,0 +1,3477 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5030824514555104,
+  "eval_steps": 500,
+  "global_step": 15260,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0010219892526291499,
+      "grad_norm": 52.572940826416016,
+      "learning_rate": 1.0157273918741808e-06,
+      "loss": 9.6136,
+      "step": 31
+    },
+    {
+      "epoch": 0.0020439785052582997,
+      "grad_norm": 26.900487899780273,
+      "learning_rate": 2.0314547837483616e-06,
+      "loss": 7.35,
+      "step": 62
+    },
+    {
+      "epoch": 0.003065967757887449,
+      "grad_norm": 15.413382530212402,
+      "learning_rate": 3.0471821756225426e-06,
+      "loss": 5.872,
+      "step": 93
+    },
+    {
+      "epoch": 0.0040879570105165994,
+      "grad_norm": 9.475220680236816,
+      "learning_rate": 4.062909567496723e-06,
+      "loss": 4.8148,
+      "step": 124
+    },
+    {
+      "epoch": 0.005109946263145749,
+      "grad_norm": 16.33511734008789,
+      "learning_rate": 5.078636959370905e-06,
+      "loss": 4.2357,
+      "step": 155
+    },
+    {
+      "epoch": 0.006131935515774898,
+      "grad_norm": 17.79788589477539,
+      "learning_rate": 6.094364351245085e-06,
+      "loss": 3.9005,
+      "step": 186
+    },
+    {
+      "epoch": 0.007153924768404049,
+      "grad_norm": 7.385252952575684,
+      "learning_rate": 7.110091743119267e-06,
+      "loss": 3.6349,
+      "step": 217
+    },
+    {
+      "epoch": 0.008175914021033199,
+      "grad_norm": 7.6574835777282715,
+      "learning_rate": 8.125819134993446e-06,
+      "loss": 3.4197,
+      "step": 248
+    },
+    {
+      "epoch": 0.009197903273662348,
+      "grad_norm": 10.027671813964844,
+      "learning_rate": 9.141546526867629e-06,
+      "loss": 3.2883,
+      "step": 279
+    },
+    {
+      "epoch": 0.010219892526291498,
+      "grad_norm": 7.447092056274414,
+      "learning_rate": 1.015727391874181e-05,
+      "loss": 3.1606,
+      "step": 310
+    },
+    {
+      "epoch": 0.011241881778920647,
+      "grad_norm": 8.796594619750977,
+      "learning_rate": 1.117300131061599e-05,
+      "loss": 3.0724,
+      "step": 341
+    },
+    {
+      "epoch": 0.012263871031549797,
+      "grad_norm": 8.47999382019043,
+      "learning_rate": 1.218872870249017e-05,
+      "loss": 3.0249,
+      "step": 372
+    },
+    {
+      "epoch": 0.013285860284178948,
+      "grad_norm": 11.703062057495117,
+      "learning_rate": 1.3204456094364351e-05,
+      "loss": 2.9383,
+      "step": 403
+    },
+    {
+      "epoch": 0.014307849536808097,
+      "grad_norm": 7.270478248596191,
+      "learning_rate": 1.4220183486238533e-05,
+      "loss": 2.8753,
+      "step": 434
+    },
+    {
+      "epoch": 0.015329838789437247,
+      "grad_norm": 5.699134349822998,
+      "learning_rate": 1.5235910878112714e-05,
+      "loss": 2.8226,
+      "step": 465
+    },
+    {
+      "epoch": 0.016351828042066398,
+      "grad_norm": 6.3912529945373535,
+      "learning_rate": 1.6251638269986893e-05,
+      "loss": 2.7754,
+      "step": 496
+    },
+    {
+      "epoch": 0.017373817294695545,
+      "grad_norm": 8.240257263183594,
+      "learning_rate": 1.7267365661861077e-05,
+      "loss": 2.7351,
+      "step": 527
+    },
+    {
+      "epoch": 0.018395806547324697,
+      "grad_norm": 9.017704010009766,
+      "learning_rate": 1.8283093053735257e-05,
+      "loss": 2.7084,
+      "step": 558
+    },
+    {
+      "epoch": 0.019417795799953844,
+      "grad_norm": 6.017426013946533,
+      "learning_rate": 1.9298820445609438e-05,
+      "loss": 2.6741,
+      "step": 589
+    },
+    {
+      "epoch": 0.020439785052582995,
+      "grad_norm": 3.789416790008545,
+      "learning_rate": 2.031454783748362e-05,
+      "loss": 2.6605,
+      "step": 620
+    },
+    {
+      "epoch": 0.021461774305212147,
+      "grad_norm": 4.747366428375244,
+      "learning_rate": 2.13302752293578e-05,
+      "loss": 2.6245,
+      "step": 651
+    },
+    {
+      "epoch": 0.022483763557841294,
+      "grad_norm": 3.8344268798828125,
+      "learning_rate": 2.234600262123198e-05,
+      "loss": 2.5791,
+      "step": 682
+    },
+    {
+      "epoch": 0.023505752810470446,
+      "grad_norm": 4.5539116859436035,
+      "learning_rate": 2.336173001310616e-05,
+      "loss": 2.5648,
+      "step": 713
+    },
+    {
+      "epoch": 0.024527742063099593,
+      "grad_norm": 4.216089248657227,
+      "learning_rate": 2.437745740498034e-05,
+      "loss": 2.5125,
+      "step": 744
+    },
+    {
+      "epoch": 0.025549731315728744,
+      "grad_norm": 4.225554466247559,
+      "learning_rate": 2.5393184796854525e-05,
+      "loss": 2.4973,
+      "step": 775
+    },
+    {
+      "epoch": 0.026571720568357896,
+      "grad_norm": 3.357351541519165,
+      "learning_rate": 2.6408912188728702e-05,
+      "loss": 2.4532,
+      "step": 806
+    },
+    {
+      "epoch": 0.027593709820987043,
+      "grad_norm": 4.109170436859131,
+      "learning_rate": 2.7424639580602886e-05,
+      "loss": 2.4504,
+      "step": 837
+    },
+    {
+      "epoch": 0.028615699073616194,
+      "grad_norm": 17.247940063476562,
+      "learning_rate": 2.8440366972477066e-05,
+      "loss": 2.4226,
+      "step": 868
+    },
+    {
+      "epoch": 0.029637688326245342,
+      "grad_norm": 3.2851662635803223,
+      "learning_rate": 2.9456094364351244e-05,
+      "loss": 2.4053,
+      "step": 899
+    },
+    {
+      "epoch": 0.030659677578874493,
+      "grad_norm": 3.3796141147613525,
+      "learning_rate": 3.0471821756225428e-05,
+      "loss": 2.3977,
+      "step": 930
+    },
+    {
+      "epoch": 0.03168166683150364,
+      "grad_norm": 3.0984764099121094,
+      "learning_rate": 3.148754914809961e-05,
+      "loss": 2.3622,
+      "step": 961
+    },
+    {
+      "epoch": 0.032703656084132796,
+      "grad_norm": 2.5464305877685547,
+      "learning_rate": 3.2503276539973785e-05,
+      "loss": 2.348,
+      "step": 992
+    },
+    {
+      "epoch": 0.03372564533676194,
+      "grad_norm": 2.848860263824463,
+      "learning_rate": 3.351900393184797e-05,
+      "loss": 2.3208,
+      "step": 1023
+    },
+    {
+      "epoch": 0.03474763458939109,
+      "grad_norm": 2.5870606899261475,
+      "learning_rate": 3.453473132372215e-05,
+      "loss": 2.3023,
+      "step": 1054
+    },
+    {
+      "epoch": 0.03576962384202024,
+      "grad_norm": 2.6556804180145264,
+      "learning_rate": 3.555045871559633e-05,
+      "loss": 2.2698,
+      "step": 1085
+    },
+    {
+      "epoch": 0.03679161309464939,
+      "grad_norm": 2.779650926589966,
+      "learning_rate": 3.6566186107470514e-05,
+      "loss": 2.2614,
+      "step": 1116
+    },
+    {
+      "epoch": 0.03781360234727854,
+      "grad_norm": 2.624191999435425,
+      "learning_rate": 3.7581913499344695e-05,
+      "loss": 2.2422,
+      "step": 1147
+    },
+    {
+      "epoch": 0.03883559159990769,
+      "grad_norm": 2.5255484580993652,
+      "learning_rate": 3.8597640891218876e-05,
+      "loss": 2.2419,
+      "step": 1178
+    },
+    {
+      "epoch": 0.03985758085253684,
+      "grad_norm": 2.3195745944976807,
+      "learning_rate": 3.9613368283093056e-05,
+      "loss": 2.2468,
+      "step": 1209
+    },
+    {
+      "epoch": 0.04087957010516599,
+      "grad_norm": 2.4712162017822266,
+      "learning_rate": 4.062909567496724e-05,
+      "loss": 2.2072,
+      "step": 1240
+    },
+    {
+      "epoch": 0.04190155935779514,
+      "grad_norm": 4.451296806335449,
+      "learning_rate": 4.164482306684142e-05,
+      "loss": 2.2136,
+      "step": 1271
+    },
+    {
+      "epoch": 0.04292354861042429,
+      "grad_norm": 2.4180150032043457,
+      "learning_rate": 4.26605504587156e-05,
+      "loss": 2.1843,
+      "step": 1302
+    },
+    {
+      "epoch": 0.04394553786305344,
+      "grad_norm": 2.395840883255005,
+      "learning_rate": 4.367627785058978e-05,
+      "loss": 2.1447,
+      "step": 1333
+    },
+    {
+      "epoch": 0.04496752711568259,
+      "grad_norm": 3.072429895401001,
+      "learning_rate": 4.469200524246396e-05,
+      "loss": 2.1405,
+      "step": 1364
+    },
+    {
+      "epoch": 0.045989516368311736,
+      "grad_norm": 1.9566724300384521,
+      "learning_rate": 4.570773263433814e-05,
+      "loss": 2.1321,
+      "step": 1395
+    },
+    {
+      "epoch": 0.04701150562094089,
+      "grad_norm": 23.60377311706543,
+      "learning_rate": 4.672346002621232e-05,
+      "loss": 2.1289,
+      "step": 1426
+    },
+    {
+      "epoch": 0.04803349487357004,
+      "grad_norm": 2.117250919342041,
+      "learning_rate": 4.77391874180865e-05,
+      "loss": 2.1239,
+      "step": 1457
+    },
+    {
+      "epoch": 0.049055484126199186,
+      "grad_norm": 2.361362934112549,
+      "learning_rate": 4.875491480996068e-05,
+      "loss": 2.0838,
+      "step": 1488
+    },
+    {
+      "epoch": 0.05007747337882834,
+      "grad_norm": 2.1867992877960205,
+      "learning_rate": 4.977064220183487e-05,
+      "loss": 2.0622,
+      "step": 1519
+    },
+    {
+      "epoch": 0.05109946263145749,
+      "grad_norm": 1.9326456785202026,
+      "learning_rate": 4.9999915451558777e-05,
+      "loss": 2.0441,
+      "step": 1550
+    },
+    {
+      "epoch": 0.052121451884086636,
+      "grad_norm": 2.076503038406372,
+      "learning_rate": 4.999955597496219e-05,
+      "loss": 2.0503,
+      "step": 1581
+    },
+    {
+      "epoch": 0.05314344113671579,
+      "grad_norm": 3.051212787628174,
+      "learning_rate": 4.9998914381774255e-05,
+      "loss": 2.0357,
+      "step": 1612
+    },
+    {
+      "epoch": 0.05416543038934494,
+      "grad_norm": 1.7924102544784546,
+      "learning_rate": 4.999799067923527e-05,
+      "loss": 2.0326,
+      "step": 1643
+    },
+    {
+      "epoch": 0.055187419641974086,
+      "grad_norm": 1.8103365898132324,
+      "learning_rate": 4.999678487776908e-05,
+      "loss": 2.0023,
+      "step": 1674
+    },
+    {
+      "epoch": 0.056209408894603234,
+      "grad_norm": 1.913725733757019,
+      "learning_rate": 4.9995296990983006e-05,
+      "loss": 2.0035,
+      "step": 1705
+    },
+    {
+      "epoch": 0.05723139814723239,
+      "grad_norm": 1.7415859699249268,
+      "learning_rate": 4.999352703566763e-05,
+      "loss": 2.0063,
+      "step": 1736
+    },
+    {
+      "epoch": 0.058253387399861536,
+      "grad_norm": 1.8145827054977417,
+      "learning_rate": 4.999147503179668e-05,
+      "loss": 1.9731,
+      "step": 1767
+    },
+    {
+      "epoch": 0.059275376652490684,
+      "grad_norm": 1.8761731386184692,
+      "learning_rate": 4.998914100252672e-05,
+      "loss": 1.9883,
+      "step": 1798
+    },
+    {
+      "epoch": 0.06029736590511984,
+      "grad_norm": 6.824073791503906,
+      "learning_rate": 4.998652497419696e-05,
+      "loss": 1.9713,
+      "step": 1829
+    },
+    {
+      "epoch": 0.061319355157748986,
+      "grad_norm": 1.7231906652450562,
+      "learning_rate": 4.9983626976328927e-05,
+      "loss": 1.9492,
+      "step": 1860
+    },
+    {
+      "epoch": 0.062341344410378134,
+      "grad_norm": 1.6888827085494995,
+      "learning_rate": 4.998044704162613e-05,
+      "loss": 1.9449,
+      "step": 1891
+    },
+    {
+      "epoch": 0.06336333366300728,
+      "grad_norm": 1.5924124717712402,
+      "learning_rate": 4.9976985205973705e-05,
+      "loss": 1.938,
+      "step": 1922
+    },
+    {
+      "epoch": 0.06438532291563644,
+      "grad_norm": 1.7029409408569336,
+      "learning_rate": 4.997324150843799e-05,
+      "loss": 1.9285,
+      "step": 1953
+    },
+    {
+      "epoch": 0.06540731216826559,
+      "grad_norm": 1.5554330348968506,
+      "learning_rate": 4.99692159912661e-05,
+      "loss": 1.9091,
+      "step": 1984
+    },
+    {
+      "epoch": 0.06642930142089473,
+      "grad_norm": 1.5639121532440186,
+      "learning_rate": 4.996490869988546e-05,
+      "loss": 1.9105,
+      "step": 2015
+    },
+    {
+      "epoch": 0.06745129067352389,
+      "grad_norm": 1.6262747049331665,
+      "learning_rate": 4.996031968290326e-05,
+      "loss": 1.9164,
+      "step": 2046
+    },
+    {
+      "epoch": 0.06847327992615304,
+      "grad_norm": 1.5408495664596558,
+      "learning_rate": 4.995544899210594e-05,
+      "loss": 1.8728,
+      "step": 2077
+    },
+    {
+      "epoch": 0.06949526917878218,
+      "grad_norm": 1.5183970928192139,
+      "learning_rate": 4.9950296682458583e-05,
+      "loss": 1.8854,
+      "step": 2108
+    },
+    {
+      "epoch": 0.07051725843141134,
+      "grad_norm": 1.9362810850143433,
+      "learning_rate": 4.994486281210429e-05,
+      "loss": 1.8811,
+      "step": 2139
+    },
+    {
+      "epoch": 0.07153924768404048,
+      "grad_norm": 1.5646640062332153,
+      "learning_rate": 4.9939147442363566e-05,
+      "loss": 1.8744,
