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-te-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 sha256:267cd392fdf9e9940100e3c7bc998f4d6e0af5a0298a44b2e38c9dd48a0ae42a
+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 sha256:59081cf45ce79282f5e8de76e6911a4b4239410680b53d3b35f7e618d86c9233
+size 3662865184

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05a09d9502f9c3eeee9836978aafa3ace20185bd9a14c03b15b331e650e49cd0
+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 sha256:49f922fc284e343b45fe31e00a63fd35a89a34ff3f010df429ff442cb2bf424c
+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": 0.5150402902586171,
+  "eval_steps": 500,
+  "global_step": 12208,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0013078513268362654,
+      "grad_norm": 31.18772315979004,
+      "learning_rate": 1.0157273918741808e-06,
+      "loss": 9.3832,
+      "step": 31
+    },
+    {
+      "epoch": 0.0026157026536725307,
+      "grad_norm": 24.045747756958008,
+      "learning_rate": 2.0314547837483616e-06,
+      "loss": 7.9011,
+      "step": 62
+    },
+    {
+      "epoch": 0.003923553980508796,
+      "grad_norm": 16.459999084472656,
+      "learning_rate": 3.0471821756225426e-06,
+      "loss": 6.3655,
+      "step": 93
+    },
+    {
+      "epoch": 0.0052314053073450615,
+      "grad_norm": 5.892439365386963,
+      "learning_rate": 4.062909567496723e-06,
+      "loss": 5.1577,
+      "step": 124
+    },
+    {
+      "epoch": 0.0065392566341813275,
+      "grad_norm": 7.445889949798584,
+      "learning_rate": 5.078636959370905e-06,
+      "loss": 4.4767,
+      "step": 155
+    },
+    {
+      "epoch": 0.007847107961017593,
+      "grad_norm": 8.36017894744873,
+      "learning_rate": 6.094364351245085e-06,
+      "loss": 4.0756,
+      "step": 186
+    },
+    {
+      "epoch": 0.009154959287853858,
+      "grad_norm": 13.23757266998291,
+      "learning_rate": 7.110091743119267e-06,
+      "loss": 3.7893,
+      "step": 217
+    },
+    {
+      "epoch": 0.010462810614690123,
+      "grad_norm": 10.12263011932373,
+      "learning_rate": 8.125819134993446e-06,
+      "loss": 3.6154,
+      "step": 248
+    },
+    {
+      "epoch": 0.01177066194152639,
+      "grad_norm": 6.559150218963623,
+      "learning_rate": 9.141546526867629e-06,
+      "loss": 3.4391,
+      "step": 279
+    },
+    {
+      "epoch": 0.013078513268362655,
+      "grad_norm": 6.898993015289307,
+      "learning_rate": 1.015727391874181e-05,
+      "loss": 3.3229,
+      "step": 310
+    },
+    {
+      "epoch": 0.01438636459519892,
+      "grad_norm": 8.434200286865234,
+      "learning_rate": 1.117300131061599e-05,
+      "loss": 3.225,
+      "step": 341
+    },
+    {
+      "epoch": 0.015694215922035185,
+      "grad_norm": 7.735746383666992,
+      "learning_rate": 1.218872870249017e-05,
+      "loss": 3.1381,
+      "step": 372
+    },
+    {
+      "epoch": 0.01700206724887145,
+      "grad_norm": 7.964824676513672,
+      "learning_rate": 1.3204456094364351e-05,
+      "loss": 3.06,
+      "step": 403
+    },
+    {
+      "epoch": 0.018309918575707716,
+      "grad_norm": 6.081613063812256,
+      "learning_rate": 1.4220183486238533e-05,
+      "loss": 3.0052,
+      "step": 434
+    },
+    {
+      "epoch": 0.01961776990254398,
+      "grad_norm": 6.740341663360596,
+      "learning_rate": 1.5235910878112714e-05,
+      "loss": 2.9035,
+      "step": 465
+    },
+    {
+      "epoch": 0.020925621229380246,
+      "grad_norm": 4.908828258514404,
+      "learning_rate": 1.6251638269986893e-05,
+      "loss": 2.8602,
+      "step": 496
+    },
+    {
+      "epoch": 0.02223347255621651,
+      "grad_norm": 5.6150360107421875,
+      "learning_rate": 1.7267365661861077e-05,
+      "loss": 2.8223,
+      "step": 527
+    },
+    {
+      "epoch": 0.02354132388305278,
+      "grad_norm": 3.5981647968292236,
+      "learning_rate": 1.8283093053735257e-05,
+      "loss": 2.7488,
+      "step": 558
+    },
+    {
+      "epoch": 0.024849175209889045,
+      "grad_norm": 4.921584606170654,
+      "learning_rate": 1.9298820445609438e-05,
+      "loss": 2.741,
+      "step": 589
+    },
+    {
+      "epoch": 0.02615702653672531,
+      "grad_norm": 3.8303065299987793,
+      "learning_rate": 2.031454783748362e-05,
+      "loss": 2.6923,
+      "step": 620
+    },
+    {
+      "epoch": 0.027464877863561575,
+      "grad_norm": 3.3674638271331787,
+      "learning_rate": 2.13302752293578e-05,
+      "loss": 2.6402,
+      "step": 651
+    },
+    {
+      "epoch": 0.02877272919039784,
+      "grad_norm": 4.096519947052002,
+      "learning_rate": 2.234600262123198e-05,
+      "loss": 2.6372,
+      "step": 682
+    },
+    {
+      "epoch": 0.030080580517234105,
+      "grad_norm": 3.10866641998291,
+      "learning_rate": 2.336173001310616e-05,
+      "loss": 2.5979,
+      "step": 713
+    },
+    {
+      "epoch": 0.03138843184407037,
+      "grad_norm": 3.3147943019866943,
+      "learning_rate": 2.437745740498034e-05,
+      "loss": 2.549,
+      "step": 744
+    },
+    {
+      "epoch": 0.032696283170906636,
+      "grad_norm": 3.045280933380127,
+      "learning_rate": 2.5393184796854525e-05,
+      "loss": 2.5487,
+      "step": 775
+    },
+    {
+      "epoch": 0.0340041344977429,
+      "grad_norm": 3.2536299228668213,
+      "learning_rate": 2.6408912188728702e-05,
+      "loss": 2.5138,
+      "step": 806
+    },
+    {
+      "epoch": 0.035311985824579166,
+      "grad_norm": 3.108548641204834,
+      "learning_rate": 2.7424639580602886e-05,
+      "loss": 2.5006,
+      "step": 837
+    },
+    {
+      "epoch": 0.03661983715141543,
+      "grad_norm": 3.048689603805542,
+      "learning_rate": 2.8440366972477066e-05,
+      "loss": 2.4434,
+      "step": 868
+    },
+    {
+      "epoch": 0.037927688478251696,
+      "grad_norm": 2.8378429412841797,
+      "learning_rate": 2.9456094364351244e-05,
+      "loss": 2.4403,
+      "step": 899
+    },
+    {
+      "epoch": 0.03923553980508796,
+      "grad_norm": 2.731419324874878,
+      "learning_rate": 3.0471821756225428e-05,
+      "loss": 2.4028,
+      "step": 930
+    },
+    {
+      "epoch": 0.04054339113192423,
+      "grad_norm": 2.4825587272644043,
+      "learning_rate": 3.148754914809961e-05,
+      "loss": 2.3695,
+      "step": 961
+    },
+    {
+      "epoch": 0.04185124245876049,
+      "grad_norm": 2.5020129680633545,
+      "learning_rate": 3.2503276539973785e-05,
+      "loss": 2.3513,
+      "step": 992
+    },
+    {
+      "epoch": 0.04315909378559676,
+      "grad_norm": 2.374310255050659,
+      "learning_rate": 3.351900393184797e-05,
+      "loss": 2.3221,
+      "step": 1023
+    },
+    {
+      "epoch": 0.04446694511243302,
+      "grad_norm": 2.4097862243652344,
+      "learning_rate": 3.453473132372215e-05,
+      "loss": 2.3366,
+      "step": 1054
+    },
+    {
+      "epoch": 0.045774796439269294,
+      "grad_norm": 2.573655128479004,
+      "learning_rate": 3.555045871559633e-05,
+      "loss": 2.2997,
+      "step": 1085
+    },
+    {
+      "epoch": 0.04708264776610556,
+      "grad_norm": 2.5408434867858887,
+      "learning_rate": 3.6566186107470514e-05,
+      "loss": 2.2729,
+      "step": 1116
+    },