+      "step": 2170
+    },
+    {
+      "epoch": 0.07256123693666963,
+      "grad_norm": 1.5929124355316162,
+      "learning_rate": 4.9933150637733574e-05,
+      "loss": 1.867,
+      "step": 2201
+    },
+    {
+      "epoch": 0.07358322618929879,
+      "grad_norm": 1.7689995765686035,
+      "learning_rate": 4.992687246588743e-05,
+      "loss": 1.8659,
+      "step": 2232
+    },
+    {
+      "epoch": 0.07460521544192793,
+      "grad_norm": 1.375406265258789,
+      "learning_rate": 4.992031299767347e-05,
+      "loss": 1.8477,
+      "step": 2263
+    },
+    {
+      "epoch": 0.07562720469455708,
+      "grad_norm": 1.3596042394638062,
+      "learning_rate": 4.9913472307114386e-05,
+      "loss": 1.8498,
+      "step": 2294
+    },
+    {
+      "epoch": 0.07664919394718624,
+      "grad_norm": 1.3918544054031372,
+      "learning_rate": 4.9906350471406446e-05,
+      "loss": 1.8538,
+      "step": 2325
+    },
+    {
+      "epoch": 0.07767118319981538,
+      "grad_norm": 1.4614112377166748,
+      "learning_rate": 4.989894757091861e-05,
+      "loss": 1.8359,
+      "step": 2356
+    },
+    {
+      "epoch": 0.07869317245244453,
+      "grad_norm": 1.563186764717102,
+      "learning_rate": 4.989126368919158e-05,
+      "loss": 1.821,
+      "step": 2387
+    },
+    {
+      "epoch": 0.07971516170507369,
+      "grad_norm": 1.3217226266860962,
+      "learning_rate": 4.988329891293693e-05,
+      "loss": 1.8345,
+      "step": 2418
+    },
+    {
+      "epoch": 0.08073715095770283,
+      "grad_norm": 1.3906276226043701,
+      "learning_rate": 4.987505333203608e-05,
+      "loss": 1.8313,
+      "step": 2449
+    },
+    {
+      "epoch": 0.08175914021033198,
+      "grad_norm": 1.2736890316009521,
+      "learning_rate": 4.9866527039539276e-05,
+      "loss": 1.8234,
+      "step": 2480
+    },
+    {
+      "epoch": 0.08278112946296114,
+      "grad_norm": 1.3050850629806519,
+      "learning_rate": 4.9857720131664594e-05,
+      "loss": 1.8181,
+      "step": 2511
+    },
+    {
+      "epoch": 0.08380311871559028,
+      "grad_norm": 1.3847019672393799,
+      "learning_rate": 4.9848632707796773e-05,
+      "loss": 1.8128,
+      "step": 2542
+    },
+    {
+      "epoch": 0.08482510796821943,
+      "grad_norm": 1.3893433809280396,
+      "learning_rate": 4.9839264870486155e-05,
+      "loss": 1.7871,
+      "step": 2573
+    },
+    {
+      "epoch": 0.08584709722084859,
+      "grad_norm": 1.3469080924987793,
+      "learning_rate": 4.9829616725447526e-05,
+      "loss": 1.8212,
+      "step": 2604
+    },
+    {
+      "epoch": 0.08686908647347773,
+      "grad_norm": 1.269865870475769,
+      "learning_rate": 4.981968838155888e-05,
+      "loss": 1.7868,
+      "step": 2635
+    },
+    {
+      "epoch": 0.08789107572610688,
+      "grad_norm": 1.2972242832183838,
+      "learning_rate": 4.980947995086024e-05,
+      "loss": 1.7987,
+      "step": 2666
+    },
+    {
+      "epoch": 0.08891306497873604,
+      "grad_norm": 1.3488340377807617,
+      "learning_rate": 4.979899154855234e-05,
+      "loss": 1.7859,
+      "step": 2697
+    },
+    {
+      "epoch": 0.08993505423136518,
+      "grad_norm": 1.3487133979797363,
+      "learning_rate": 4.9788223292995386e-05,
+      "loss": 1.7851,
+      "step": 2728
+    },
+    {
+      "epoch": 0.09095704348399433,
+      "grad_norm": 1.2412410974502563,
+      "learning_rate": 4.977717530570768e-05,
+      "loss": 1.7802,
+      "step": 2759
+    },
+    {
+      "epoch": 0.09197903273662347,
+      "grad_norm": 1.3017562627792358,
+      "learning_rate": 4.976584771136425e-05,
+      "loss": 1.775,
+      "step": 2790
+    },
+    {
+      "epoch": 0.09300102198925263,
+      "grad_norm": 1.2923076152801514,
+      "learning_rate": 4.975424063779547e-05,
+      "loss": 1.76,
+      "step": 2821
+    },
+    {
+      "epoch": 0.09402301124188178,
+      "grad_norm": 1.2735223770141602,
+      "learning_rate": 4.974235421598557e-05,
+      "loss": 1.7604,
+      "step": 2852
+    },
+    {
+      "epoch": 0.09504500049451092,
+      "grad_norm": 1.303673505783081,
+      "learning_rate": 4.973018858007122e-05,
+      "loss": 1.7685,
+      "step": 2883
+    },
+    {
+      "epoch": 0.09606698974714008,
+      "grad_norm": 1.5336410999298096,
+      "learning_rate": 4.9717743867339963e-05,
+      "loss": 1.7682,
+      "step": 2914
+    },
+    {
+      "epoch": 0.09708897899976923,
+      "grad_norm": 5.014227867126465,
+      "learning_rate": 4.9705020218228695e-05,
+      "loss": 1.7617,
+      "step": 2945
+    },
+    {
+      "epoch": 0.09811096825239837,
+      "grad_norm": 1.2603938579559326,
+      "learning_rate": 4.969201777632205e-05,
+      "loss": 1.7621,
+      "step": 2976
+    },
+    {
+      "epoch": 0.09913295750502753,
+      "grad_norm": 1.32491934299469,
+      "learning_rate": 4.9678736688350846e-05,
+      "loss": 1.7411,
+      "step": 3007
+    },
+    {
+      "epoch": 0.10015494675765668,
+      "grad_norm": 1.206735372543335,
+      "learning_rate": 4.966517710419033e-05,
+      "loss": 1.7262,
+      "step": 3038
+    },
+    {
+      "epoch": 0.10117693601028582,
+      "grad_norm": 1.254231572151184,
+      "learning_rate": 4.965133917685858e-05,
+      "loss": 1.7454,
+      "step": 3069
+    },
+    {
+      "epoch": 0.10219892526291498,
+      "grad_norm": 1.3085408210754395,
+      "learning_rate": 4.9637223062514714e-05,
+      "loss": 1.7517,
+      "step": 3100
+    },
+    {
+      "epoch": 0.10322091451554413,
+      "grad_norm": 1.3184605836868286,
+      "learning_rate": 4.962282892045718e-05,
+      "loss": 1.7542,
+      "step": 3131
+    },
+    {
+      "epoch": 0.10424290376817327,
+      "grad_norm": 1.2284983396530151,
+      "learning_rate": 4.9608156913121904e-05,
+      "loss": 1.738,
+      "step": 3162
+    },
+    {
+      "epoch": 0.10526489302080243,
+      "grad_norm": 1.3870880603790283,
+      "learning_rate": 4.959320720608049e-05,
+      "loss": 1.7358,
+      "step": 3193
+    },
+    {
+      "epoch": 0.10628688227343158,
+      "grad_norm": 1.1335322856903076,
+      "learning_rate": 4.9577979968038354e-05,
+      "loss": 1.742,
+      "step": 3224
+    },
+    {
+      "epoch": 0.10730887152606072,
+      "grad_norm": 1.1794465780258179,
+      "learning_rate": 4.956247537083282e-05,
+      "loss": 1.7357,
+      "step": 3255
+    },
+    {
+      "epoch": 0.10833086077868988,
+      "grad_norm": 1.1701149940490723,
+      "learning_rate": 4.9546693589431145e-05,
+      "loss": 1.7289,
+      "step": 3286
+    },
+    {
+      "epoch": 0.10935285003131903,
+      "grad_norm": 1.169094443321228,
+      "learning_rate": 4.9530634801928595e-05,
+      "loss": 1.7238,
+      "step": 3317
+    },
+    {
+      "epoch": 0.11037483928394817,
+      "grad_norm": 1.2735379934310913,
+      "learning_rate": 4.9514299189546395e-05,
+      "loss": 1.7275,
+      "step": 3348
+    },
+    {
+      "epoch": 0.11139682853657733,
+      "grad_norm": 1.2806981801986694,
+      "learning_rate": 4.949768693662973e-05,
+      "loss": 1.7135,
+      "step": 3379
+    },
+    {
+      "epoch": 0.11241881778920647,
+      "grad_norm": 1.208024263381958,
+      "learning_rate": 4.948079823064559e-05,
+      "loss": 1.7251,
+      "step": 3410
+    },
+    {
+      "epoch": 0.11344080704183562,
+      "grad_norm": 1.275516152381897,
+      "learning_rate": 4.946363326218074e-05,
+      "loss": 1.7259,
+      "step": 3441
+    },
+    {
+      "epoch": 0.11446279629446478,
+      "grad_norm": 1.1761465072631836,
+      "learning_rate": 4.9446192224939525e-05,
+      "loss": 1.7024,
+      "step": 3472
+    },
+    {
+      "epoch": 0.11548478554709392,
+      "grad_norm": 1.1216075420379639,
+      "learning_rate": 4.942847531574167e-05,
+      "loss": 1.6849,
+      "step": 3503
+    },
+    {
+      "epoch": 0.11650677479972307,
+      "grad_norm": 1.1286563873291016,
+      "learning_rate": 4.941048273452008e-05,
+      "loss": 1.7004,
+      "step": 3534
+    },
+    {
+      "epoch": 0.11752876405235223,
+      "grad_norm": 1.1531614065170288,
+      "learning_rate": 4.9392214684318605e-05,
+      "loss": 1.7101,
+      "step": 3565
+    },
+    {
+      "epoch": 0.11855075330498137,
+      "grad_norm": 1.143051266670227,
+      "learning_rate": 4.93736713712897e-05,
+      "loss": 1.7127,
+      "step": 3596
+    },
+    {
+      "epoch": 0.11957274255761052,
+      "grad_norm": 1.1483272314071655,
+      "learning_rate": 4.9354853004692124e-05,
+      "loss": 1.6968,
+      "step": 3627
+    },
+    {
+      "epoch": 0.12059473181023968,
+      "grad_norm": 1.1267555952072144,
+      "learning_rate": 4.93357597968886e-05,
+      "loss": 1.7023,
+      "step": 3658
+    },
+    {
+      "epoch": 0.12161672106286882,
+      "grad_norm": 1.1552249193191528,
+      "learning_rate": 4.931639196334338e-05,
+      "loss": 1.7171,
+      "step": 3689
+    },
+    {
+      "epoch": 0.12263871031549797,
+      "grad_norm": 1.1388061046600342,
+      "learning_rate": 4.9296749722619826e-05,
+      "loss": 1.7061,
+      "step": 3720
+    },
+    {
+      "epoch": 0.12366069956812713,
+      "grad_norm": 1.127455234527588,
+      "learning_rate": 4.9276833296377966e-05,
+      "loss": 1.6879,
+      "step": 3751
+    },
+    {
+      "epoch": 0.12468268882075627,
+      "grad_norm": 1.1534373760223389,
+      "learning_rate": 4.925664290937196e-05,
+      "loss": 1.7091,
+      "step": 3782
+    },
+    {
+      "epoch": 0.12570467807338542,
+      "grad_norm": 1.2369154691696167,
+      "learning_rate": 4.9236178789447576e-05,
+      "loss": 1.6923,
+      "step": 3813
+    },
+    {
+      "epoch": 0.12672666732601456,
+      "grad_norm": 1.074436068534851,
+      "learning_rate": 4.921544116753962e-05,
+      "loss": 1.6805,
+      "step": 3844
+    },
+    {
+      "epoch": 0.12774865657864373,
+      "grad_norm": 1.112226963043213,
+      "learning_rate": 4.919443027766935e-05,
+      "loss": 1.6527,
+      "step": 3875
+    },
+    {
+      "epoch": 0.12877064583127287,
+      "grad_norm": 1.0999863147735596,
+      "learning_rate": 4.91731463569418e-05,
+      "loss": 1.6614,
+      "step": 3906
+    },
+    {
+      "epoch": 0.129792635083902,
+      "grad_norm": 1.098036527633667,
+      "learning_rate": 4.915158964554312e-05,
+      "loss": 1.6826,
+      "step": 3937
+    },
+    {
+      "epoch": 0.13081462433653118,
+      "grad_norm": 1.1108450889587402,
+      "learning_rate": 4.912976038673786e-05,
+      "loss": 1.6886,
+      "step": 3968
+    },
+    {
+      "epoch": 0.13183661358916032,
+      "grad_norm": 1.0916872024536133,
+      "learning_rate": 4.9107658826866254e-05,
+      "loss": 1.6782,
+      "step": 3999
+    },
+    {
+      "epoch": 0.13285860284178946,
+      "grad_norm": 1.0818581581115723,
+      "learning_rate": 4.908528521534139e-05,
+      "loss": 1.6796,
+      "step": 4030
+    },
+    {
+      "epoch": 0.13388059209441863,
+      "grad_norm": 1.0908610820770264,
+      "learning_rate": 4.906263980464644e-05,
+      "loss": 1.6662,
+      "step": 4061
+    },
+    {
+      "epoch": 0.13490258134704777,
+      "grad_norm": 1.0384143590927124,
+      "learning_rate": 4.903972285033178e-05,
+      "loss": 1.6811,
+      "step": 4092
+    },
+    {
+      "epoch": 0.1359245705996769,
+      "grad_norm": 1.0998533964157104,
+      "learning_rate": 4.901653461101213e-05,
+      "loss": 1.6817,
+      "step": 4123
+    },
+    {
+      "epoch": 0.13694655985230608,
+      "grad_norm": 1.1726231575012207,
+      "learning_rate": 4.8993075348363626e-05,
+      "loss": 1.6532,
+      "step": 4154
+    },
+    {
+      "epoch": 0.13796854910493522,
+      "grad_norm": 1.075464129447937,
+      "learning_rate": 4.896934532712084e-05,
+      "loss": 1.671,
+      "step": 4185
+    },
+    {
+      "epoch": 0.13899053835756436,
+      "grad_norm": 1.0557868480682373,
+      "learning_rate": 4.8945344815073846e-05,
+      "loss": 1.6548,
+      "step": 4216
+    },
+    {
+      "epoch": 0.14001252761019353,
+      "grad_norm": 1.0531095266342163,
+      "learning_rate": 4.892107408306516e-05,
+      "loss": 1.6526,
+      "step": 4247
+    },
+    {
+      "epoch": 0.14103451686282267,
+      "grad_norm": 1.138203501701355,
+      "learning_rate": 4.889653340498669e-05,
+      "loss": 1.678,
+      "step": 4278
+    },
+    {
+      "epoch": 0.1420565061154518,
+      "grad_norm": 1.0668121576309204,
+      "learning_rate": 4.8871723057776664e-05,
+      "loss": 1.6552,
+      "step": 4309
+    },
+    {
+      "epoch": 0.14307849536808095,
+      "grad_norm": 1.0312261581420898,
+      "learning_rate": 4.8846643321416476e-05,
+      "loss": 1.6731,
+      "step": 4340
+    },
+    {
+      "epoch": 0.14410048462071012,
+      "grad_norm": 1.0868667364120483,
+      "learning_rate": 4.882129447892753e-05,
+      "loss": 1.6713,
+      "step": 4371
+    },
+    {
+      "epoch": 0.14512247387333926,
+      "grad_norm": 1.0213130712509155,
+      "learning_rate": 4.8795676816368076e-05,
+      "loss": 1.6515,
+      "step": 4402
+    },
+    {
+      "epoch": 0.1461444631259684,
+      "grad_norm": 1.190875768661499,
+      "learning_rate": 4.876979062282995e-05,
+      "loss": 1.651,
+      "step": 4433
+    },
+    {
+      "epoch": 0.14716645237859757,
+      "grad_norm": 1.0551568269729614,
+      "learning_rate": 4.8743636190435325e-05,
+      "loss": 1.6751,
+      "step": 4464
+    },
+    {
+      "epoch": 0.1481884416312267,
+      "grad_norm": 1.0654323101043701,
+      "learning_rate": 4.871721381433344e-05,
+      "loss": 1.6499,
+      "step": 4495
+    },
+    {
+      "epoch": 0.14921043088385585,
+      "grad_norm": 1.04425048828125,
+      "learning_rate": 4.869052379269719e-05,
+      "loss": 1.6401,
+      "step": 4526
+    },
+    {
+      "epoch": 0.15023242013648502,
+      "grad_norm": 1.3416290283203125,
+      "learning_rate": 4.866356642671985e-05,
+      "loss": 1.6553,
+      "step": 4557
+    },
+    {
+      "epoch": 0.15125440938911416,
+      "grad_norm": 1.073529601097107,
+      "learning_rate": 4.8636342020611634e-05,
+      "loss": 1.6413,
+      "step": 4588
+    },
+    {
+      "epoch": 0.1522763986417433,
+      "grad_norm": 1.0386462211608887,
+      "learning_rate": 4.860885088159626e-05,
+      "loss": 1.6595,
+      "step": 4619
+    },
+    {
+      "epoch": 0.15329838789437247,
+      "grad_norm": 1.0544514656066895,
+      "learning_rate": 4.858109331990751e-05,
+      "loss": 1.6387,
+      "step": 4650
+    },
+    {
+      "epoch": 0.15432037714700161,
+      "grad_norm": 1.088112473487854,
+      "learning_rate": 4.855306964878567e-05,
+      "loss": 1.628,
+      "step": 4681
+    },
+    {
+      "epoch": 0.15534236639963075,
+      "grad_norm": 0.9930492639541626,
+      "learning_rate": 4.8524780184474084e-05,
+      "loss": 1.6554,
+      "step": 4712
+    },
+    {
+      "epoch": 0.15636435565225992,
+      "grad_norm": 0.9864984154701233,
+      "learning_rate": 4.8496225246215496e-05,
+      "loss": 1.6558,
+      "step": 4743
+    },
+    {
+      "epoch": 0.15738634490488906,
+      "grad_norm": 1.0170128345489502,
+      "learning_rate": 4.8467405156248505e-05,
+      "loss": 1.6289,
+      "step": 4774
+    },
+    {
+      "epoch": 0.1584083341575182,
+      "grad_norm": 1.0360223054885864,
+      "learning_rate": 4.843832023980392e-05,
+      "loss": 1.6314,
+      "step": 4805
+    },
+    {
+      "epoch": 0.15943032341014737,
+      "grad_norm": 1.0165129899978638,
+      "learning_rate": 4.840897082510106e-05,
+      "loss": 1.6294,
+      "step": 4836
+    },
+    {
+      "epoch": 0.16045231266277651,
+      "grad_norm": 1.079991102218628,
+      "learning_rate": 4.8379357243344084e-05,
+      "loss": 1.6204,
+      "step": 4867
+    },
+    {
+      "epoch": 0.16147430191540565,
+      "grad_norm": 1.0515645742416382,
+      "learning_rate": 4.8349479828718236e-05,
+      "loss": 1.6322,
+      "step": 4898
+    },
+    {
+      "epoch": 0.16249629116803482,
+      "grad_norm": 1.0226655006408691,
+      "learning_rate": 4.8319338918386075e-05,
+      "loss": 1.6476,
+      "step": 4929
+    },
+    {
+      "epoch": 0.16351828042066396,
+      "grad_norm": 1.0581114292144775,
+      "learning_rate": 4.828893485248369e-05,
+      "loss": 1.6302,
+      "step": 4960
+    },
+    {
+      "epoch": 0.1645402696732931,
+      "grad_norm": 1.0156742334365845,
+      "learning_rate": 4.825826797411682e-05,
+      "loss": 1.6292,
+      "step": 4991
+    },
+    {
+      "epoch": 0.16556225892592227,
+      "grad_norm": 1.0153559446334839,
+      "learning_rate": 4.822733862935702e-05,
+      "loss": 1.6367,
+      "step": 5022
+    },
+    {
+      "epoch": 0.16658424817855141,
+      "grad_norm": 1.0488505363464355,
+      "learning_rate": 4.819614716723775e-05,
+      "loss": 1.644,
+      "step": 5053
+    },
+    {
+      "epoch": 0.16760623743118055,
+      "grad_norm": 1.092781901359558,
+      "learning_rate": 4.8164693939750425e-05,
+      "loss": 1.6318,
+      "step": 5084
+    },
+    {
+      "epoch": 0.16862822668380972,
+      "grad_norm": 0.9972744584083557,
+      "learning_rate": 4.813297930184042e-05,
+      "loss": 1.6206,
+      "step": 5115
+    },
+    {
+      "epoch": 0.16965021593643886,
+      "grad_norm": 1.0455750226974487,
+      "learning_rate": 4.810100361140314e-05,
+      "loss": 1.6296,
+      "step": 5146
+    },
+    {
+      "epoch": 0.170672205189068,
+      "grad_norm": 0.9624122977256775,
+      "learning_rate": 4.8068767229279885e-05,
+      "loss": 1.6307,
+      "step": 5177
+    },
+    {
+      "epoch": 0.17169419444169717,
+      "grad_norm": 1.4828526973724365,
+      "learning_rate": 4.8036270519253854e-05,
+      "loss": 1.6377,
+      "step": 5208
+    },
+    {
+      "epoch": 0.17271618369432631,
+      "grad_norm": 1.0732771158218384,
+      "learning_rate": 4.8003513848046e-05,
+      "loss": 1.6148,
+      "step": 5239
+    },
+    {
+      "epoch": 0.17373817294695545,
+      "grad_norm": 1.0065757036209106,
+      "learning_rate": 4.79704975853109e-05,
+      "loss": 1.6192,
+      "step": 5270
+    },
+    {
+      "epoch": 0.17476016219958462,
+      "grad_norm": 1.7071099281311035,
+      "learning_rate": 4.793722210363262e-05,
+      "loss": 1.6205,
+      "step": 5301
+    },
+    {
+      "epoch": 0.17578215145221376,
+      "grad_norm": 1.009507417678833,
+      "learning_rate": 4.7903687778520414e-05,
+      "loss": 1.6261,
+      "step": 5332
+    },
+    {
+      "epoch": 0.1768041407048429,
+      "grad_norm": 1.0593280792236328,
+      "learning_rate": 4.7869894988404593e-05,
+      "loss": 1.6286,
+      "step": 5363
+    },
+    {
+      "epoch": 0.17782612995747207,
+      "grad_norm": 1.0053679943084717,
+      "learning_rate": 4.783584411463221e-05,
+      "loss": 1.6424,
+      "step": 5394
+    },
+    {
+      "epoch": 0.17884811921010121,
+      "grad_norm": 0.983214795589447,
+      "learning_rate": 4.780153554146274e-05,
+      "loss": 1.6292,
+      "step": 5425
+    },
+    {
+      "epoch": 0.17987010846273035,
+      "grad_norm": 0.9617491960525513,
+      "learning_rate": 4.7766969656063766e-05,
+      "loss": 1.6182,
+      "step": 5456
+    },
+    {
+      "epoch": 0.18089209771535952,
+      "grad_norm": 1.0862797498703003,
+      "learning_rate": 4.773214684850662e-05,
+      "loss": 1.6213,
+      "step": 5487
+    },
+    {
+      "epoch": 0.18191408696798866,
+      "grad_norm": 1.0468218326568604,
+      "learning_rate": 4.769706751176193e-05,
+      "loss": 1.6176,
+      "step": 5518
+    },
+    {
+      "epoch": 0.1829360762206178,
+      "grad_norm": 0.9474911093711853,
+      "learning_rate": 4.7661732041695264e-05,
+      "loss": 1.5864,
+      "step": 5549
+    },
+    {
+      "epoch": 0.18395806547324695,
+      "grad_norm": 0.9839109778404236,
+      "learning_rate": 4.762614083706258e-05,
+      "loss": 1.6177,
+      "step": 5580
+    },
+    {
+      "epoch": 0.18498005472587611,
+      "grad_norm": 1.9305601119995117,
+      "learning_rate": 4.759029429950581e-05,
+      "loss": 1.6132,
+      "step": 5611
+    },
+    {
+      "epoch": 0.18600204397850525,
+      "grad_norm": 0.9609850645065308,
+      "learning_rate": 4.7554192833548235e-05,
+      "loss": 1.6115,
+      "step": 5642
+    },
+    {
+      "epoch": 0.1870240332311344,
+      "grad_norm": 1.0501559972763062,
+      "learning_rate": 4.751783684659e-05,
+      "loss": 1.6017,
+      "step": 5673
+    },
+    {
+      "epoch": 0.18804602248376356,
+      "grad_norm": 0.9933464527130127,
+      "learning_rate": 4.748122674890348e-05,
+      "loss": 1.6136,
+      "step": 5704
+    },
+    {
+      "epoch": 0.1890680117363927,
+      "grad_norm": 0.9463350772857666,
+      "learning_rate": 4.7444362953628654e-05,
+      "loss": 1.6102,
+      "step": 5735
+    },
+    {
+      "epoch": 0.19009000098902185,
+      "grad_norm": 0.9974256753921509,
+      "learning_rate": 4.7407245876768424e-05,
+      "loss": 1.6101,
+      "step": 5766
+    },
+    {
+      "epoch": 0.19111199024165101,
+      "grad_norm": 0.9747878313064575,
+      "learning_rate": 4.736987593718397e-05,
+      "loss": 1.5967,
+      "step": 5797
+    },
+    {
+      "epoch": 0.19213397949428015,
+      "grad_norm": 0.9755719900131226,
+      "learning_rate": 4.733225355658999e-05,
+      "loss": 1.5987,
+      "step": 5828
+    },
+    {
+      "epoch": 0.1931559687469093,
+      "grad_norm": 0.9605233669281006,
+      "learning_rate": 4.7294379159549926e-05,
+      "loss": 1.6238,
+      "step": 5859
+    },
+    {
+      "epoch": 0.19417795799953846,
+      "grad_norm": 0.9777940511703491,
+      "learning_rate": 4.725625317347119e-05,
+      "loss": 1.5976,
+      "step": 5890
+    },
+    {
+      "epoch": 0.1951999472521676,
+      "grad_norm": 0.9619265198707581,
+      "learning_rate": 4.7217876028600374e-05,
+      "loss": 1.5985,
+      "step": 5921
+    },
+    {
+      "epoch": 0.19622193650479675,
+      "grad_norm": 0.970813512802124,
+      "learning_rate": 4.717924815801832e-05,
+      "loss": 1.6097,
+      "step": 5952
+    },
+    {
+      "epoch": 0.19724392575742591,
+      "grad_norm": 1.1910721063613892,
+      "learning_rate": 4.714036999763532e-05,
+      "loss": 1.6156,
+      "step": 5983
+    },
+    {
+      "epoch": 0.19826591501005505,
+      "grad_norm": 1.1106246709823608,
+      "learning_rate": 4.7101241986186116e-05,
+      "loss": 1.5761,
+      "step": 6014
+    },
+    {
+      "epoch": 0.1992879042626842,
+      "grad_norm": 1.0065436363220215,
+      "learning_rate": 4.7061864565225e-05,
+      "loss": 1.5857,
+      "step": 6045
+    },
+    {
+      "epoch": 0.20030989351531336,
+      "grad_norm": 0.9245477914810181,
+      "learning_rate": 4.702223817912081e-05,
+      "loss": 1.6099,
+      "step": 6076
+    },
+    {
+      "epoch": 0.2013318827679425,
+      "grad_norm": 0.9705063104629517,
+      "learning_rate": 4.698236327505195e-05,
+      "loss": 1.5995,
+      "step": 6107
+    },
+    {
+      "epoch": 0.20235387202057165,
+      "grad_norm": 0.9455100893974304,
+      "learning_rate": 4.694224030300127e-05,
+      "loss": 1.6302,
+      "step": 6138
+    },
+    {
+      "epoch": 0.20337586127320081,
+      "grad_norm": 0.9505909085273743,
+      "learning_rate": 4.690186971575107e-05,
+      "loss": 1.5799,
+      "step": 6169
+    },
+    {
+      "epoch": 0.20439785052582995,
+      "grad_norm": 0.9440078139305115,
+      "learning_rate": 4.6861251968877916e-05,
+      "loss": 1.5889,
+      "step": 6200
+    },
+    {
+      "epoch": 0.2054198397784591,
+      "grad_norm": 0.9610021710395813,
+      "learning_rate": 4.68203875207476e-05,
+      "loss": 1.6049,
+      "step": 6231
+    },
+    {
+      "epoch": 0.20644182903108826,
+      "grad_norm": 0.9686371684074402,
+      "learning_rate": 4.677927683250983e-05,
+      "loss": 1.5985,
+      "step": 6262
+    },
+    {
+      "epoch": 0.2074638182837174,
+      "grad_norm": 0.9532095789909363,
+      "learning_rate": 4.6737920368093156e-05,
+      "loss": 1.5763,
+      "step": 6293
+    },
+    {
+      "epoch": 0.20848580753634655,
+      "grad_norm": 0.9185531139373779,
+      "learning_rate": 4.669631859419965e-05,
+      "loss": 1.5719,
+      "step": 6324
+    },
+    {
+      "epoch": 0.20950779678897571,
+      "grad_norm": 0.917314350605011,
+      "learning_rate": 4.6654471980299676e-05,
+      "loss": 1.5634,
+      "step": 6355
+    },
+    {
+      "epoch": 0.21052978604160485,
+      "grad_norm": 0.9497798681259155,
+      "learning_rate": 4.661238099862658e-05,
+      "loss": 1.5836,
+      "step": 6386
+    },
+    {
+      "epoch": 0.211551775294234,
+      "grad_norm": 0.939011812210083,
+      "learning_rate": 4.657004612417138e-05,
+      "loss": 1.601,
+      "step": 6417
+    },
+    {
+      "epoch": 0.21257376454686316,
+      "grad_norm": 0.981315016746521,
+      "learning_rate": 4.6527467834677374e-05,
+      "loss": 1.5896,
+      "step": 6448
+    },
+    {
+      "epoch": 0.2135957537994923,
+      "grad_norm": 0.9485774636268616,
+      "learning_rate": 4.648464661063478e-05,
+      "loss": 1.5912,
+      "step": 6479
+    },
+    {
+      "epoch": 0.21461774305212145,
+      "grad_norm": 0.9504795670509338,
+      "learning_rate": 4.6441582935275264e-05,
+      "loss": 1.5827,
+      "step": 6510
+    },
+    {
+      "epoch": 0.21563973230475061,
+      "grad_norm": 0.9627436399459839,
+      "learning_rate": 4.6398277294566586e-05,
+      "loss": 1.5858,
+      "step": 6541
+    },
+    {
+      "epoch": 0.21666172155737976,
+      "grad_norm": 0.9468591809272766,