+    {
+      "epoch": 0.048390499092941824,
+      "grad_norm": 2.222527265548706,
+      "learning_rate": 3.7581913499344695e-05,
+      "loss": 2.2716,
+      "step": 1147
+    },
+    {
+      "epoch": 0.04969835041977809,
+      "grad_norm": 2.342715263366699,
+      "learning_rate": 3.8597640891218876e-05,
+      "loss": 2.2661,
+      "step": 1178
+    },
+    {
+      "epoch": 0.051006201746614355,
+      "grad_norm": 2.134208917617798,
+      "learning_rate": 3.9613368283093056e-05,
+      "loss": 2.2206,
+      "step": 1209
+    },
+    {
+      "epoch": 0.05231405307345062,
+      "grad_norm": 2.2482688426971436,
+      "learning_rate": 4.062909567496724e-05,
+      "loss": 2.2207,
+      "step": 1240
+    },
+    {
+      "epoch": 0.053621904400286885,
+      "grad_norm": 2.2316832542419434,
+      "learning_rate": 4.164482306684142e-05,
+      "loss": 2.1847,
+      "step": 1271
+    },
+    {
+      "epoch": 0.05492975572712315,
+      "grad_norm": 2.2321085929870605,
+      "learning_rate": 4.26605504587156e-05,
+      "loss": 2.2079,
+      "step": 1302
+    },
+    {
+      "epoch": 0.056237607053959415,
+      "grad_norm": 2.115349054336548,
+      "learning_rate": 4.367627785058978e-05,
+      "loss": 2.1458,
+      "step": 1333
+    },
+    {
+      "epoch": 0.05754545838079568,
+      "grad_norm": 2.210914373397827,
+      "learning_rate": 4.469200524246396e-05,
+      "loss": 2.1435,
+      "step": 1364
+    },
+    {
+      "epoch": 0.058853309707631946,
+      "grad_norm": 2.1882164478302,
+      "learning_rate": 4.570773263433814e-05,
+      "loss": 2.1389,
+      "step": 1395
+    },
+    {
+      "epoch": 0.06016116103446821,
+      "grad_norm": 2.01705265045166,
+      "learning_rate": 4.672346002621232e-05,
+      "loss": 2.1599,
+      "step": 1426
+    },
+    {
+      "epoch": 0.061469012361304476,
+      "grad_norm": 1.9447391033172607,
+      "learning_rate": 4.77391874180865e-05,
+      "loss": 2.1254,
+      "step": 1457
+    },
+    {
+      "epoch": 0.06277686368814074,
+      "grad_norm": 1.9278348684310913,
+      "learning_rate": 4.875491480996068e-05,
+      "loss": 2.1109,
+      "step": 1488
+    },
+    {
+      "epoch": 0.064084715014977,
+      "grad_norm": 167.2142791748047,
+      "learning_rate": 4.977064220183487e-05,
+      "loss": 2.12,
+      "step": 1519
+    },
+    {
+      "epoch": 0.06539256634181327,
+      "grad_norm": 15.058513641357422,
+      "learning_rate": 4.9999915451558777e-05,
+      "loss": 3.2174,
+      "step": 1550
+    },
+    {
+      "epoch": 0.06670041766864954,
+      "grad_norm": 2.8855061531066895,
+      "learning_rate": 4.999955597496219e-05,
+      "loss": 2.191,
+      "step": 1581
+    },
+    {
+      "epoch": 0.0680082689954858,
+      "grad_norm": 1.9484020471572876,
+      "learning_rate": 4.9998914381774255e-05,
+      "loss": 2.1053,
+      "step": 1612
+    },
+    {
+      "epoch": 0.06931612032232207,
+      "grad_norm": 5.792853832244873,
+      "learning_rate": 4.999799067923527e-05,
+      "loss": 2.1058,
+      "step": 1643
+    },
+    {
+      "epoch": 0.07062397164915833,
+      "grad_norm": 5.8536553382873535,
+      "learning_rate": 4.999678487776908e-05,
+      "loss": 2.0906,
+      "step": 1674
+    },
+    {
+      "epoch": 0.0719318229759946,
+      "grad_norm": 2.8606152534484863,
+      "learning_rate": 4.9995296990983006e-05,
+      "loss": 2.1356,
+      "step": 1705
+    },
+    {
+      "epoch": 0.07323967430283086,
+      "grad_norm": 2.423034191131592,
+      "learning_rate": 4.999352703566763e-05,
+      "loss": 2.0468,
+      "step": 1736
+    },
+    {
+      "epoch": 0.07454752562966713,
+      "grad_norm": 1.7297399044036865,
+      "learning_rate": 4.999147503179668e-05,
+      "loss": 2.0687,
+      "step": 1767
+    },
+    {
+      "epoch": 0.07585537695650339,
+      "grad_norm": 4.29679536819458,
+      "learning_rate": 4.998914100252672e-05,
+      "loss": 2.026,
+      "step": 1798
+    },
+    {
+      "epoch": 0.07716322828333966,
+      "grad_norm": 1.942807674407959,
+      "learning_rate": 4.998652497419696e-05,
+      "loss": 2.034,
+      "step": 1829
+    },
+    {
+      "epoch": 0.07847107961017592,
+      "grad_norm": 1.8823152780532837,
+      "learning_rate": 4.9983626976328927e-05,
+      "loss": 2.0186,
+      "step": 1860
+    },
+    {
+      "epoch": 0.07977893093701219,
+      "grad_norm": 2.135873556137085,
+      "learning_rate": 4.998044704162613e-05,
+      "loss": 2.0047,
+      "step": 1891
+    },
+    {
+      "epoch": 0.08108678226384845,
+      "grad_norm": 3.113102436065674,
+      "learning_rate": 4.9976985205973705e-05,
+      "loss": 1.9954,
+      "step": 1922
+    },
+    {
+      "epoch": 0.08239463359068472,
+      "grad_norm": 2.253596305847168,
+      "learning_rate": 4.997324150843799e-05,
+      "loss": 1.9744,
+      "step": 1953
+    },
+    {
+      "epoch": 0.08370248491752098,
+      "grad_norm": 5.765998363494873,
+      "learning_rate": 4.99692159912661e-05,
+      "loss": 1.9908,
+      "step": 1984
+    },
+    {
+      "epoch": 0.08501033624435725,
+      "grad_norm": 2.8442440032958984,
+      "learning_rate": 4.996490869988546e-05,
+      "loss": 1.9803,
+      "step": 2015
+    },
+    {
+      "epoch": 0.08631818757119351,
+      "grad_norm": 1.7528963088989258,
+      "learning_rate": 4.996031968290326e-05,
+      "loss": 1.9419,
+      "step": 2046
+    },
+    {
+      "epoch": 0.08762603889802978,
+      "grad_norm": 1.7754414081573486,
+      "learning_rate": 4.995544899210594e-05,
+      "loss": 1.9485,
+      "step": 2077
+    },
+    {
+      "epoch": 0.08893389022486604,
+      "grad_norm": 1.6553430557250977,
+      "learning_rate": 4.9950296682458583e-05,
+      "loss": 1.9469,
+      "step": 2108
+    },
+    {
+      "epoch": 0.09024174155170232,
+      "grad_norm": 1.7296561002731323,
+      "learning_rate": 4.994486281210429e-05,
+      "loss": 1.9195,
+      "step": 2139
+    },
+    {
+      "epoch": 0.09154959287853859,
+      "grad_norm": 1.7001283168792725,
+      "learning_rate": 4.9939147442363566e-05,
+      "loss": 1.9324,
+      "step": 2170
+    },
+    {
+      "epoch": 0.09285744420537485,
+      "grad_norm": 7.332984447479248,
+      "learning_rate": 4.9933150637733574e-05,
+      "loss": 1.9171,
+      "step": 2201
+    },
+    {
+      "epoch": 0.09416529553221112,
+      "grad_norm": 1.6546969413757324,
+      "learning_rate": 4.992687246588743e-05,
+      "loss": 1.9152,
+      "step": 2232
+    },
+    {
+      "epoch": 0.09547314685904738,
+      "grad_norm": 1.843203067779541,
+      "learning_rate": 4.992031299767347e-05,
+      "loss": 1.9015,
+      "step": 2263
+    },
+    {
+      "epoch": 0.09678099818588365,
+      "grad_norm": 4.51094388961792,
+      "learning_rate": 4.9913472307114386e-05,
+      "loss": 1.917,
+      "step": 2294
+    },
+    {
+      "epoch": 0.09808884951271991,
+      "grad_norm": 1.5267099142074585,
+      "learning_rate": 4.9906350471406446e-05,
+      "loss": 1.8985,
+      "step": 2325
+    },
+    {
+      "epoch": 0.09939670083955618,
+      "grad_norm": 2.0826663970947266,
+      "learning_rate": 4.989894757091861e-05,
+      "loss": 1.8968,
+      "step": 2356
+    },
+    {
+      "epoch": 0.10070455216639244,
+      "grad_norm": 1.4929964542388916,
+      "learning_rate": 4.989126368919158e-05,
+      "loss": 1.8711,
+      "step": 2387
+    },
+    {
+      "epoch": 0.10201240349322871,
+      "grad_norm": 1.478498935699463,
+      "learning_rate": 4.988329891293693e-05,
+      "loss": 1.8672,
+      "step": 2418
+    },
+    {
+      "epoch": 0.10332025482006497,
+      "grad_norm": 1.4785969257354736,
+      "learning_rate": 4.987505333203608e-05,
+      "loss": 1.8435,
+      "step": 2449
+    },
+    {
+      "epoch": 0.10462810614690124,
+      "grad_norm": 1.524807333946228,
+      "learning_rate": 4.9866527039539276e-05,
+      "loss": 1.8543,
+      "step": 2480
+    },
+    {
+      "epoch": 0.1059359574737375,
+      "grad_norm": 1.4232748746871948,
+      "learning_rate": 4.9857720131664594e-05,
+      "loss": 1.8463,
+      "step": 2511
+    },
+    {
+      "epoch": 0.10724380880057377,
+      "grad_norm": 1.7178603410720825,
+      "learning_rate": 4.9848632707796773e-05,
+      "loss": 1.8512,
+      "step": 2542
+    },
+    {
+      "epoch": 0.10855166012741004,
+      "grad_norm": 1.4624053239822388,
+      "learning_rate": 4.9839264870486155e-05,
+      "loss": 1.8421,
+      "step": 2573
+    },
+    {
+      "epoch": 0.1098595114542463,
+      "grad_norm": 2.0191211700439453,
+      "learning_rate": 4.9829616725447526e-05,
+      "loss": 1.8393,
+      "step": 2604
+    },
+    {
+      "epoch": 0.11116736278108257,
+      "grad_norm": 1.4346847534179688,
+      "learning_rate": 4.981968838155888e-05,
+      "loss": 1.8149,
+      "step": 2635
+    },
+    {
+      "epoch": 0.11247521410791883,
+      "grad_norm": 1.4674941301345825,
+      "learning_rate": 4.980947995086024e-05,
+      "loss": 1.8215,
+      "step": 2666
+    },
+    {
+      "epoch": 0.1137830654347551,
+      "grad_norm": 1.4122453927993774,
+      "learning_rate": 4.979899154855234e-05,
+      "loss": 1.8265,
+      "step": 2697
+    },
+    {
+      "epoch": 0.11509091676159136,
+      "grad_norm": 1.4748708009719849,
+      "learning_rate": 4.9788223292995386e-05,
+      "loss": 1.8149,
+      "step": 2728
+    },
+    {
+      "epoch": 0.11639876808842763,
+      "grad_norm": 1.40476655960083,
+      "learning_rate": 4.977717530570768e-05,
+      "loss": 1.8316,
+      "step": 2759
+    },
+    {
+      "epoch": 0.11770661941526389,
+      "grad_norm": 1.4909706115722656,
+      "learning_rate": 4.976584771136425e-05,
+      "loss": 1.8208,
+      "step": 2790
+    },
+    {
+      "epoch": 0.11901447074210016,
+      "grad_norm": 1.3661363124847412,
+      "learning_rate": 4.975424063779547e-05,
+      "loss": 1.8038,
+      "step": 2821
+    },
+    {
+      "epoch": 0.12032232206893642,
+      "grad_norm": 1.422453761100769,
+      "learning_rate": 4.974235421598557e-05,
+      "loss": 1.7926,
+      "step": 2852
+    },
+    {
+      "epoch": 0.12163017339577269,
+      "grad_norm": 1.3766013383865356,
+      "learning_rate": 4.973018858007122e-05,
+      "loss": 1.8192,
+      "step": 2883
+    },
+    {
+      "epoch": 0.12293802472260895,
+      "grad_norm": 1.3904545307159424,
+      "learning_rate": 4.9717743867339963e-05,
+      "loss": 1.7653,
+      "step": 2914
+    },
+    {
+      "epoch": 0.12424587604944522,
+      "grad_norm": 1.369018316268921,
+      "learning_rate": 4.9705020218228695e-05,
+      "loss": 1.7879,
+      "step": 2945
+    },
+    {
+      "epoch": 0.12555372737628148,
+      "grad_norm": 1.5040982961654663,
+      "learning_rate": 4.969201777632205e-05,
+      "loss": 1.7777,
+      "step": 2976
+    },
+    {
+      "epoch": 0.12686157870311776,
+      "grad_norm": 1.3161810636520386,
+      "learning_rate": 4.9678736688350846e-05,
+      "loss": 1.7654,
+      "step": 3007
+    },
+    {
+      "epoch": 0.128169430029954,
+      "grad_norm": 1.3379234075546265,
+      "learning_rate": 4.966517710419033e-05,
+      "loss": 1.7699,
+      "step": 3038
+    },
+    {
+      "epoch": 0.1294772813567903,
+      "grad_norm": 1.3384974002838135,
+      "learning_rate": 4.965133917685858e-05,
+      "loss": 1.7915,
+      "step": 3069
+    },
+    {
+      "epoch": 0.13078513268362654,
+      "grad_norm": 1.2991316318511963,
+      "learning_rate": 4.9637223062514714e-05,
+      "loss": 1.7636,
+      "step": 3100
+    },
+    {
+      "epoch": 0.13209298401046282,
+      "grad_norm": 2.500105857849121,
+      "learning_rate": 4.962282892045718e-05,
+      "loss": 1.7573,
+      "step": 3131
+    },
+    {
+      "epoch": 0.13340083533729907,
+      "grad_norm": 1.2635610103607178,
+      "learning_rate": 4.9608156913121904e-05,
+      "loss": 1.7537,
+      "step": 3162
+    },
+    {
+      "epoch": 0.13470868666413535,
+      "grad_norm": 1.2823940515518188,
+      "learning_rate": 4.959320720608049e-05,
+      "loss": 1.7709,
+      "step": 3193
+    },
+    {
+      "epoch": 0.1360165379909716,
+      "grad_norm": 1.2606983184814453,
+      "learning_rate": 4.9577979968038354e-05,
+      "loss": 1.7611,
+      "step": 3224
+    },
+    {
+      "epoch": 0.13732438931780788,
+      "grad_norm": 1.305782437324524,
+      "learning_rate": 4.956247537083282e-05,
+      "loss": 1.7547,
+      "step": 3255
+    },
+    {
+      "epoch": 0.13863224064464413,
+      "grad_norm": 1.2986756563186646,
+      "learning_rate": 4.9546693589431145e-05,
+      "loss": 1.7241,
+      "step": 3286
+    },
+    {
+      "epoch": 0.1399400919714804,
+      "grad_norm": 1.3163083791732788,
+      "learning_rate": 4.9530634801928595e-05,
+      "loss": 1.7352,
+      "step": 3317
+    },
+    {
+      "epoch": 0.14124794329831666,
+      "grad_norm": 1.2844524383544922,
+      "learning_rate": 4.9514299189546395e-05,
+      "loss": 1.7316,
+      "step": 3348
+    },
+    {
+      "epoch": 0.14255579462515294,
+      "grad_norm": 1.2861442565917969,
+      "learning_rate": 4.949768693662973e-05,
+      "loss": 1.7233,
+      "step": 3379
+    },
+    {
+      "epoch": 0.1438636459519892,
+      "grad_norm": 1.2419766187667847,
+      "learning_rate": 4.948079823064559e-05,
+      "loss": 1.7278,
+      "step": 3410
+    },
+    {
+      "epoch": 0.14517149727882547,
+      "grad_norm": 1.2518367767333984,
+      "learning_rate": 4.946363326218074e-05,
+      "loss": 1.7399,
+      "step": 3441
+    },
+    {
+      "epoch": 0.14647934860566172,
+      "grad_norm": 1.217373251914978,
+      "learning_rate": 4.9446192224939525e-05,
+      "loss": 1.7386,
+      "step": 3472
+    },
+    {
+      "epoch": 0.147787199932498,
+      "grad_norm": 1.2229036092758179,
+      "learning_rate": 4.942847531574167e-05,
+      "loss": 1.7096,
+      "step": 3503
+    },
+    {
+      "epoch": 0.14909505125933425,
+      "grad_norm": 1.2012135982513428,
+      "learning_rate": 4.941048273452008e-05,
+      "loss": 1.7195,
+      "step": 3534
+    },
+    {
+      "epoch": 0.15040290258617053,
+      "grad_norm": 1.2632161378860474,
+      "learning_rate": 4.9392214684318605e-05,
+      "loss": 1.7377,
+      "step": 3565
+    },
+    {
+      "epoch": 0.15171075391300679,
+      "grad_norm": 1.2119094133377075,
+      "learning_rate": 4.93736713712897e-05,