+      "learning_rate": 4.6354730177207e-05,
+      "loss": 1.5884,
+      "step": 6572
+    },
+    {
+      "epoch": 0.2176837108100089,
+      "grad_norm": 0.9847991466522217,
+      "learning_rate": 4.6310942074619787e-05,
+      "loss": 1.5744,
+      "step": 6603
+    },
+    {
+      "epoch": 0.21870570006263806,
+      "grad_norm": 0.9207347631454468,
+      "learning_rate": 4.626691348094777e-05,
+      "loss": 1.5675,
+      "step": 6634
+    },
+    {
+      "epoch": 0.2197276893152672,
+      "grad_norm": 0.9114487171173096,
+      "learning_rate": 4.622264489304762e-05,
+      "loss": 1.5726,
+      "step": 6665
+    },
+    {
+      "epoch": 0.22074967856789635,
+      "grad_norm": 0.9141913652420044,
+      "learning_rate": 4.617813681048434e-05,
+      "loss": 1.5757,
+      "step": 6696
+    },
+    {
+      "epoch": 0.2217716678205255,
+      "grad_norm": 0.9770637154579163,
+      "learning_rate": 4.61333897355256e-05,
+      "loss": 1.5819,
+      "step": 6727
+    },
+    {
+      "epoch": 0.22279365707315466,
+      "grad_norm": 0.9790964126586914,
+      "learning_rate": 4.608840417313604e-05,
+      "loss": 1.5793,
+      "step": 6758
+    },
+    {
+      "epoch": 0.2238156463257838,
+      "grad_norm": 0.9311193227767944,
+      "learning_rate": 4.6043180630971646e-05,
+      "loss": 1.5823,
+      "step": 6789
+    },
+    {
+      "epoch": 0.22483763557841294,
+      "grad_norm": 0.934339165687561,
+      "learning_rate": 4.599771961937391e-05,
+      "loss": 1.5643,
+      "step": 6820
+    },
+    {
+      "epoch": 0.2258596248310421,
+      "grad_norm": 0.9052058458328247,
+      "learning_rate": 4.5952021651364204e-05,
+      "loss": 1.5752,
+      "step": 6851
+    },
+    {
+      "epoch": 0.22688161408367125,
+      "grad_norm": 0.9528570175170898,
+      "learning_rate": 4.590608724263786e-05,
+      "loss": 1.5603,
+      "step": 6882
+    },
+    {
+      "epoch": 0.2279036033363004,
+      "grad_norm": 0.9073063135147095,
+      "learning_rate": 4.585991691155845e-05,
+      "loss": 1.555,
+      "step": 6913
+    },
+    {
+      "epoch": 0.22892559258892956,
+      "grad_norm": 0.9537662267684937,
+      "learning_rate": 4.581351117915188e-05,
+      "loss": 1.5662,
+      "step": 6944
+    },
+    {
+      "epoch": 0.2299475818415587,
+      "grad_norm": 0.9296181201934814,
+      "learning_rate": 4.5766870569100534e-05,
+      "loss": 1.5649,
+      "step": 6975
+    },
+    {
+      "epoch": 0.23096957109418784,
+      "grad_norm": 0.947211503982544,
+      "learning_rate": 4.571999560773736e-05,
+      "loss": 1.5834,
+      "step": 7006
+    },
+    {
+      "epoch": 0.231991560346817,
+      "grad_norm": 0.9705089330673218,
+      "learning_rate": 4.5672886824039915e-05,
+      "loss": 1.5817,
+      "step": 7037
+    },
+    {
+      "epoch": 0.23301354959944615,
+      "grad_norm": 0.9289253950119019,
+      "learning_rate": 4.5625544749624435e-05,
+      "loss": 1.5792,
+      "step": 7068
+    },
+    {
+      "epoch": 0.2340355388520753,
+      "grad_norm": 0.9166892766952515,
+      "learning_rate": 4.5577969918739794e-05,
+      "loss": 1.559,
+      "step": 7099
+    },
+    {
+      "epoch": 0.23505752810470446,
+      "grad_norm": 0.9205060601234436,
+      "learning_rate": 4.5530162868261486e-05,
+      "loss": 1.5564,
+      "step": 7130
+    },
+    {
+      "epoch": 0.2360795173573336,
+      "grad_norm": 0.9769343733787537,
+      "learning_rate": 4.548212413768558e-05,
+      "loss": 1.5499,
+      "step": 7161
+    },
+    {
+      "epoch": 0.23710150660996274,
+      "grad_norm": 1.0154651403427124,
+      "learning_rate": 4.543385426912261e-05,
+      "loss": 1.5832,
+      "step": 7192
+    },
+    {
+      "epoch": 0.2381234958625919,
+      "grad_norm": 0.9247255325317383,
+      "learning_rate": 4.53853538072915e-05,
+      "loss": 1.5844,
+      "step": 7223
+    },
+    {
+      "epoch": 0.23914548511522105,
+      "grad_norm": 0.8840001225471497,
+      "learning_rate": 4.533662329951336e-05,
+      "loss": 1.5456,
+      "step": 7254
+    },
+    {
+      "epoch": 0.2401674743678502,
+      "grad_norm": 0.986392080783844,
+      "learning_rate": 4.528766329570536e-05,
+      "loss": 1.5743,
+      "step": 7285
+    },
+    {
+      "epoch": 0.24118946362047936,
+      "grad_norm": 0.8750962615013123,
+      "learning_rate": 4.523847434837447e-05,
+      "loss": 1.5751,
+      "step": 7316
+    },
+    {
+      "epoch": 0.2422114528731085,
+      "grad_norm": 0.9039379954338074,
+      "learning_rate": 4.518905701261128e-05,
+      "loss": 1.5603,
+      "step": 7347
+    },
+    {
+      "epoch": 0.24323344212573764,
+      "grad_norm": 0.9081151485443115,
+      "learning_rate": 4.5139411846083715e-05,
+      "loss": 1.5542,
+      "step": 7378
+    },
+    {
+      "epoch": 0.2442554313783668,
+      "grad_norm": 1.532193899154663,
+      "learning_rate": 4.508953940903073e-05,
+      "loss": 1.5693,
+      "step": 7409
+    },
+    {
+      "epoch": 0.24527742063099595,
+      "grad_norm": 0.9598657488822937,
+      "learning_rate": 4.5039440264255994e-05,
+      "loss": 1.5672,
+      "step": 7440
+    },
+    {
+      "epoch": 0.2462994098836251,
+      "grad_norm": 1.3318407535552979,
+      "learning_rate": 4.498911497712155e-05,
+      "loss": 1.5739,
+      "step": 7471
+    },
+    {
+      "epoch": 0.24732139913625426,
+      "grad_norm": 0.9309579730033875,
+      "learning_rate": 4.493856411554142e-05,
+      "loss": 1.5504,
+      "step": 7502
+    },
+    {
+      "epoch": 0.2483433883888834,
+      "grad_norm": 0.9426462650299072,
+      "learning_rate": 4.4887788249975206e-05,
+      "loss": 1.5529,
+      "step": 7533
+    },
+    {
+      "epoch": 0.24936537764151254,
+      "grad_norm": 0.9388718605041504,
+      "learning_rate": 4.4836787953421656e-05,
+      "loss": 1.5589,
+      "step": 7564
+    },
+    {
+      "epoch": 0.2503873668941417,
+      "grad_norm": 0.8922486901283264,
+      "learning_rate": 4.478556380141218e-05,
+      "loss": 1.5453,
+      "step": 7595
+    },
+    {
+      "epoch": 0.25140935614677085,
+      "grad_norm": 0.9597366452217102,
+      "learning_rate": 4.4734116372004375e-05,
+      "loss": 1.5565,
+      "step": 7626
+    },
+    {
+      "epoch": 0.2524313453994,
+      "grad_norm": 0.880445659160614,
+      "learning_rate": 4.4682446245775477e-05,
+      "loss": 1.5429,
+      "step": 7657
+    },
+    {
+      "epoch": 0.2534533346520291,
+      "grad_norm": 0.8895862102508545,
+      "learning_rate": 4.463055400581586e-05,
+      "loss": 1.5462,
+      "step": 7688
+    },
+    {
+      "epoch": 0.25447532390465827,
+      "grad_norm": 0.8859049677848816,
+      "learning_rate": 4.4578440237722374e-05,
+      "loss": 1.5678,
+      "step": 7719
+    },
+    {
+      "epoch": 0.25549731315728746,
+      "grad_norm": 0.9074852466583252,
+      "learning_rate": 4.452610552959183e-05,
+      "loss": 1.5695,
+      "step": 7750
+    },
+    {
+      "epoch": 0.2565193024099166,
+      "grad_norm": 0.9472444653511047,
+      "learning_rate": 4.447355047201428e-05,
+      "loss": 1.5527,
+      "step": 7781
+    },
+    {
+      "epoch": 0.25754129166254575,
+      "grad_norm": 0.901016891002655,
+      "learning_rate": 4.4420775658066414e-05,
+      "loss": 1.5523,
+      "step": 7812
+    },
+    {
+      "epoch": 0.2585632809151749,
+      "grad_norm": 0.8963896632194519,
+      "learning_rate": 4.436778168330484e-05,
+      "loss": 1.5623,
+      "step": 7843
+    },
+    {
+      "epoch": 0.259585270167804,
+      "grad_norm": 0.9571655988693237,
+      "learning_rate": 4.4314569145759353e-05,
+      "loss": 1.5446,
+      "step": 7874
+    },
+    {
+      "epoch": 0.26060725942043317,
+      "grad_norm": 0.9321922659873962,
+      "learning_rate": 4.42611386459262e-05,
+      "loss": 1.5514,
+      "step": 7905
+    },
+    {
+      "epoch": 0.26162924867306236,
+      "grad_norm": 0.8753949403762817,
+      "learning_rate": 4.420749078676133e-05,
+      "loss": 1.5524,
+      "step": 7936
+    },
+    {
+      "epoch": 0.2626512379256915,
+      "grad_norm": 0.8667870759963989,
+      "learning_rate": 4.4153626173673516e-05,
+      "loss": 1.5435,
+      "step": 7967
+    },
+    {
+      "epoch": 0.26367322717832065,
+      "grad_norm": 0.926670491695404,
+      "learning_rate": 4.409954541451762e-05,
+      "loss": 1.5448,
+      "step": 7998
+    },
+    {
+      "epoch": 0.2646952164309498,
+      "grad_norm": 0.9438245892524719,
+      "learning_rate": 4.404524911958764e-05,
+      "loss": 1.5706,
+      "step": 8029
+    },
+    {
+      "epoch": 0.2657172056835789,
+      "grad_norm": 0.9131088256835938,
+      "learning_rate": 4.399073790160989e-05,
+      "loss": 1.5361,
+      "step": 8060
+    },
+    {
+      "epoch": 0.26673919493620807,
+      "grad_norm": 0.914857804775238,
+      "learning_rate": 4.393601237573607e-05,
+      "loss": 1.5588,
+      "step": 8091
+    },
+    {
+      "epoch": 0.26776118418883726,
+      "grad_norm": 0.9113429188728333,
+      "learning_rate": 4.388107315953628e-05,
+      "loss": 1.5603,
+      "step": 8122
+    },
+    {
+      "epoch": 0.2687831734414664,
+      "grad_norm": 0.8804867267608643,
+      "learning_rate": 4.382592087299212e-05,
+      "loss": 1.5577,
+      "step": 8153
+    },
+    {
+      "epoch": 0.26980516269409555,
+      "grad_norm": 0.8368428349494934,
+      "learning_rate": 4.377055613848964e-05,
+      "loss": 1.5369,
+      "step": 8184
+    },
+    {
+      "epoch": 0.2708271519467247,
+      "grad_norm": 0.9133582711219788,
+      "learning_rate": 4.3714979580812355e-05,
+      "loss": 1.5522,
+      "step": 8215
+    },
+    {
+      "epoch": 0.2718491411993538,
+      "grad_norm": 0.902574360370636,
+      "learning_rate": 4.365919182713416e-05,
+      "loss": 1.5572,
+      "step": 8246
+    },
+    {
+      "epoch": 0.27287113045198297,
+      "grad_norm": 0.9236746430397034,
+      "learning_rate": 4.360319350701226e-05,
+      "loss": 1.5477,
+      "step": 8277
+    },
+    {
+      "epoch": 0.27389311970461216,
+      "grad_norm": 0.8866250514984131,
+      "learning_rate": 4.3546985252380115e-05,
+      "loss": 1.5576,
+      "step": 8308
+    },
+    {
+      "epoch": 0.2749151089572413,
+      "grad_norm": 0.8597050905227661,
+      "learning_rate": 4.349056769754021e-05,
+      "loss": 1.5454,
+      "step": 8339
+    },
+    {
+      "epoch": 0.27593709820987045,
+      "grad_norm": 0.9166654348373413,
+      "learning_rate": 4.3433941479156994e-05,
+      "loss": 1.5342,
+      "step": 8370
+    },
+    {
+      "epoch": 0.2769590874624996,
+      "grad_norm": 0.8913152813911438,
+      "learning_rate": 4.3377107236249647e-05,
+      "loss": 1.5489,
+      "step": 8401
+    },
+    {
+      "epoch": 0.2779810767151287,
+      "grad_norm": 0.9009787440299988,
+      "learning_rate": 4.332006561018488e-05,
+      "loss": 1.5617,
+      "step": 8432
+    },
+    {
+      "epoch": 0.27900306596775787,
+      "grad_norm": 0.8625615239143372,
+      "learning_rate": 4.3262817244669683e-05,
+      "loss": 1.5545,
+      "step": 8463
+    },
+    {
+      "epoch": 0.28002505522038706,
+      "grad_norm": 0.8483917713165283,
+      "learning_rate": 4.3205362785744083e-05,
+      "loss": 1.5287,
+      "step": 8494
+    },
+    {
+      "epoch": 0.2810470444730162,
+      "grad_norm": 0.8959261178970337,
+      "learning_rate": 4.314770288177384e-05,
+      "loss": 1.5503,
+      "step": 8525
+    },
+    {
+      "epoch": 0.28206903372564535,
+      "grad_norm": 0.9090222716331482,
+      "learning_rate": 4.308983818344313e-05,
+      "loss": 1.5469,
+      "step": 8556
+    },
+    {
+      "epoch": 0.2830910229782745,
+      "grad_norm": 0.9215665459632874,
+      "learning_rate": 4.3031769343747206e-05,
+      "loss": 1.519,
+      "step": 8587
+    },
+    {
+      "epoch": 0.2841130122309036,
+      "grad_norm": 0.8699467778205872,
+      "learning_rate": 4.297349701798505e-05,
+      "loss": 1.5507,
+      "step": 8618
+    },
+    {
+      "epoch": 0.28513500148353277,
+      "grad_norm": 0.9755619764328003,
+      "learning_rate": 4.2915021863751916e-05,
+      "loss": 1.5542,
+      "step": 8649
+    },
+    {
+      "epoch": 0.2861569907361619,
+      "grad_norm": 0.8612878918647766,
+      "learning_rate": 4.285634454093198e-05,
+      "loss": 1.55,
+      "step": 8680
+    },
+    {
+      "epoch": 0.2871789799887911,
+      "grad_norm": 0.8708077073097229,
+      "learning_rate": 4.279746571169086e-05,
+      "loss": 1.5239,
+      "step": 8711
+    },
+    {
+      "epoch": 0.28820096924142025,
+      "grad_norm": 0.8952695727348328,
+      "learning_rate": 4.2738386040468136e-05,
+      "loss": 1.5275,
+      "step": 8742
+    },
+    {
+      "epoch": 0.2892229584940494,
+      "grad_norm": 0.8305310010910034,
+      "learning_rate": 4.2679106193969866e-05,
+      "loss": 1.5419,
+      "step": 8773
+    },
+    {
+      "epoch": 0.2902449477466785,
+      "grad_norm": 0.9172886610031128,
+      "learning_rate": 4.261962684116106e-05,
+      "loss": 1.5266,
+      "step": 8804
+    },
+    {
+      "epoch": 0.29126693699930767,
+      "grad_norm": 0.8972066044807434,
+      "learning_rate": 4.2559948653258145e-05,
+      "loss": 1.5428,
+      "step": 8835
+    },
+    {
+      "epoch": 0.2922889262519368,
+      "grad_norm": 0.8838576078414917,
+      "learning_rate": 4.250007230372134e-05,
+      "loss": 1.5685,
+      "step": 8866
+    },
+    {
+      "epoch": 0.293310915504566,
+      "grad_norm": 0.8614609241485596,
+      "learning_rate": 4.2439998468247126e-05,
+      "loss": 1.5624,
+      "step": 8897
+    },
+    {
+      "epoch": 0.29433290475719515,
+      "grad_norm": 0.8305181860923767,
+      "learning_rate": 4.2379727824760566e-05,
+      "loss": 1.5424,
+      "step": 8928
+    },
+    {
+      "epoch": 0.2953548940098243,
+      "grad_norm": 0.8790427446365356,
+      "learning_rate": 4.231926105340768e-05,
+      "loss": 1.5316,
+      "step": 8959
+    },
+    {
+      "epoch": 0.2963768832624534,
+      "grad_norm": 0.8905590772628784,
+      "learning_rate": 4.225859883654776e-05,
+      "loss": 1.5136,
+      "step": 8990
+    },
+    {
+      "epoch": 0.29739887251508257,
+      "grad_norm": 0.8998729586601257,
+      "learning_rate": 4.219774185874569e-05,
+      "loss": 1.5372,
+      "step": 9021
+    },
+    {
+      "epoch": 0.2984208617677117,
+      "grad_norm": 0.8840643763542175,
+      "learning_rate": 4.213669080676418e-05,
+      "loss": 1.5371,
+      "step": 9052
+    },
+    {
+      "epoch": 0.2994428510203409,
+      "grad_norm": 0.9000579714775085,
+      "learning_rate": 4.2075446369556056e-05,
+      "loss": 1.5369,
+      "step": 9083
+    },
+    {
+      "epoch": 0.30046484027297005,
+      "grad_norm": 0.9541018009185791,
+      "learning_rate": 4.201400923825648e-05,
+      "loss": 1.5537,
+      "step": 9114
+    },
+    {
+      "epoch": 0.3014868295255992,
+      "grad_norm": 0.8957076072692871,
+      "learning_rate": 4.195238010617511e-05,
+      "loss": 1.5409,
+      "step": 9145
+    },
+    {
+      "epoch": 0.30250881877822833,
+      "grad_norm": 0.8320883512496948,
+      "learning_rate": 4.1890559668788344e-05,
+      "loss": 1.5178,
+      "step": 9176
+    },
+    {
+      "epoch": 0.30353080803085747,
+      "grad_norm": 0.8729486465454102,
+      "learning_rate": 4.1828548623731405e-05,
+      "loss": 1.5498,
+      "step": 9207
+    },
+    {
+      "epoch": 0.3045527972834866,
+      "grad_norm": 0.8582361936569214,
+      "learning_rate": 4.1766347670790506e-05,
+      "loss": 1.5209,
+      "step": 9238
+    },
+    {
+      "epoch": 0.3055747865361158,
+      "grad_norm": 0.890997052192688,
+      "learning_rate": 4.170395751189495e-05,
+      "loss": 1.5423,
+      "step": 9269
+    },
+    {
+      "epoch": 0.30659677578874495,
+      "grad_norm": 0.9070558547973633,
+      "learning_rate": 4.164137885110921e-05,
+      "loss": 1.5519,
+      "step": 9300
+    },
+    {
+      "epoch": 0.3076187650413741,
+      "grad_norm": 0.9573651552200317,
+      "learning_rate": 4.157861239462495e-05,
+      "loss": 1.5439,
+      "step": 9331
+    },
+    {
+      "epoch": 0.30864075429400323,
+      "grad_norm": 0.9029926061630249,
+      "learning_rate": 4.1515658850753114e-05,
+      "loss": 1.539,
+      "step": 9362
+    },
+    {
+      "epoch": 0.30966274354663237,
+      "grad_norm": 0.8370001316070557,
+      "learning_rate": 4.145251892991588e-05,
+      "loss": 1.5401,
+      "step": 9393
+    },
+    {
+      "epoch": 0.3106847327992615,
+      "grad_norm": 0.8818012475967407,
+      "learning_rate": 4.138919334463868e-05,
+      "loss": 1.5166,
+      "step": 9424
+    },
+    {
+      "epoch": 0.3117067220518907,
+      "grad_norm": 0.8851699233055115,
+      "learning_rate": 4.1325682809542124e-05,
+      "loss": 1.5334,
+      "step": 9455
+    },
+    {
+      "epoch": 0.31272871130451985,
+      "grad_norm": 0.8938205242156982,
+      "learning_rate": 4.126198804133398e-05,
+      "loss": 1.5408,
+      "step": 9486
+    },
+    {
+      "epoch": 0.313750700557149,
+      "grad_norm": 0.8480469584465027,
+      "learning_rate": 4.1198109758801055e-05,
+      "loss": 1.5149,
+      "step": 9517
+    },
+    {
+      "epoch": 0.31477268980977813,
+      "grad_norm": 0.8756515383720398,
+      "learning_rate": 4.113404868280107e-05,
+      "loss": 1.5174,
+      "step": 9548
+    },
+    {
+      "epoch": 0.31579467906240727,
+      "grad_norm": 0.8261292576789856,
+      "learning_rate": 4.106980553625457e-05,
+      "loss": 1.5295,
+      "step": 9579
+    },
+    {
+      "epoch": 0.3168166683150364,
+      "grad_norm": 0.9329167604446411,
+      "learning_rate": 4.100538104413674e-05,
+      "loss": 1.5151,
+      "step": 9610
+    },
+    {
+      "epoch": 0.3178386575676656,
+      "grad_norm": 0.8843585848808289,
+      "learning_rate": 4.09407759334692e-05,
+      "loss": 1.5241,
+      "step": 9641
+    },
+    {
+      "epoch": 0.31886064682029475,
+      "grad_norm": 0.8441824316978455,
+      "learning_rate": 4.087599093331186e-05,
+      "loss": 1.5293,
+      "step": 9672
+    },
+    {
+      "epoch": 0.3198826360729239,
+      "grad_norm": 0.8727023005485535,
+      "learning_rate": 4.081102677475462e-05,
+      "loss": 1.5332,
+      "step": 9703
+    },
+    {
+      "epoch": 0.32090462532555303,
+      "grad_norm": 0.8603296279907227,
+      "learning_rate": 4.0745884190909194e-05,
+      "loss": 1.5205,
+      "step": 9734
+    },
+    {
+      "epoch": 0.32192661457818217,
+      "grad_norm": 0.8445816040039062,
+      "learning_rate": 4.0680563916900796e-05,
+      "loss": 1.541,
+      "step": 9765
+    },
+    {
+      "epoch": 0.3229486038308113,
+      "grad_norm": 0.8408164978027344,
+      "learning_rate": 4.0615066689859815e-05,
+      "loss": 1.5106,
+      "step": 9796
+    },
+    {
+      "epoch": 0.32397059308344045,
+      "grad_norm": 0.901888370513916,
+      "learning_rate": 4.0549393248913584e-05,
+      "loss": 1.5376,
+      "step": 9827
+    },
+    {
+      "epoch": 0.32499258233606965,
+      "grad_norm": 0.878149688243866,
+      "learning_rate": 4.048354433517794e-05,
+      "loss": 1.5197,
+      "step": 9858
+    },
+    {
+      "epoch": 0.3260145715886988,
+      "grad_norm": 0.8681669235229492,
+      "learning_rate": 4.0417520691748916e-05,
+      "loss": 1.524,
+      "step": 9889
+    },
+    {
+      "epoch": 0.32703656084132793,
+      "grad_norm": 0.8651006817817688,
+      "learning_rate": 4.035132306369438e-05,
+      "loss": 1.5257,
+      "step": 9920
+    },
+    {
+      "epoch": 0.32805855009395707,
+      "grad_norm": 0.8485890030860901,
+      "learning_rate": 4.028495219804555e-05,
+      "loss": 1.5325,
+      "step": 9951
+    },
+    {
+      "epoch": 0.3290805393465862,
+      "grad_norm": 0.8644028902053833,
+      "learning_rate": 4.021840884378864e-05,
+      "loss": 1.5432,
+      "step": 9982
+    },
+    {
+      "epoch": 0.33010252859921535,
+      "grad_norm": 0.9188100695610046,
+      "learning_rate": 4.015169375185633e-05,
+      "loss": 1.5381,
+      "step": 10013
+    },
+    {
+      "epoch": 0.33112451785184455,
+      "grad_norm": 0.9121026396751404,
+      "learning_rate": 4.0084807675119396e-05,
+      "loss": 1.5157,
+      "step": 10044
+    },
+    {
+      "epoch": 0.3321465071044737,
+      "grad_norm": 0.8835768699645996,
+      "learning_rate": 4.0017751368378106e-05,
+      "loss": 1.527,
+      "step": 10075
+    },
+    {
+      "epoch": 0.33316849635710283,
+      "grad_norm": 0.8608120679855347,
+      "learning_rate": 3.995052558835377e-05,
+      "loss": 1.5326,
+      "step": 10106
+    },
+    {
+      "epoch": 0.33419048560973197,
+      "grad_norm": 0.8970103859901428,
+      "learning_rate": 3.988313109368017e-05,
+      "loss": 1.5241,
+      "step": 10137
+    },
+    {
+      "epoch": 0.3352124748623611,
+      "grad_norm": 0.832877516746521,
+      "learning_rate": 3.981556864489504e-05,
+      "loss": 1.5093,
+      "step": 10168
+    },
+    {
+      "epoch": 0.33623446411499025,
+      "grad_norm": 0.8215609788894653,
+      "learning_rate": 3.974783900443142e-05,
+      "loss": 1.5243,
+      "step": 10199
+    },
+    {
+      "epoch": 0.33725645336761945,
+      "grad_norm": 0.8891729712486267,
+      "learning_rate": 3.9679942936609095e-05,
+      "loss": 1.527,
+      "step": 10230
+    },
+    {
+      "epoch": 0.3382784426202486,
+      "grad_norm": 0.8482518196105957,
+      "learning_rate": 3.961188120762596e-05,
+      "loss": 1.5171,
+      "step": 10261
+    },
+    {
+      "epoch": 0.33930043187287773,
+      "grad_norm": 0.8347421288490295,
+      "learning_rate": 3.954365458554938e-05,
+      "loss": 1.5209,
+      "step": 10292
+    },
+    {
+      "epoch": 0.34032242112550687,
+      "grad_norm": 0.8662514686584473,
+      "learning_rate": 3.947526384030751e-05,
+      "loss": 1.5225,
+      "step": 10323
+    },
+    {
+      "epoch": 0.341344410378136,
+      "grad_norm": 0.8288858532905579,
+      "learning_rate": 3.9406709743680624e-05,
+      "loss": 1.4988,
+      "step": 10354
+    },
+    {
+      "epoch": 0.34236639963076515,
+      "grad_norm": 0.8532800674438477,
+      "learning_rate": 3.9337993069292366e-05,
+      "loss": 1.5292,
+      "step": 10385
+    },
+    {
+      "epoch": 0.34338838888339435,
+      "grad_norm": 0.8530318140983582,
+      "learning_rate": 3.926911459260109e-05,
+      "loss": 1.5439,
+      "step": 10416
+    },
+    {
+      "epoch": 0.3444103781360235,
+      "grad_norm": 0.8556480407714844,
+      "learning_rate": 3.920007509089102e-05,
+      "loss": 1.502,
+      "step": 10447
+    },
+    {
+      "epoch": 0.34543236738865263,
+      "grad_norm": 0.834280252456665,
+      "learning_rate": 3.913087534326357e-05,
+      "loss": 1.5359,
+      "step": 10478
+    },
+    {
+      "epoch": 0.34645435664128177,
+      "grad_norm": 0.8753178119659424,
+      "learning_rate": 3.9061516130628475e-05,
+      "loss": 1.5247,
+      "step": 10509
+    },
+    {
+      "epoch": 0.3474763458939109,
+      "grad_norm": 0.8129472732543945,
+      "learning_rate": 3.8991998235695025e-05,
+      "loss": 1.509,
+      "step": 10540
+    },
+    {
+      "epoch": 0.34849833514654005,
+      "grad_norm": 0.8485814929008484,
+      "learning_rate": 3.8922322442963224e-05,
+      "loss": 1.5155,
+      "step": 10571
+    },
+    {
+      "epoch": 0.34952032439916925,
+      "grad_norm": 0.8839988708496094,
+      "learning_rate": 3.885248953871491e-05,
+      "loss": 1.5076,
+      "step": 10602
+    },
+    {
+      "epoch": 0.3505423136517984,
+      "grad_norm": 0.8462734818458557,
+      "learning_rate": 3.8782500311004915e-05,
+      "loss": 1.5016,
+      "step": 10633
+    },
+    {
+      "epoch": 0.35156430290442753,
+      "grad_norm": 0.8573621511459351,
+      "learning_rate": 3.871235554965218e-05,
+      "loss": 1.5418,
+      "step": 10664
+    },
+    {
+      "epoch": 0.35258629215705667,
+      "grad_norm": 0.8314201235771179,
+      "learning_rate": 3.864205604623078e-05,
+      "loss": 1.5167,
+      "step": 10695
+    },
+    {
+      "epoch": 0.3536082814096858,
+      "grad_norm": 0.8317237496376038,
+      "learning_rate": 3.857160259406107e-05,
+      "loss": 1.5121,
+      "step": 10726
+    },
+    {
+      "epoch": 0.35463027066231495,
+      "grad_norm": 0.8582017421722412,
+      "learning_rate": 3.8500995988200674e-05,
+      "loss": 1.5137,
+      "step": 10757
+    },
+    {
+      "epoch": 0.35565225991494415,
+      "grad_norm": 0.8427022695541382,
+      "learning_rate": 3.843023702543556e-05,
+      "loss": 1.5248,
+      "step": 10788
+    },
+    {
+      "epoch": 0.3566742491675733,
+      "grad_norm": 0.8414435386657715,
+      "learning_rate": 3.8359326504270984e-05,
+      "loss": 1.4923,
+      "step": 10819
+    },
+    {
+      "epoch": 0.35769623842020243,
+      "grad_norm": 0.8638574481010437,
+      "learning_rate": 3.828826522492255e-05,
+      "loss": 1.4947,
+      "step": 10850
+    },
+    {
+      "epoch": 0.35871822767283157,
+      "grad_norm": 0.8254904747009277,
+      "learning_rate": 3.821705398930713e-05,
+      "loss": 1.524,
+      "step": 10881
+    },
+    {
+      "epoch": 0.3597402169254607,
+      "grad_norm": 0.8651305437088013,
+      "learning_rate": 3.814569360103385e-05,
+      "loss": 1.5034,
+      "step": 10912
+    },
+    {
+      "epoch": 0.36076220617808985,
+      "grad_norm": 0.8567565679550171,
+      "learning_rate": 3.807418486539499e-05,
+      "loss": 1.4971,
+      "step": 10943
+    },
+    {