+      "loss": 1.7276,
+      "step": 3596
+    },
+    {
+      "epoch": 0.15301860523984306,
+      "grad_norm": 1.2516822814941406,
+      "learning_rate": 4.9354853004692124e-05,
+      "loss": 1.7224,
+      "step": 3627
+    },
+    {
+      "epoch": 0.15432645656667932,
+      "grad_norm": 1.2437561750411987,
+      "learning_rate": 4.93357597968886e-05,
+      "loss": 1.703,
+      "step": 3658
+    },
+    {
+      "epoch": 0.1556343078935156,
+      "grad_norm": 1.4856292009353638,
+      "learning_rate": 4.931639196334338e-05,
+      "loss": 1.7139,
+      "step": 3689
+    },
+    {
+      "epoch": 0.15694215922035185,
+      "grad_norm": 1.202919840812683,
+      "learning_rate": 4.9296749722619826e-05,
+      "loss": 1.7081,
+      "step": 3720
+    },
+    {
+      "epoch": 0.15825001054718812,
+      "grad_norm": 1.1720086336135864,
+      "learning_rate": 4.9276833296377966e-05,
+      "loss": 1.7086,
+      "step": 3751
+    },
+    {
+      "epoch": 0.15955786187402438,
+      "grad_norm": 1.2187249660491943,
+      "learning_rate": 4.925664290937196e-05,
+      "loss": 1.6871,
+      "step": 3782
+    },
+    {
+      "epoch": 0.16086571320086065,
+      "grad_norm": 1.1918401718139648,
+      "learning_rate": 4.9236178789447576e-05,
+      "loss": 1.7058,
+      "step": 3813
+    },
+    {
+      "epoch": 0.1621735645276969,
+      "grad_norm": 1.1956909894943237,
+      "learning_rate": 4.921544116753962e-05,
+      "loss": 1.6986,
+      "step": 3844
+    },
+    {
+      "epoch": 0.16348141585453319,
+      "grad_norm": 1.1646822690963745,
+      "learning_rate": 4.919443027766935e-05,
+      "loss": 1.6797,
+      "step": 3875
+    },
+    {
+      "epoch": 0.16478926718136944,
+      "grad_norm": 1.2145137786865234,
+      "learning_rate": 4.91731463569418e-05,
+      "loss": 1.678,
+      "step": 3906
+    },
+    {
+      "epoch": 0.16609711850820572,
+      "grad_norm": 1.2347453832626343,
+      "learning_rate": 4.915158964554312e-05,
+      "loss": 1.672,
+      "step": 3937
+    },
+    {
+      "epoch": 0.16740496983504197,
+      "grad_norm": 1.1764047145843506,
+      "learning_rate": 4.912976038673786e-05,
+      "loss": 1.6864,
+      "step": 3968
+    },
+    {
+      "epoch": 0.16871282116187825,
+      "grad_norm": 1.1730256080627441,
+      "learning_rate": 4.9107658826866254e-05,
+      "loss": 1.7021,
+      "step": 3999
+    },
+    {
+      "epoch": 0.1700206724887145,
+      "grad_norm": 1.1880205869674683,
+      "learning_rate": 4.908528521534139e-05,
+      "loss": 1.6832,
+      "step": 4030
+    },
+    {
+      "epoch": 0.17132852381555078,
+      "grad_norm": 1.1810024976730347,
+      "learning_rate": 4.906263980464644e-05,
+      "loss": 1.6674,
+      "step": 4061
+    },
+    {
+      "epoch": 0.17263637514238703,
+      "grad_norm": 1.2133933305740356,
+      "learning_rate": 4.903972285033178e-05,
+      "loss": 1.6887,
+      "step": 4092
+    },
+    {
+      "epoch": 0.1739442264692233,
+      "grad_norm": 1.1253775358200073,
+      "learning_rate": 4.901653461101213e-05,
+      "loss": 1.6884,
+      "step": 4123
+    },
+    {
+      "epoch": 0.17525207779605956,
+      "grad_norm": 1.215759038925171,
+      "learning_rate": 4.8993075348363626e-05,
+      "loss": 1.7013,
+      "step": 4154
+    },
+    {
+      "epoch": 0.17655992912289584,
+      "grad_norm": 1.1305285692214966,
+      "learning_rate": 4.896934532712084e-05,
+      "loss": 1.6573,
+      "step": 4185
+    },
+    {
+      "epoch": 0.1778677804497321,
+      "grad_norm": 1.127212405204773,
+      "learning_rate": 4.8945344815073846e-05,
+      "loss": 1.6769,
+      "step": 4216
+    },
+    {
+      "epoch": 0.17917563177656837,
+      "grad_norm": 1.1379367113113403,
+      "learning_rate": 4.892107408306516e-05,
+      "loss": 1.6583,
+      "step": 4247
+    },
+    {
+      "epoch": 0.18048348310340465,
+      "grad_norm": 1.0926482677459717,
+      "learning_rate": 4.889653340498669e-05,
+      "loss": 1.6674,
+      "step": 4278
+    },
+    {
+      "epoch": 0.1817913344302409,
+      "grad_norm": 1.1098601818084717,
+      "learning_rate": 4.8871723057776664e-05,
+      "loss": 1.6598,
+      "step": 4309
+    },
+    {
+      "epoch": 0.18309918575707718,
+      "grad_norm": 1.129784345626831,
+      "learning_rate": 4.8846643321416476e-05,
+      "loss": 1.6786,
+      "step": 4340
+    },
+    {
+      "epoch": 0.18440703708391343,
+      "grad_norm": 1.1000723838806152,
+      "learning_rate": 4.882129447892753e-05,
+      "loss": 1.6623,
+      "step": 4371
+    },
+    {
+      "epoch": 0.1857148884107497,
+      "grad_norm": 1.2229663133621216,
+      "learning_rate": 4.8795676816368076e-05,
+      "loss": 1.6675,
+      "step": 4402
+    },
+    {
+      "epoch": 0.18702273973758596,
+      "grad_norm": 1.1608648300170898,
+      "learning_rate": 4.876979062282995e-05,
+      "loss": 1.6499,
+      "step": 4433
+    },
+    {
+      "epoch": 0.18833059106442224,
+      "grad_norm": 1.1060220003128052,
+      "learning_rate": 4.8743636190435325e-05,
+      "loss": 1.6453,
+      "step": 4464
+    },
+    {
+      "epoch": 0.1896384423912585,
+      "grad_norm": 1.1028501987457275,
+      "learning_rate": 4.871721381433344e-05,
+      "loss": 1.6393,
+      "step": 4495
+    },
+    {
+      "epoch": 0.19094629371809477,
+      "grad_norm": 1.1736187934875488,
+      "learning_rate": 4.869052379269719e-05,
+      "loss": 1.6563,
+      "step": 4526
+    },
+    {
+      "epoch": 0.19225414504493102,
+      "grad_norm": 1.1284164190292358,
+      "learning_rate": 4.866356642671985e-05,
+      "loss": 1.6535,
+      "step": 4557
+    },
+    {
+      "epoch": 0.1935619963717673,
+      "grad_norm": 1.1155307292938232,
+      "learning_rate": 4.8636342020611634e-05,
+      "loss": 1.6417,
+      "step": 4588
+    },
+    {
+      "epoch": 0.19486984769860355,
+      "grad_norm": 1.1379483938217163,
+      "learning_rate": 4.860885088159626e-05,
+      "loss": 1.6432,
+      "step": 4619
+    },
+    {
+      "epoch": 0.19617769902543983,
+      "grad_norm": 1.1166200637817383,
+      "learning_rate": 4.858109331990751e-05,
+      "loss": 1.6545,
+      "step": 4650
+    },
+    {
+      "epoch": 0.19748555035227608,
+      "grad_norm": 1.081626296043396,
+      "learning_rate": 4.855306964878567e-05,
+      "loss": 1.6402,
+      "step": 4681
+    },
+    {
+      "epoch": 0.19879340167911236,
+      "grad_norm": 1.0875532627105713,
+      "learning_rate": 4.8524780184474084e-05,
+      "loss": 1.6498,
+      "step": 4712
+    },
+    {
+      "epoch": 0.2001012530059486,
+      "grad_norm": 1.0928492546081543,
+      "learning_rate": 4.8496225246215496e-05,
+      "loss": 1.6341,
+      "step": 4743
+    },
+    {
+      "epoch": 0.2014091043327849,
+      "grad_norm": 1.1116279363632202,
+      "learning_rate": 4.8467405156248505e-05,
+      "loss": 1.6389,
+      "step": 4774
+    },
+    {
+      "epoch": 0.20271695565962114,
+      "grad_norm": 1.0984513759613037,
+      "learning_rate": 4.843832023980392e-05,
+      "loss": 1.6277,
+      "step": 4805
+    },
+    {
+      "epoch": 0.20402480698645742,
+      "grad_norm": 1.09713876247406,
+      "learning_rate": 4.840897082510106e-05,