+      "epoch": 0.36178419543071905,
+      "grad_norm": 0.8213040828704834,
+      "learning_rate": 3.80025285893569e-05,
+      "loss": 1.5095,
+      "step": 10974
+    },
+    {
+      "epoch": 0.3628061846833482,
+      "grad_norm": 0.8153424859046936,
+      "learning_rate": 3.793072558155093e-05,
+      "loss": 1.5168,
+      "step": 11005
+    },
+    {
+      "epoch": 0.36382817393597733,
+      "grad_norm": 0.8211629390716553,
+      "learning_rate": 3.785877665226426e-05,
+      "loss": 1.5208,
+      "step": 11036
+    },
+    {
+      "epoch": 0.36485016318860647,
+      "grad_norm": 0.8744972348213196,
+      "learning_rate": 3.778668261343079e-05,
+      "loss": 1.5133,
+      "step": 11067
+    },
+    {
+      "epoch": 0.3658721524412356,
+      "grad_norm": 0.8211522698402405,
+      "learning_rate": 3.771444427862192e-05,
+      "loss": 1.5042,
+      "step": 11098
+    },
+    {
+      "epoch": 0.36689414169386475,
+      "grad_norm": 0.8390249609947205,
+      "learning_rate": 3.7642062463037465e-05,
+      "loss": 1.5214,
+      "step": 11129
+    },
+    {
+      "epoch": 0.3679161309464939,
+      "grad_norm": 0.8379174470901489,
+      "learning_rate": 3.7569537983496373e-05,
+      "loss": 1.5164,
+      "step": 11160
+    },
+    {
+      "epoch": 0.3689381201991231,
+      "grad_norm": 0.8449585437774658,
+      "learning_rate": 3.749687165842753e-05,
+      "loss": 1.5049,
+      "step": 11191
+    },
+    {
+      "epoch": 0.36996010945175223,
+      "grad_norm": 0.7959738969802856,
+      "learning_rate": 3.7424064307860536e-05,
+      "loss": 1.4941,
+      "step": 11222
+    },
+    {
+      "epoch": 0.37098209870438137,
+      "grad_norm": 0.8311371207237244,
+      "learning_rate": 3.735111675341645e-05,
+      "loss": 1.513,
+      "step": 11253
+    },
+    {
+      "epoch": 0.3720040879570105,
+      "grad_norm": 0.828087329864502,
+      "learning_rate": 3.7278029818298524e-05,
+      "loss": 1.4983,
+      "step": 11284
+    },
+    {
+      "epoch": 0.37302607720963965,
+      "grad_norm": 0.8467016220092773,
+      "learning_rate": 3.720480432728287e-05,
+      "loss": 1.5167,
+      "step": 11315
+    },
+    {
+      "epoch": 0.3740480664622688,
+      "grad_norm": 0.8619351983070374,
+      "learning_rate": 3.71314411067092e-05,
+      "loss": 1.5065,
+      "step": 11346
+    },
+    {
+      "epoch": 0.375070055714898,
+      "grad_norm": 0.8230463862419128,
+      "learning_rate": 3.70579409844715e-05,
+      "loss": 1.4987,
+      "step": 11377
+    },
+    {
+      "epoch": 0.37609204496752713,
+      "grad_norm": 0.8631263971328735,
+      "learning_rate": 3.698430479000865e-05,
+      "loss": 1.5023,
+      "step": 11408
+    },
+    {
+      "epoch": 0.37711403422015627,
+      "grad_norm": 0.8831419348716736,
+      "learning_rate": 3.691053335429509e-05,
+      "loss": 1.5046,
+      "step": 11439
+    },
+    {
+      "epoch": 0.3781360234727854,
+      "grad_norm": 0.8332011103630066,
+      "learning_rate": 3.683662750983147e-05,
+      "loss": 1.5002,
+      "step": 11470
+    },
+    {
+      "epoch": 0.37915801272541455,
+      "grad_norm": 0.8661298751831055,
+      "learning_rate": 3.676258809063518e-05,
+      "loss": 1.51,
+      "step": 11501
+    },
+    {
+      "epoch": 0.3801800019780437,
+      "grad_norm": 0.8714830279350281,
+      "learning_rate": 3.6688415932231004e-05,
+      "loss": 1.5031,
+      "step": 11532
+    },
+    {
+      "epoch": 0.3812019912306729,
+      "grad_norm": 0.8633294701576233,
+      "learning_rate": 3.661411187164166e-05,
+      "loss": 1.4854,
+      "step": 11563
+    },
+    {
+      "epoch": 0.38222398048330203,
+      "grad_norm": 0.8436555862426758,
+      "learning_rate": 3.65396767473784e-05,
+      "loss": 1.5213,
+      "step": 11594
+    },
+    {
+      "epoch": 0.38324596973593117,
+      "grad_norm": 0.8612047433853149,
+      "learning_rate": 3.6465111399431465e-05,
+      "loss": 1.5002,
+      "step": 11625
+    },
+    {
+      "epoch": 0.3842679589885603,
+      "grad_norm": 0.8069844245910645,
+      "learning_rate": 3.6390416669260674e-05,
+      "loss": 1.5034,
+      "step": 11656
+    },
+    {
+      "epoch": 0.38528994824118945,
+      "grad_norm": 0.8230804204940796,
+      "learning_rate": 3.63155933997859e-05,
+      "loss": 1.5155,
+      "step": 11687
+    },
+    {
+      "epoch": 0.3863119374938186,
+      "grad_norm": 0.8166376352310181,
+      "learning_rate": 3.624064243537758e-05,
+      "loss": 1.487,
+      "step": 11718
+    },
+    {
+      "epoch": 0.3873339267464478,
+      "grad_norm": 0.8213214874267578,
+      "learning_rate": 3.616556462184716e-05,
+      "loss": 1.5178,
+      "step": 11749
+    },
+    {
+      "epoch": 0.38835591599907693,
+      "grad_norm": 0.8418950438499451,
+      "learning_rate": 3.609036080643755e-05,
+      "loss": 1.5173,
+      "step": 11780
+    },
+    {
+      "epoch": 0.38937790525170607,
+      "grad_norm": 0.839227020740509,
+      "learning_rate": 3.60150318378136e-05,
+      "loss": 1.51,
+      "step": 11811
+    },
+    {
+      "epoch": 0.3903998945043352,
+      "grad_norm": 0.8407977819442749,
+      "learning_rate": 3.5939578566052465e-05,
+      "loss": 1.4967,
+      "step": 11842
+    },
+    {
+      "epoch": 0.39142188375696435,
+      "grad_norm": 0.8286086320877075,
+      "learning_rate": 3.586400184263408e-05,
+      "loss": 1.4817,
+      "step": 11873
+    },
+    {
+      "epoch": 0.3924438730095935,
+      "grad_norm": 0.8609039783477783,
+      "learning_rate": 3.578830252043148e-05,
+      "loss": 1.4842,
+      "step": 11904
+    },
+    {
+      "epoch": 0.3934658622622227,
+      "grad_norm": 0.8497804403305054,
+      "learning_rate": 3.571248145370125e-05,
+      "loss": 1.509,
+      "step": 11935
+    },
+    {
+      "epoch": 0.39448785151485183,
+      "grad_norm": 0.8288097977638245,
+      "learning_rate": 3.5636539498073794e-05,
+      "loss": 1.4914,
+      "step": 11966
+    },
+    {
+      "epoch": 0.39550984076748097,
+      "grad_norm": 0.8199227452278137,
+      "learning_rate": 3.556047751054378e-05,
+      "loss": 1.4754,
+      "step": 11997
+    },
+    {
+      "epoch": 0.3965318300201101,
+      "grad_norm": 0.8441981077194214,
+      "learning_rate": 3.548429634946039e-05,
+      "loss": 1.4826,
+      "step": 12028
+    },
+    {
+      "epoch": 0.39755381927273925,
+      "grad_norm": 0.7997297048568726,
+      "learning_rate": 3.540799687451768e-05,
+      "loss": 1.4804,
+      "step": 12059
+    },
+    {
+      "epoch": 0.3985758085253684,
+      "grad_norm": 0.8018672466278076,
+      "learning_rate": 3.533157994674485e-05,
+      "loss": 1.4995,
+      "step": 12090
+    },
+    {
+      "epoch": 0.3995977977779976,
+      "grad_norm": 0.8712153434753418,
+      "learning_rate": 3.5255046428496546e-05,
+      "loss": 1.5044,
+      "step": 12121
+    },
+    {
+      "epoch": 0.40061978703062673,
+      "grad_norm": 0.852215588092804,
+      "learning_rate": 3.517839718344311e-05,
+      "loss": 1.4931,
+      "step": 12152
+    },
+    {
+      "epoch": 0.40164177628325587,
+      "grad_norm": 0.8421558141708374,
+      "learning_rate": 3.510163307656086e-05,
+      "loss": 1.4967,
+      "step": 12183
+    },
+    {
+      "epoch": 0.402663765535885,
+      "grad_norm": 0.8428821563720703,
+      "learning_rate": 3.5024754974122324e-05,
+      "loss": 1.5042,
+      "step": 12214
+    },
+    {
+      "epoch": 0.40368575478851415,
+      "grad_norm": 0.8397454023361206,
+      "learning_rate": 3.494776374368643e-05,
+      "loss": 1.4987,
+      "step": 12245
+    },
+    {
+      "epoch": 0.4047077440411433,
+      "grad_norm": 0.8511505126953125,
+      "learning_rate": 3.4870660254088724e-05,
+      "loss": 1.5062,
+      "step": 12276
+    },
+    {
+      "epoch": 0.40572973329377243,
+      "grad_norm": 0.8236075639724731,
+      "learning_rate": 3.479344537543164e-05,
+      "loss": 1.4907,
+      "step": 12307
+    },
+    {
+      "epoch": 0.40675172254640163,
+      "grad_norm": 0.8540985584259033,
+      "learning_rate": 3.4716119979074565e-05,
+      "loss": 1.4898,
+      "step": 12338
+    },
+    {
+      "epoch": 0.40777371179903077,
+      "grad_norm": 0.8223760724067688,
+      "learning_rate": 3.463868493762412e-05,
+      "loss": 1.4794,
+      "step": 12369
+    },
+    {
+      "epoch": 0.4087957010516599,
+      "grad_norm": 0.8553142547607422,
+      "learning_rate": 3.456114112492418e-05,
+      "loss": 1.5021,
+      "step": 12400
+    },
+    {
+      "epoch": 0.40981769030428905,
+      "grad_norm": 0.83010333776474,
+      "learning_rate": 3.4483489416046164e-05,
+      "loss": 1.4776,
+      "step": 12431
+    },
+    {
+      "epoch": 0.4108396795569182,
+      "grad_norm": 0.8293822407722473,
+      "learning_rate": 3.440573068727905e-05,
+      "loss": 1.4883,
+      "step": 12462
+    },
+    {
+      "epoch": 0.41186166880954733,
+      "grad_norm": 0.8343706727027893,
+      "learning_rate": 3.4327865816119495e-05,
+      "loss": 1.4919,
+      "step": 12493
+    },
+    {
+      "epoch": 0.41288365806217653,
+      "grad_norm": 0.8471996784210205,
+      "learning_rate": 3.4249895681262025e-05,
+      "loss": 1.4999,
+      "step": 12524
+    },
+    {
+      "epoch": 0.41390564731480567,
+      "grad_norm": 0.8553738594055176,
+      "learning_rate": 3.417182116258899e-05,
+      "loss": 1.4816,
+      "step": 12555
+    },
+    {
+      "epoch": 0.4149276365674348,
+      "grad_norm": 0.8174490332603455,
+      "learning_rate": 3.409364314116074e-05,
+      "loss": 1.471,
+      "step": 12586
+    },
+    {
+      "epoch": 0.41594962582006395,
+      "grad_norm": 0.797466516494751,
+      "learning_rate": 3.401536249920559e-05,
+      "loss": 1.4922,
+      "step": 12617
+    },
+    {
+      "epoch": 0.4169716150726931,
+      "grad_norm": 0.8381075263023376,
+      "learning_rate": 3.393698012010998e-05,
+      "loss": 1.4955,
+      "step": 12648
+    },
+    {
+      "epoch": 0.41799360432532223,
+      "grad_norm": 0.8211097717285156,
+      "learning_rate": 3.385849688840839e-05,
+      "loss": 1.5054,
+      "step": 12679
+    },
+    {
+      "epoch": 0.41901559357795143,
+      "grad_norm": 0.8614106178283691,
+      "learning_rate": 3.3779913689773414e-05,
+      "loss": 1.4906,
+      "step": 12710
+    },
+    {
+      "epoch": 0.42003758283058057,
+      "grad_norm": 0.8300454616546631,
+      "learning_rate": 3.370123141100578e-05,
+      "loss": 1.5008,
+      "step": 12741
+    },
+    {
+      "epoch": 0.4210595720832097,
+      "grad_norm": 0.8297508955001831,
+      "learning_rate": 3.3622450940024305e-05,
+      "loss": 1.4885,
+      "step": 12772
+    },
+    {
+      "epoch": 0.42208156133583885,
+      "grad_norm": 0.8315346837043762,
+      "learning_rate": 3.35435731658559e-05,
+      "loss": 1.4839,
+      "step": 12803
+    },
+    {
+      "epoch": 0.423103550588468,
+      "grad_norm": 0.8035879135131836,
+      "learning_rate": 3.346459897862552e-05,
+      "loss": 1.4849,
+      "step": 12834
+    },
+    {
+      "epoch": 0.42412553984109713,
+      "grad_norm": 0.8297046422958374,
+      "learning_rate": 3.338552926954613e-05,
+      "loss": 1.4874,
+      "step": 12865
+    },
+    {
+      "epoch": 0.42514752909372633,
+      "grad_norm": 0.8357899188995361,
+      "learning_rate": 3.330636493090868e-05,
+      "loss": 1.4894,
+      "step": 12896
+    },
+    {
+      "epoch": 0.42616951834635547,
+      "grad_norm": 0.8307090997695923,
+      "learning_rate": 3.322710685607193e-05,
+      "loss": 1.4906,
+      "step": 12927
+    },
+    {
+      "epoch": 0.4271915075989846,
+      "grad_norm": 0.8082265853881836,
+      "learning_rate": 3.314775593945251e-05,
+      "loss": 1.4879,
+      "step": 12958
+    },
+    {
+      "epoch": 0.42821349685161375,
+      "grad_norm": 0.8400994539260864,
+      "learning_rate": 3.3068313076514714e-05,
+      "loss": 1.4902,
+      "step": 12989
+    },
+    {
+      "epoch": 0.4292354861042429,
+      "grad_norm": 0.8030775785446167,
+      "learning_rate": 3.298877916376047e-05,
+      "loss": 1.4844,
+      "step": 13020
+    },
+    {
+      "epoch": 0.43025747535687203,
+      "grad_norm": 0.8701795935630798,
+      "learning_rate": 3.290915509871915e-05,
+      "loss": 1.4803,
+      "step": 13051
+    },
+    {
+      "epoch": 0.43127946460950123,
+      "grad_norm": 0.8453795313835144,
+      "learning_rate": 3.282944177993753e-05,
+      "loss": 1.4841,
+      "step": 13082
+    },
+    {
+      "epoch": 0.43230145386213037,
+      "grad_norm": 0.8204758167266846,
+      "learning_rate": 3.274964010696957e-05,
+      "loss": 1.4879,
+      "step": 13113
+    },
+    {
+      "epoch": 0.4333234431147595,
+      "grad_norm": 0.8047789931297302,
+      "learning_rate": 3.266975098036629e-05,