+      "loss": 1.6244,
+      "step": 4836
+    },
+    {
+      "epoch": 0.20533265831329367,
+      "grad_norm": 1.089237928390503,
+      "learning_rate": 4.8379357243344084e-05,
+      "loss": 1.6136,
+      "step": 4867
+    },
+    {
+      "epoch": 0.20664050964012995,
+      "grad_norm": 1.1337491273880005,
+      "learning_rate": 4.8349479828718236e-05,
+      "loss": 1.641,
+      "step": 4898
+    },
+    {
+      "epoch": 0.2079483609669662,
+      "grad_norm": 1.1337246894836426,
+      "learning_rate": 4.8319338918386075e-05,
+      "loss": 1.6163,
+      "step": 4929
+    },
+    {
+      "epoch": 0.20925621229380248,
+      "grad_norm": 1.112273097038269,
+      "learning_rate": 4.828893485248369e-05,
+      "loss": 1.6384,
+      "step": 4960
+    },
+    {
+      "epoch": 0.21056406362063873,
+      "grad_norm": 1.049856424331665,
+      "learning_rate": 4.825826797411682e-05,
+      "loss": 1.6245,
+      "step": 4991
+    },
+    {
+      "epoch": 0.211871914947475,
+      "grad_norm": 2.468637704849243,
+      "learning_rate": 4.822733862935702e-05,
+      "loss": 1.6165,
+      "step": 5022
+    },
+    {
+      "epoch": 0.21317976627431126,
+      "grad_norm": 1.0854454040527344,
+      "learning_rate": 4.819614716723775e-05,
+      "loss": 1.6252,
+      "step": 5053
+    },
+    {
+      "epoch": 0.21448761760114754,
+      "grad_norm": 1.0815082788467407,
+      "learning_rate": 4.8164693939750425e-05,
+      "loss": 1.6096,
+      "step": 5084
+    },
+    {
+      "epoch": 0.2157954689279838,
+      "grad_norm": 1.053945541381836,
+      "learning_rate": 4.813297930184042e-05,
+      "loss": 1.6296,
+      "step": 5115
+    },
+    {
+      "epoch": 0.21710332025482007,
+      "grad_norm": 1.06475031375885,
+      "learning_rate": 4.810100361140314e-05,
+      "loss": 1.629,
+      "step": 5146
+    },
+    {
+      "epoch": 0.21841117158165632,
+      "grad_norm": 1.1072969436645508,
+      "learning_rate": 4.8068767229279885e-05,
+      "loss": 1.6244,
+      "step": 5177
+    },
+    {
+      "epoch": 0.2197190229084926,
+      "grad_norm": 1.0536466836929321,
+      "learning_rate": 4.8036270519253854e-05,
+      "loss": 1.6474,
+      "step": 5208
+    },
+    {
+      "epoch": 0.22102687423532885,
+      "grad_norm": 1.1039215326309204,
+      "learning_rate": 4.8003513848046e-05,
+      "loss": 1.6354,
+      "step": 5239
+    },
+    {
+      "epoch": 0.22233472556216513,
+      "grad_norm": 1.0463244915008545,
+      "learning_rate": 4.79704975853109e-05,
+      "loss": 1.6154,
+      "step": 5270
+    },
+    {
+      "epoch": 0.22364257688900138,
+      "grad_norm": 1.0931519269943237,
+      "learning_rate": 4.793722210363262e-05,
+      "loss": 1.6037,
+      "step": 5301
+    },
+    {
+      "epoch": 0.22495042821583766,
+      "grad_norm": 1.0838814973831177,
+      "learning_rate": 4.7903687778520414e-05,
+      "loss": 1.6352,
+      "step": 5332
+    },
+    {
+      "epoch": 0.2262582795426739,
+      "grad_norm": 1.0400842428207397,
+      "learning_rate": 4.7869894988404593e-05,
+      "loss": 1.5924,
+      "step": 5363
+    },
+    {
+      "epoch": 0.2275661308695102,
+      "grad_norm": 1.0707345008850098,
+      "learning_rate": 4.783584411463221e-05,
+      "loss": 1.6211,
+      "step": 5394
+    },
+    {
+      "epoch": 0.22887398219634644,
+      "grad_norm": 1.0422611236572266,
+      "learning_rate": 4.780153554146274e-05,
+      "loss": 1.5969,
+      "step": 5425
+    },
+    {
+      "epoch": 0.23018183352318272,
+      "grad_norm": 1.0401543378829956,
+      "learning_rate": 4.7766969656063766e-05,
+      "loss": 1.5974,
+      "step": 5456
+    },
+    {
+      "epoch": 0.23148968485001897,
+      "grad_norm": 1.0429288148880005,
+      "learning_rate": 4.773214684850662e-05,
+      "loss": 1.6043,
+      "step": 5487
+    },
+    {
+      "epoch": 0.23279753617685525,
+      "grad_norm": 1.098827600479126,
+      "learning_rate": 4.769706751176193e-05,
+      "loss": 1.5984,
+      "step": 5518
+    },
+    {
+      "epoch": 0.2341053875036915,
+      "grad_norm": 1.0090724229812622,
+      "learning_rate": 4.7661732041695264e-05,
+      "loss": 1.6012,
+      "step": 5549
+    },
+    {
+      "epoch": 0.23541323883052778,
+      "grad_norm": 1.0732818841934204,
+      "learning_rate": 4.762614083706258e-05,
+      "loss": 1.5996,
+      "step": 5580
+    },
+    {
+      "epoch": 0.23672109015736403,
+      "grad_norm": 1.082144856452942,
+      "learning_rate": 4.759029429950581e-05,
+      "loss": 1.6127,
+      "step": 5611
+    },
+    {
+      "epoch": 0.2380289414842003,
+      "grad_norm": 1.0642670392990112,
+      "learning_rate": 4.7554192833548235e-05,
+      "loss": 1.5962,
+      "step": 5642
+    },
+    {
+      "epoch": 0.23933679281103656,
+      "grad_norm": 1.1351134777069092,
+      "learning_rate": 4.751783684659e-05,
+      "loss": 1.5983,
+      "step": 5673
+    },
+    {
+      "epoch": 0.24064464413787284,
+      "grad_norm": 1.09076726436615,
+      "learning_rate": 4.748122674890348e-05,
+      "loss": 1.6162,
+      "step": 5704
+    },
+    {
+      "epoch": 0.24195249546470912,
+      "grad_norm": 1.0234689712524414,
+      "learning_rate": 4.7444362953628654e-05,
+      "loss": 1.596,
+      "step": 5735
+    },
+    {
+      "epoch": 0.24326034679154537,
+      "grad_norm": 1.1209464073181152,
+      "learning_rate": 4.7407245876768424e-05,
+      "loss": 1.602,
+      "step": 5766
+    },
+    {
+      "epoch": 0.24456819811838165,
+      "grad_norm": 1.0940710306167603,
+      "learning_rate": 4.736987593718397e-05,
+      "loss": 1.5992,
+      "step": 5797
+    },
+    {
+      "epoch": 0.2458760494452179,
+      "grad_norm": 1.0460273027420044,
+      "learning_rate": 4.733225355658999e-05,
+      "loss": 1.5881,
+      "step": 5828
+    },
+    {
+      "epoch": 0.24718390077205418,
+      "grad_norm": 1.0842856168746948,
+      "learning_rate": 4.7294379159549926e-05,
+      "loss": 1.594,
+      "step": 5859
+    },
+    {
+      "epoch": 0.24849175209889043,
+      "grad_norm": 1.0244876146316528,
+      "learning_rate": 4.725625317347119e-05,
+      "loss": 1.583,
+      "step": 5890
+    },
+    {
+      "epoch": 0.2497996034257267,
+      "grad_norm": 1.0182656049728394,
+      "learning_rate": 4.7217876028600374e-05,
+      "loss": 1.5839,
+      "step": 5921
+    },
+    {
+      "epoch": 0.25110745475256296,
+      "grad_norm": 1.0451878309249878,
+      "learning_rate": 4.717924815801832e-05,
+      "loss": 1.6051,
+      "step": 5952
+    },
+    {
+      "epoch": 0.2524153060793992,
+      "grad_norm": 1.0340505838394165,
+      "learning_rate": 4.714036999763532e-05,
+      "loss": 1.5969,
+      "step": 5983
+    },
+    {
+      "epoch": 0.2537231574062355,
+      "grad_norm": 1.0457735061645508,
+      "learning_rate": 4.7101241986186116e-05,
+      "loss": 1.5971,
+      "step": 6014
+    },
+    {
+      "epoch": 0.2550310087330718,
+      "grad_norm": 1.034166693687439,
+      "learning_rate": 4.7061864565225e-05,
+      "loss": 1.5982,
+      "step": 6045
+    },
+    {
+      "epoch": 0.256338860059908,
+      "grad_norm": 1.0326176881790161,