+      "loss": 1.4869,
+      "step": 13144
+    },
+    {
+      "epoch": 0.43434543236738865,
+      "grad_norm": 0.8196751475334167,
+      "learning_rate": 3.258977530166562e-05,
+      "loss": 1.487,
+      "step": 13175
+    },
+    {
+      "epoch": 0.4353674216200178,
+      "grad_norm": 0.8294420838356018,
+      "learning_rate": 3.250971397338227e-05,
+      "loss": 1.4876,
+      "step": 13206
+    },
+    {
+      "epoch": 0.43638941087264693,
+      "grad_norm": 0.7943994998931885,
+      "learning_rate": 3.2429567898997404e-05,
+      "loss": 1.4601,
+      "step": 13237
+    },
+    {
+      "epoch": 0.43741140012527613,
+      "grad_norm": 0.8354049921035767,
+      "learning_rate": 3.234933798294859e-05,
+      "loss": 1.4914,
+      "step": 13268
+    },
+    {
+      "epoch": 0.43843338937790527,
+      "grad_norm": 0.8477530479431152,
+      "learning_rate": 3.2269025130619535e-05,
+      "loss": 1.4559,
+      "step": 13299
+    },
+    {
+      "epoch": 0.4394553786305344,
+      "grad_norm": 0.8300078511238098,
+      "learning_rate": 3.218863024832985e-05,
+      "loss": 1.4727,
+      "step": 13330
+    },
+    {
+      "epoch": 0.44047736788316355,
+      "grad_norm": 0.83632892370224,
+      "learning_rate": 3.2108154243324864e-05,
+      "loss": 1.4822,
+      "step": 13361
+    },
+    {
+      "epoch": 0.4414993571357927,
+      "grad_norm": 0.8274350166320801,
+      "learning_rate": 3.2027598023765345e-05,
+      "loss": 1.482,
+      "step": 13392
+    },
+    {
+      "epoch": 0.44252134638842183,
+      "grad_norm": 0.8118026852607727,
+      "learning_rate": 3.194696249871729e-05,
+      "loss": 1.4947,
+      "step": 13423
+    },
+    {
+      "epoch": 0.443543335641051,
+      "grad_norm": 0.7988345623016357,
+      "learning_rate": 3.186624857814164e-05,
+      "loss": 1.4634,
+      "step": 13454
+    },
+    {
+      "epoch": 0.44456532489368017,
+      "grad_norm": 0.8391137719154358,
+      "learning_rate": 3.178545717288401e-05,
+      "loss": 1.4715,
+      "step": 13485
+    },
+    {
+      "epoch": 0.4455873141463093,
+      "grad_norm": 0.8533878326416016,
+      "learning_rate": 3.170458919466444e-05,
+      "loss": 1.4667,
+      "step": 13516
+    },
+    {
+      "epoch": 0.44660930339893845,
+      "grad_norm": 0.8210632801055908,
+      "learning_rate": 3.1623645556067063e-05,
+      "loss": 1.475,
+      "step": 13547
+    },
+    {
+      "epoch": 0.4476312926515676,
+      "grad_norm": 0.8421019911766052,
+      "learning_rate": 3.154262717052985e-05,
+      "loss": 1.4814,
+      "step": 13578
+    },
+    {
+      "epoch": 0.44865328190419673,
+      "grad_norm": 0.8044966459274292,
+      "learning_rate": 3.146153495233426e-05,
+      "loss": 1.4739,
+      "step": 13609
+    },
+    {
+      "epoch": 0.4496752711568259,
+      "grad_norm": 0.8291748762130737,
+      "learning_rate": 3.1380369816594944e-05,
+      "loss": 1.4723,
+      "step": 13640
+    },
+    {
+      "epoch": 0.45069726040945507,
+      "grad_norm": 0.8362712264060974,
+      "learning_rate": 3.129913267924946e-05,
+      "loss": 1.4783,
+      "step": 13671
+    },
+    {
+      "epoch": 0.4517192496620842,
+      "grad_norm": 0.809481143951416,
+      "learning_rate": 3.121782445704782e-05,
+      "loss": 1.4771,
+      "step": 13702
+    },
+    {
+      "epoch": 0.45274123891471335,
+      "grad_norm": 0.8484416007995605,
+      "learning_rate": 3.11364460675423e-05,
+      "loss": 1.4615,
+      "step": 13733
+    },
+    {
+      "epoch": 0.4537632281673425,
+      "grad_norm": 0.8735551238059998,
+      "learning_rate": 3.1054998429076934e-05,
+      "loss": 1.4754,
+      "step": 13764
+    },
+    {
+      "epoch": 0.45478521741997163,
+      "grad_norm": 0.8091564774513245,
+      "learning_rate": 3.097348246077728e-05,
+      "loss": 1.4853,
+      "step": 13795
+    },
+    {
+      "epoch": 0.4558072066726008,
+      "grad_norm": 0.8234131932258606,
+      "learning_rate": 3.0891899082539924e-05,
+      "loss": 1.4786,
+      "step": 13826
+    },
+    {
+      "epoch": 0.45682919592522997,
+      "grad_norm": 0.8537734746932983,
+      "learning_rate": 3.0810249215022233e-05,
+      "loss": 1.4757,
+      "step": 13857
+    },
+    {
+      "epoch": 0.4578511851778591,
+      "grad_norm": 0.8478782773017883,
+      "learning_rate": 3.0728533779631865e-05,
+      "loss": 1.4621,
+      "step": 13888
+    },
+    {
+      "epoch": 0.45887317443048825,
+      "grad_norm": 0.8195151090621948,
+      "learning_rate": 3.064675369851637e-05,
+      "loss": 1.4727,
+      "step": 13919
+    },
+    {
+      "epoch": 0.4598951636831174,
+      "grad_norm": 0.8208017349243164,
+      "learning_rate": 3.056490989455289e-05,
+      "loss": 1.4744,
+      "step": 13950
+    },
+    {
+      "epoch": 0.46091715293574653,
+      "grad_norm": 0.7893416285514832,
+      "learning_rate": 3.0483003291337596e-05,
+      "loss": 1.4713,
+      "step": 13981
+    },
+    {
+      "epoch": 0.4619391421883757,
+      "grad_norm": 2.002336263656616,
+      "learning_rate": 3.040103481317539e-05,
+      "loss": 1.4523,
+      "step": 14012
+    },
+    {
+      "epoch": 0.46296113144100487,
+      "grad_norm": 0.7943160533905029,
+      "learning_rate": 3.03190053850694e-05,
+      "loss": 1.4635,
+      "step": 14043
+    },
+    {
+      "epoch": 0.463983120693634,
+      "grad_norm": 0.8262372612953186,
+      "learning_rate": 3.0236915932710573e-05,
+      "loss": 1.47,
+      "step": 14074
+    },
+    {
+      "epoch": 0.46500510994626315,
+      "grad_norm": 0.8457150459289551,
+      "learning_rate": 3.0154767382467232e-05,
+      "loss": 1.4757,
+      "step": 14105
+    },
+    {
+      "epoch": 0.4660270991988923,
+      "grad_norm": 0.8377997279167175,
+      "learning_rate": 3.0072560661374582e-05,
+      "loss": 1.4752,
+      "step": 14136
+    },
+    {
+      "epoch": 0.46704908845152143,
+      "grad_norm": 0.7971871495246887,
+      "learning_rate": 2.999029669712431e-05,
+      "loss": 1.4744,
+      "step": 14167
+    },
+    {
+      "epoch": 0.4680710777041506,
+      "grad_norm": 0.8239099383354187,
+      "learning_rate": 2.990797641805408e-05,
+      "loss": 1.4683,
+      "step": 14198
+    },
+    {
+      "epoch": 0.46909306695677977,
+      "grad_norm": 0.8354623317718506,
+      "learning_rate": 2.982560075313704e-05,
+      "loss": 1.4859,
+      "step": 14229
+    },
+    {
+      "epoch": 0.4701150562094089,
+      "grad_norm": 0.8527148962020874,
+      "learning_rate": 2.9743170631971368e-05,
+      "loss": 1.4569,
+      "step": 14260
+    },
+    {
+      "epoch": 0.47113704546203805,
+      "grad_norm": 0.8640620112419128,
+      "learning_rate": 2.9660686984769792e-05,
+      "loss": 1.4711,
+      "step": 14291
+    },
+    {
+      "epoch": 0.4721590347146672,
+      "grad_norm": 0.8033869862556458,
+      "learning_rate": 2.9578150742349047e-05,
+      "loss": 1.4803,
+      "step": 14322
+    },
+    {
+      "epoch": 0.47318102396729633,
+      "grad_norm": 0.8113462924957275,
+      "learning_rate": 2.949556283611942e-05,
+      "loss": 1.4644,
+      "step": 14353
+    },
+    {
+      "epoch": 0.4742030132199255,
+      "grad_norm": 0.8008654117584229,
+      "learning_rate": 2.9412924198074206e-05,
+      "loss": 1.4591,
+      "step": 14384
+    },
+    {
+      "epoch": 0.47522500247255467,
+      "grad_norm": 0.8297123312950134,
+      "learning_rate": 2.9330235760779208e-05,
+      "loss": 1.4772,
+      "step": 14415
+    },
+    {
+      "epoch": 0.4762469917251838,
+      "grad_norm": 0.8336069583892822,
+      "learning_rate": 2.9247498457362188e-05,
+      "loss": 1.4735,
+      "step": 14446
+    },
+    {
+      "epoch": 0.47726898097781295,
+      "grad_norm": 0.7794061899185181,
+      "learning_rate": 2.9164713221502373e-05,
+      "loss": 1.4655,
+      "step": 14477
+    },
+    {
+      "epoch": 0.4782909702304421,
+      "grad_norm": 0.8473496437072754,
+      "learning_rate": 2.9081880987419912e-05,
+      "loss": 1.4764,
+      "step": 14508
+    },
+    {
+      "epoch": 0.47931295948307123,
+      "grad_norm": 0.8163958191871643,
+      "learning_rate": 2.8999002689865296e-05,
+      "loss": 1.4735,
+      "step": 14539
+    },
+    {
+      "epoch": 0.4803349487357004,
+      "grad_norm": 0.8134874701499939,
+      "learning_rate": 2.8916079264108852e-05,
+      "loss": 1.4725,
+      "step": 14570
+    },
+    {
+      "epoch": 0.48135693798832957,
+      "grad_norm": 0.788411557674408,
+      "learning_rate": 2.883311164593017e-05,
+      "loss": 1.4641,
+      "step": 14601
+    },
+    {
+      "epoch": 0.4823789272409587,
+      "grad_norm": 0.8075402975082397,
+      "learning_rate": 2.875010077160754e-05,
+      "loss": 1.473,
+      "step": 14632
+    },
+    {
+      "epoch": 0.48340091649358785,
+      "grad_norm": 0.8053046464920044,
+      "learning_rate": 2.866704757790741e-05,
+      "loss": 1.4642,
+      "step": 14663
+    },
+    {
+      "epoch": 0.484422905746217,
+      "grad_norm": 0.8402507901191711,
+      "learning_rate": 2.858395300207376e-05,
+      "loss": 1.4768,
+      "step": 14694
+    },
+    {
+      "epoch": 0.48544489499884613,
+      "grad_norm": 0.8206636905670166,
+      "learning_rate": 2.8500817981817607e-05,
+      "loss": 1.448,
+      "step": 14725
+    },
+    {
+      "epoch": 0.4864668842514753,
+      "grad_norm": 0.8397791385650635,
+      "learning_rate": 2.8417643455306336e-05,
+      "loss": 1.4611,
+      "step": 14756
+    },
+    {
+      "epoch": 0.4874888735041044,
+      "grad_norm": 0.8360273838043213,
+      "learning_rate": 2.8334430361153185e-05,
+      "loss": 1.4681,
+      "step": 14787
+    },
+    {
+      "epoch": 0.4885108627567336,
+      "grad_norm": 0.7953571677207947,
+      "learning_rate": 2.8251179638406612e-05,
+      "loss": 1.4749,
+      "step": 14818
+    },
+    {
+      "epoch": 0.48953285200936275,
+      "grad_norm": 0.8476656079292297,
+      "learning_rate": 2.8167892226539704e-05,
+      "loss": 1.4774,
+      "step": 14849
+    },
+    {
+      "epoch": 0.4905548412619919,
+      "grad_norm": 0.7990041375160217,
+      "learning_rate": 2.8084569065439588e-05,
+      "loss": 1.4599,
+      "step": 14880
+    },
+    {
+      "epoch": 0.49157683051462103,
+      "grad_norm": 0.8252399563789368,
+      "learning_rate": 2.8001211095396807e-05,
+      "loss": 1.482,
+      "step": 14911
+    },
+    {
+      "epoch": 0.4925988197672502,
+      "grad_norm": 0.8177118897438049,
+      "learning_rate": 2.791781925709473e-05,
+      "loss": 1.476,
+      "step": 14942
+    },
+    {
+      "epoch": 0.4936208090198793,
+      "grad_norm": 0.8130631446838379,
+      "learning_rate": 2.7834394491598908e-05,
+      "loss": 1.4584,
+      "step": 14973
+    },
+    {
+      "epoch": 0.4946427982725085,
+      "grad_norm": 0.8575690388679504,
+      "learning_rate": 2.7750937740346485e-05,
+      "loss": 1.4567,
+      "step": 15004
+    },
+    {
+      "epoch": 0.49566478752513765,
+      "grad_norm": 0.8180646300315857,
+      "learning_rate": 2.7667449945135564e-05,
+      "loss": 1.4838,
+      "step": 15035
+    },
+    {
+      "epoch": 0.4966867767777668,
+      "grad_norm": 0.8085652589797974,
+      "learning_rate": 2.7583932048114557e-05,
+      "loss": 1.4473,
+      "step": 15066
+    },
+    {
+      "epoch": 0.49770876603039593,
+      "grad_norm": 0.7771590352058411,
+      "learning_rate": 2.7500384991771587e-05,
+      "loss": 1.4613,
+      "step": 15097
+    },
+    {
+      "epoch": 0.4987307552830251,
+      "grad_norm": 0.8312346339225769,
+      "learning_rate": 2.7416809718923825e-05,
+      "loss": 1.4561,
+      "step": 15128
+    },
+    {
+      "epoch": 0.4997527445356542,
+      "grad_norm": 0.8133281469345093,
+      "learning_rate": 2.7333207172706864e-05,
+      "loss": 1.4617,
+      "step": 15159
+    },
+    {
+      "epoch": 0.5007747337882834,
+      "grad_norm": 0.8043552041053772,
+      "learning_rate": 2.7249578296564088e-05,
+      "loss": 1.4814,
+      "step": 15190
+    },
+    {
+      "epoch": 0.5017967230409125,
+      "grad_norm": 0.8398190140724182,
+      "learning_rate": 2.7165924034235973e-05,
+      "loss": 1.4604,
+      "step": 15221
+    },
+    {
+      "epoch": 0.5028187122935417,
+      "grad_norm": 0.8101472854614258,
+      "learning_rate": 2.708224532974953e-05,
+      "loss": 1.4655,
+      "step": 15252
+    }
+  ],
+  "logging_steps": 31,
+  "max_steps": 30517,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 3052,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.065842709765292e+19,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-15260/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:653df926fe7b7d8bc5bd05f93f711031a6b8f6cec15c51d661d79c0b0841d6f1
+size 5304