+      "learning_rate": 4.702223817912081e-05,
+      "loss": 1.5691,
+      "step": 6076
+    },
+    {
+      "epoch": 0.2576467113867443,
+      "grad_norm": 1.0339311361312866,
+      "learning_rate": 4.698236327505195e-05,
+      "loss": 1.5726,
+      "step": 6107
+    },
+    {
+      "epoch": 0.2589545627135806,
+      "grad_norm": 1.022299885749817,
+      "learning_rate": 4.694224030300127e-05,
+      "loss": 1.5935,
+      "step": 6138
+    },
+    {
+      "epoch": 0.26026241404041683,
+      "grad_norm": 1.009255051612854,
+      "learning_rate": 4.690186971575107e-05,
+      "loss": 1.574,
+      "step": 6169
+    },
+    {
+      "epoch": 0.2615702653672531,
+      "grad_norm": 1.0181437730789185,
+      "learning_rate": 4.6861251968877916e-05,
+      "loss": 1.57,
+      "step": 6200
+    },
+    {
+      "epoch": 0.26287811669408934,
+      "grad_norm": 1.0302594900131226,
+      "learning_rate": 4.68203875207476e-05,
+      "loss": 1.5785,
+      "step": 6231
+    },
+    {
+      "epoch": 0.26418596802092564,
+      "grad_norm": 1.006404161453247,
+      "learning_rate": 4.677927683250983e-05,
+      "loss": 1.5798,
+      "step": 6262
+    },
+    {
+      "epoch": 0.2654938193477619,
+      "grad_norm": 0.993584394454956,
+      "learning_rate": 4.6737920368093156e-05,
+      "loss": 1.5558,
+      "step": 6293
+    },
+    {
+      "epoch": 0.26680167067459815,
+      "grad_norm": 0.9635722637176514,
+      "learning_rate": 4.669631859419965e-05,
+      "loss": 1.5716,
+      "step": 6324
+    },
+    {
+      "epoch": 0.2681095220014344,
+      "grad_norm": 0.9815465211868286,
+      "learning_rate": 4.6654471980299676e-05,
+      "loss": 1.5472,
+      "step": 6355
+    },
+    {
+      "epoch": 0.2694173733282707,
+      "grad_norm": 0.9921912550926208,
+      "learning_rate": 4.661238099862658e-05,
+      "loss": 1.5786,
+      "step": 6386
+    },
+    {
+      "epoch": 0.27072522465510696,
+      "grad_norm": 1.0193076133728027,
+      "learning_rate": 4.657004612417138e-05,
+      "loss": 1.5672,
+      "step": 6417
+    },
+    {
+      "epoch": 0.2720330759819432,
+      "grad_norm": 0.9979498982429504,
+      "learning_rate": 4.6527467834677374e-05,
+      "loss": 1.5549,
+      "step": 6448
+    },
+    {
+      "epoch": 0.27334092730877946,
+      "grad_norm": 1.0342402458190918,
+      "learning_rate": 4.648464661063478e-05,
+      "loss": 1.5808,
+      "step": 6479
+    },
+    {
+      "epoch": 0.27464877863561576,
+      "grad_norm": 0.9821639060974121,
+      "learning_rate": 4.6441582935275264e-05,
+      "loss": 1.5642,
+      "step": 6510
+    },
+    {
+      "epoch": 0.275956629962452,
+      "grad_norm": 1.002773404121399,
+      "learning_rate": 4.6398277294566586e-05,
+      "loss": 1.5646,
+      "step": 6541
+    },
+    {
+      "epoch": 0.27726448128928827,
+      "grad_norm": 1.0241411924362183,
+      "learning_rate": 4.6354730177207e-05,
+      "loss": 1.5744,
+      "step": 6572
+    },
+    {
+      "epoch": 0.2785723326161245,
+      "grad_norm": 1.0101004838943481,
+      "learning_rate": 4.6310942074619787e-05,
+      "loss": 1.5905,
+      "step": 6603
+    },
+    {
+      "epoch": 0.2798801839429608,
+      "grad_norm": 1.0355374813079834,
+      "learning_rate": 4.626691348094777e-05,
+      "loss": 1.5713,
+      "step": 6634
+    },
+    {
+      "epoch": 0.2811880352697971,
+      "grad_norm": 1.0100233554840088,
+      "learning_rate": 4.622264489304762e-05,
+      "loss": 1.5491,
+      "step": 6665
+    },
+    {
+      "epoch": 0.2824958865966333,
+      "grad_norm": 1.0172356367111206,
+      "learning_rate": 4.617813681048434e-05,
+      "loss": 1.562,
+      "step": 6696
+    },
+    {
+      "epoch": 0.2838037379234696,
+      "grad_norm": 0.994799017906189,
+      "learning_rate": 4.61333897355256e-05,
+      "loss": 1.5526,
+      "step": 6727
+    },
+    {
+      "epoch": 0.2851115892503059,
+      "grad_norm": 1.1320250034332275,
+      "learning_rate": 4.608840417313604e-05,
+      "loss": 1.5616,
+      "step": 6758
+    },
+    {
+      "epoch": 0.28641944057714214,
+      "grad_norm": 1.013725996017456,
+      "learning_rate": 4.6043180630971646e-05,
+      "loss": 1.5345,
+      "step": 6789
+    },
+    {
+      "epoch": 0.2877272919039784,
+      "grad_norm": 1.045462727546692,
+      "learning_rate": 4.599771961937391e-05,
+      "loss": 1.56,
+      "step": 6820
+    },
+    {
+      "epoch": 0.28903514323081464,
+      "grad_norm": 1.0075098276138306,
+      "learning_rate": 4.5952021651364204e-05,
+      "loss": 1.5825,
+      "step": 6851
+    },
+    {
+      "epoch": 0.29034299455765095,
+      "grad_norm": 0.9952128529548645,
+      "learning_rate": 4.590608724263786e-05,
+      "loss": 1.5581,
+      "step": 6882
+    },
+    {
+      "epoch": 0.2916508458844872,
+      "grad_norm": 0.9492574334144592,
+      "learning_rate": 4.585991691155845e-05,
+      "loss": 1.554,
+      "step": 6913
+    },
+    {
+      "epoch": 0.29295869721132345,
+      "grad_norm": 0.9850384593009949,
+      "learning_rate": 4.581351117915188e-05,
+      "loss": 1.5614,
+      "step": 6944
+    },
+    {
+      "epoch": 0.2942665485381597,
+      "grad_norm": 0.9840113520622253,
+      "learning_rate": 4.5766870569100534e-05,
+      "loss": 1.5631,
+      "step": 6975
+    },
+    {
+      "epoch": 0.295574399864996,
+      "grad_norm": 0.9830542802810669,
+      "learning_rate": 4.571999560773736e-05,
+      "loss": 1.5597,
+      "step": 7006
+    },
+    {
+      "epoch": 0.29688225119183226,
+      "grad_norm": 0.9737412929534912,
+      "learning_rate": 4.5672886824039915e-05,
+      "loss": 1.5412,
+      "step": 7037
+    },
+    {
+      "epoch": 0.2981901025186685,
+      "grad_norm": 1.0272278785705566,
+      "learning_rate": 4.5625544749624435e-05,
+      "loss": 1.5724,
+      "step": 7068
+    },
+    {
+      "epoch": 0.29949795384550476,
+      "grad_norm": 0.973682165145874,
+      "learning_rate": 4.5577969918739794e-05,
+      "loss": 1.5739,
+      "step": 7099
+    },
+    {
+      "epoch": 0.30080580517234107,
+      "grad_norm": 0.9709253907203674,
+      "learning_rate": 4.5530162868261486e-05,
+      "loss": 1.5666,
+      "step": 7130
+    },
+    {
+      "epoch": 0.3021136564991773,
+      "grad_norm": 0.9426018595695496,
+      "learning_rate": 4.548212413768558e-05,
+      "loss": 1.5542,
+      "step": 7161
+    },
+    {
+      "epoch": 0.30342150782601357,
+      "grad_norm": 1.026181697845459,
+      "learning_rate": 4.543385426912261e-05,
+      "loss": 1.5235,
+      "step": 7192
+    },
+    {
+      "epoch": 0.3047293591528499,
+      "grad_norm": 0.9783868193626404,
+      "learning_rate": 4.53853538072915e-05,
+      "loss": 1.5591,
+      "step": 7223
+    },
+    {
+      "epoch": 0.30603721047968613,
+      "grad_norm": 0.9816028475761414,
+      "learning_rate": 4.533662329951336e-05,
+      "loss": 1.5484,
+      "step": 7254
+    },
+    {
+      "epoch": 0.3073450618065224,
+      "grad_norm": 0.9516949653625488,
+      "learning_rate": 4.528766329570536e-05,
+      "loss": 1.5251,
+      "step": 7285
+    },
+    {
+      "epoch": 0.30865291313335863,
+      "grad_norm": 0.9601557850837708,