checkpoint-18312/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/Qwen2.5-7B-Instruct-ta-madlad-mean/",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 161672
+}

checkpoint-18312/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.44.0.dev0"
+}

checkpoint-18312/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2b22cb2baa7479c8eacf5109616ef8bb8147b0840e1b9f22d960eb9d1403b2e
+size 4842817304

checkpoint-18312/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:becf3c41c7359877372d1f9bdba9efe52cb2b8dab7330b346e831a36665b8f0e
+size 4998852224

checkpoint-18312/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad9da13aef49ef9aa84ff7ac6ae375fc2f8c339648214e7663e44e16a6763847
+size 4984124304

checkpoint-18312/model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc2c86e34819a46908bfe3ad42f3986e7efdfc34f67e43f40f690f77c7b0672
+size 4932743992

checkpoint-18312/model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:891f86a74d6b1791b98b581ff94cbedb16bfdb78595b9697dc3fd2ecc5974ba2
+size 4998852296

checkpoint-18312/model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93aab516b338dce5b05f5997622fdbb81d198ae034347626ad5febee2e2bef20
+size 3662865184

checkpoint-18312/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edf0e12d8fefb2e5121a1e1539bd77d454a0853d062db0834d73db5d2923e61f
+size 2317729920

checkpoint-18312/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 30737946624
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00006-of-00007.safetensors"
+  }
+}

checkpoint-18312/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2e03a328d3df4d12876c92abfe8251b8a79ba3cb9553e634b98039de099452a
+size 16728842070

checkpoint-18312/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
+size 14244

checkpoint-18312/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0e65c3d6f29e706fd941a38280ce5628189a6998eac6d29abbeab00ad838d00
+size 1064

checkpoint-18312/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:653df926fe7b7d8bc5bd05f93f711031a6b8f6cec15c51d661d79c0b0841d6f1
+size 5304

checkpoint-21364/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/Qwen2.5-7B-Instruct-ta-madlad-mean/",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 161672
+}

checkpoint-21364/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.44.0.dev0"
+}

checkpoint-21364/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3983a0b99e4066b29806ea42faba0a0ef5ed44c4a65e3dab60e8348a451ab9d6
+size 4842817304

checkpoint-21364/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:becf3c41c7359877372d1f9bdba9efe52cb2b8dab7330b346e831a36665b8f0e
+size 4998852224

checkpoint-21364/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad9da13aef49ef9aa84ff7ac6ae375fc2f8c339648214e7663e44e16a6763847
+size 4984124304