+      "learning_rate": 4.523847434837447e-05,
+      "loss": 1.5668,
+      "step": 7316
+    },
+    {
+      "epoch": 0.30996076446019494,
+      "grad_norm": 0.9607630372047424,
+      "learning_rate": 4.518905701261128e-05,
+      "loss": 1.5576,
+      "step": 7347
+    },
+    {
+      "epoch": 0.3112686157870312,
+      "grad_norm": 0.9606896638870239,
+      "learning_rate": 4.5139411846083715e-05,
+      "loss": 1.5441,
+      "step": 7378
+    },
+    {
+      "epoch": 0.31257646711386744,
+      "grad_norm": 1.0111651420593262,
+      "learning_rate": 4.508953940903073e-05,
+      "loss": 1.5586,
+      "step": 7409
+    },
+    {
+      "epoch": 0.3138843184407037,
+      "grad_norm": 0.9388339519500732,
+      "learning_rate": 4.5039440264255994e-05,
+      "loss": 1.5472,
+      "step": 7440
+    },
+    {
+      "epoch": 0.31519216976754,
+      "grad_norm": 0.9507540464401245,
+      "learning_rate": 4.498911497712155e-05,
+      "loss": 1.5579,
+      "step": 7471
+    },
+    {
+      "epoch": 0.31650002109437625,
+      "grad_norm": 0.9572455286979675,
+      "learning_rate": 4.493856411554142e-05,
+      "loss": 1.5433,
+      "step": 7502
+    },
+    {
+      "epoch": 0.3178078724212125,
+      "grad_norm": 0.9485601782798767,
+      "learning_rate": 4.4887788249975206e-05,
+      "loss": 1.5513,
+      "step": 7533
+    },
+    {
+      "epoch": 0.31911572374804875,
+      "grad_norm": 0.9995166063308716,
+      "learning_rate": 4.4836787953421656e-05,
+      "loss": 1.5289,
+      "step": 7564
+    },
+    {
+      "epoch": 0.32042357507488506,
+      "grad_norm": 1.1004894971847534,
+      "learning_rate": 4.478556380141218e-05,
+      "loss": 1.5306,
+      "step": 7595
+    },
+    {
+      "epoch": 0.3217314264017213,
+      "grad_norm": 0.9642030000686646,
+      "learning_rate": 4.4734116372004375e-05,
+      "loss": 1.5497,
+      "step": 7626
+    },
+    {
+      "epoch": 0.32303927772855756,
+      "grad_norm": 0.9486343860626221,
+      "learning_rate": 4.4682446245775477e-05,
+      "loss": 1.5458,
+      "step": 7657
+    },
+    {
+      "epoch": 0.3243471290553938,
+      "grad_norm": 0.942319929599762,
+      "learning_rate": 4.463055400581586e-05,
+      "loss": 1.5306,
+      "step": 7688
+    },
+    {
+      "epoch": 0.3256549803822301,
+      "grad_norm": 0.9433887004852295,
+      "learning_rate": 4.4578440237722374e-05,
+      "loss": 1.5394,
+      "step": 7719
+    },
+    {
+      "epoch": 0.32696283170906637,
+      "grad_norm": 0.9954056739807129,
+      "learning_rate": 4.452610552959183e-05,
+      "loss": 1.551,
+      "step": 7750
+    },
+    {
+      "epoch": 0.3282706830359026,
+      "grad_norm": 0.9406622052192688,
+      "learning_rate": 4.447355047201428e-05,
+      "loss": 1.5481,
+      "step": 7781
+    },
+    {
+      "epoch": 0.3295785343627389,
+      "grad_norm": 0.9743403792381287,
+      "learning_rate": 4.4420775658066414e-05,
+      "loss": 1.533,
+      "step": 7812
+    },
+    {
+      "epoch": 0.3308863856895752,
+      "grad_norm": 0.9561812877655029,
+      "learning_rate": 4.436778168330484e-05,
+      "loss": 1.5615,
+      "step": 7843
+    },
+    {
+      "epoch": 0.33219423701641143,
+      "grad_norm": 0.9623595476150513,
+      "learning_rate": 4.4314569145759353e-05,
+      "loss": 1.5463,
+      "step": 7874
+    },
+    {
+      "epoch": 0.3335020883432477,
+      "grad_norm": 0.9475456476211548,
+      "learning_rate": 4.42611386459262e-05,
+      "loss": 1.558,
+      "step": 7905
+    },
+    {
+      "epoch": 0.33480993967008393,
+      "grad_norm": 0.9283867478370667,
+      "learning_rate": 4.420749078676133e-05,
+      "loss": 1.5237,
+      "step": 7936
+    },
+    {
+      "epoch": 0.33611779099692024,
+      "grad_norm": 0.9494192004203796,
+      "learning_rate": 4.4153626173673516e-05,
+      "loss": 1.5315,
+      "step": 7967
+    },
+    {
+      "epoch": 0.3374256423237565,
+      "grad_norm": 0.9378790855407715,
+      "learning_rate": 4.409954541451762e-05,
+      "loss": 1.5378,
+      "step": 7998
+    },
+    {
+      "epoch": 0.33873349365059274,
+      "grad_norm": 0.9318397045135498,
+      "learning_rate": 4.404524911958764e-05,
+      "loss": 1.5199,
+      "step": 8029
+    },
+    {
+      "epoch": 0.340041344977429,
+      "grad_norm": 0.9440187215805054,
+      "learning_rate": 4.399073790160989e-05,
+      "loss": 1.5313,
+      "step": 8060
+    },
+    {
+      "epoch": 0.3413491963042653,
+      "grad_norm": 0.9643428921699524,
+      "learning_rate": 4.393601237573607e-05,
+      "loss": 1.5267,
+      "step": 8091
+    },
+    {
+      "epoch": 0.34265704763110155,
+      "grad_norm": 0.9626632928848267,
+      "learning_rate": 4.388107315953628e-05,
+      "loss": 1.5312,
+      "step": 8122
+    },
+    {
+      "epoch": 0.3439648989579378,
+      "grad_norm": 0.9867373704910278,
+      "learning_rate": 4.382592087299212e-05,
+      "loss": 1.5162,
+      "step": 8153
+    },
+    {
+      "epoch": 0.34527275028477405,
+      "grad_norm": 0.9584757685661316,
+      "learning_rate": 4.377055613848964e-05,
+      "loss": 1.5201,
+      "step": 8184
+    },
+    {
+      "epoch": 0.34658060161161036,
+      "grad_norm": 0.9587807655334473,
+      "learning_rate": 4.3714979580812355e-05,
+      "loss": 1.55,
+      "step": 8215
+    },
+    {
+      "epoch": 0.3478884529384466,
+      "grad_norm": 0.948785662651062,
+      "learning_rate": 4.365919182713416e-05,
+      "loss": 1.5392,
+      "step": 8246
+    },
+    {
+      "epoch": 0.34919630426528286,
+      "grad_norm": 0.9717795252799988,
+      "learning_rate": 4.360319350701226e-05,
+      "loss": 1.5112,
+      "step": 8277
+    },
+    {
+      "epoch": 0.3505041555921191,
+      "grad_norm": 0.9338726997375488,
+      "learning_rate": 4.3546985252380115e-05,
+      "loss": 1.5371,
+      "step": 8308
+    },
+    {
+      "epoch": 0.3518120069189554,
+      "grad_norm": 0.9878547191619873,
+      "learning_rate": 4.349056769754021e-05,
+      "loss": 1.5349,
+      "step": 8339
+    },
+    {
+      "epoch": 0.3531198582457917,
+      "grad_norm": 1.0211338996887207,
+      "learning_rate": 4.3433941479156994e-05,
+      "loss": 1.5234,
+      "step": 8370
+    },
+    {
+      "epoch": 0.3544277095726279,
+      "grad_norm": 0.944474458694458,
+      "learning_rate": 4.3377107236249647e-05,
+      "loss": 1.5306,
+      "step": 8401
+    },
+    {
+      "epoch": 0.3557355608994642,
+      "grad_norm": 0.9218102097511292,
+      "learning_rate": 4.332006561018488e-05,
+      "loss": 1.5113,
+      "step": 8432
+    },
+    {
+      "epoch": 0.3570434122263005,
+      "grad_norm": 0.9429653286933899,
+      "learning_rate": 4.3262817244669683e-05,
+      "loss": 1.5095,
+      "step": 8463
+    },
+    {
+      "epoch": 0.35835126355313673,
+      "grad_norm": 0.8979545831680298,
+      "learning_rate": 4.3205362785744083e-05,
+      "loss": 1.522,
+      "step": 8494
+    },
+    {
+      "epoch": 0.359659114879973,
+      "grad_norm": 0.9040619134902954,
+      "learning_rate": 4.314770288177384e-05,
+      "loss": 1.5197,
+      "step": 8525
+    },
+    {
+      "epoch": 0.3609669662068093,
+      "grad_norm": 0.9038030505180359,
+      "learning_rate": 4.308983818344313e-05,
+      "loss": 1.5218,
+      "step": 8556
+    },
+    {
+      "epoch": 0.36227481753364554,
+      "grad_norm": 0.9493038654327393,
+      "learning_rate": 4.3031769343747206e-05,
+      "loss": 1.5306,
+      "step": 8587
+    },
+    {
+      "epoch": 0.3635826688604818,
+      "grad_norm": 0.9084991812705994,
+      "learning_rate": 4.297349701798505e-05,
+      "loss": 1.5146,
+      "step": 8618
+    },
+    {
+      "epoch": 0.36489052018731805,
+      "grad_norm": 0.9597145915031433,
+      "learning_rate": 4.2915021863751916e-05,
+      "loss": 1.5202,
+      "step": 8649
+    },
+    {
+      "epoch": 0.36619837151415435,
+      "grad_norm": 0.9139339923858643,
+      "learning_rate": 4.285634454093198e-05,
+      "loss": 1.5082,
+      "step": 8680
+    },
+    {
+      "epoch": 0.3675062228409906,
+      "grad_norm": 0.955664336681366,
+      "learning_rate": 4.279746571169086e-05,
+      "loss": 1.5073,
+      "step": 8711
+    },
+    {
+      "epoch": 0.36881407416782686,
+      "grad_norm": 0.975068986415863,
+      "learning_rate": 4.2738386040468136e-05,
+      "loss": 1.5086,
+      "step": 8742
+    },
+    {
+      "epoch": 0.3701219254946631,
+      "grad_norm": 0.9280393719673157,
+      "learning_rate": 4.2679106193969866e-05,
+      "loss": 1.5342,
+      "step": 8773
+    },
+    {
+      "epoch": 0.3714297768214994,
+      "grad_norm": 0.9098469614982605,
+      "learning_rate": 4.261962684116106e-05,
+      "loss": 1.5305,
+      "step": 8804
+    },
+    {
+      "epoch": 0.37273762814833566,
+      "grad_norm": 0.9359835386276245,
+      "learning_rate": 4.2559948653258145e-05,
+      "loss": 1.5172,
+      "step": 8835
+    },
+    {
+      "epoch": 0.3740454794751719,
+      "grad_norm": 0.9431541562080383,
+      "learning_rate": 4.250007230372134e-05,
+      "loss": 1.5128,
+      "step": 8866
+    },
+    {
+      "epoch": 0.37535333080200817,
+      "grad_norm": 0.8999470472335815,
+      "learning_rate": 4.2439998468247126e-05,
+      "loss": 1.5025,
+      "step": 8897
+    },
+    {
+      "epoch": 0.3766611821288445,
+      "grad_norm": 0.9414424300193787,
+      "learning_rate": 4.2379727824760566e-05,
+      "loss": 1.5135,
+      "step": 8928
+    },
+    {
+      "epoch": 0.3779690334556807,
+      "grad_norm": 0.9347614049911499,
+      "learning_rate": 4.231926105340768e-05,
+      "loss": 1.5252,
+      "step": 8959
+    },
+    {
+      "epoch": 0.379276884782517,
+      "grad_norm": 0.9166226983070374,
+      "learning_rate": 4.225859883654776e-05,
+      "loss": 1.519,
+      "step": 8990
+    },
+    {
+      "epoch": 0.3805847361093532,
+      "grad_norm": 0.9614241719245911,
+      "learning_rate": 4.219774185874569e-05,
+      "loss": 1.494,
+      "step": 9021
+    },
+    {
+      "epoch": 0.38189258743618953,
+      "grad_norm": 0.9002947211265564,
+      "learning_rate": 4.213669080676418e-05,
+      "loss": 1.5093,
+      "step": 9052
+    },
+    {
+      "epoch": 0.3832004387630258,
+      "grad_norm": 0.8749356269836426,
+      "learning_rate": 4.2075446369556056e-05,
+      "loss": 1.512,
+      "step": 9083
+    },
+    {
+      "epoch": 0.38450829008986204,
+      "grad_norm": 0.954454243183136,
+      "learning_rate": 4.201400923825648e-05,
+      "loss": 1.4987,
+      "step": 9114
+    },
+    {
+      "epoch": 0.3858161414166983,
+      "grad_norm": 0.9184893369674683,
+      "learning_rate": 4.195238010617511e-05,
+      "loss": 1.5195,
+      "step": 9145
+    },
+    {
+      "epoch": 0.3871239927435346,
+      "grad_norm": 0.9145151376724243,
+      "learning_rate": 4.1890559668788344e-05,
+      "loss": 1.5149,
+      "step": 9176
+    },
+    {
+      "epoch": 0.38843184407037085,
+      "grad_norm": 0.9118244051933289,
+      "learning_rate": 4.1828548623731405e-05,
+      "loss": 1.5179,
+      "step": 9207
+    },
+    {
+      "epoch": 0.3897396953972071,
+      "grad_norm": 0.918662428855896,
+      "learning_rate": 4.1766347670790506e-05,
+      "loss": 1.5023,
+      "step": 9238
+    },
+    {
+      "epoch": 0.39104754672404335,
+      "grad_norm": 0.9427615404129028,
+      "learning_rate": 4.170395751189495e-05,
+      "loss": 1.5093,
+      "step": 9269
+    },
+    {
+      "epoch": 0.39235539805087966,
+      "grad_norm": 0.8825695514678955,
+      "learning_rate": 4.164137885110921e-05,
+      "loss": 1.5056,
+      "step": 9300
+    },
+    {
+      "epoch": 0.3936632493777159,
+      "grad_norm": 0.9850104451179504,
+      "learning_rate": 4.157861239462495e-05,
+      "loss": 1.5308,
+      "step": 9331
+    },
+    {
+      "epoch": 0.39497110070455216,
+      "grad_norm": 0.9645696878433228,
+      "learning_rate": 4.1515658850753114e-05,
+      "loss": 1.4933,
+      "step": 9362
+    },
+    {
+      "epoch": 0.3962789520313884,
+      "grad_norm": 0.9052213430404663,
+      "learning_rate": 4.145251892991588e-05,
+      "loss": 1.5072,
+      "step": 9393
+    },
+    {
+      "epoch": 0.3975868033582247,
+      "grad_norm": 0.9212966561317444,
+      "learning_rate": 4.138919334463868e-05,
+      "loss": 1.5041,
+      "step": 9424
+    },
+    {
+      "epoch": 0.39889465468506097,
+      "grad_norm": 0.8963611721992493,
+      "learning_rate": 4.1325682809542124e-05,
+      "loss": 1.5121,
+      "step": 9455
+    },
+    {
+      "epoch": 0.4002025060118972,
+      "grad_norm": 0.9025225639343262,
+      "learning_rate": 4.126198804133398e-05,
+      "loss": 1.5018,
+      "step": 9486
+    },
+    {
+      "epoch": 0.40151035733873347,
+      "grad_norm": 0.9104238748550415,
+      "learning_rate": 4.1198109758801055e-05,
+      "loss": 1.5107,
+      "step": 9517
+    },
+    {
+      "epoch": 0.4028182086655698,
+      "grad_norm": 0.9045152068138123,
+      "learning_rate": 4.113404868280107e-05,
+      "loss": 1.4841,
+      "step": 9548
+    },
+    {
+      "epoch": 0.40412605999240603,
+      "grad_norm": 0.950362503528595,
+      "learning_rate": 4.106980553625457e-05,
+      "loss": 1.5274,
+      "step": 9579
+    },
+    {
+      "epoch": 0.4054339113192423,
+      "grad_norm": 0.8988200426101685,
+      "learning_rate": 4.100538104413674e-05,
+      "loss": 1.5144,
+      "step": 9610
+    },
+    {
+      "epoch": 0.40674176264607853,
+      "grad_norm": 0.9193787574768066,
+      "learning_rate": 4.09407759334692e-05,
+      "loss": 1.5083,
+      "step": 9641
+    },
+    {
+      "epoch": 0.40804961397291484,
+      "grad_norm": 0.885677695274353,
+      "learning_rate": 4.087599093331186e-05,
+      "loss": 1.4969,
+      "step": 9672
+    },
+    {
+      "epoch": 0.4093574652997511,
+      "grad_norm": 0.9060222506523132,
+      "learning_rate": 4.081102677475462e-05,
+      "loss": 1.4821,
+      "step": 9703
+    },
+    {
+      "epoch": 0.41066531662658734,
+      "grad_norm": 0.9060747623443604,
+      "learning_rate": 4.0745884190909194e-05,
+      "loss": 1.4851,
+      "step": 9734
+    },
+    {
+      "epoch": 0.4119731679534236,
+      "grad_norm": 0.8934387564659119,
+      "learning_rate": 4.0680563916900796e-05,
+      "loss": 1.4874,
+      "step": 9765
+    },
+    {
+      "epoch": 0.4132810192802599,
+      "grad_norm": 0.8983092904090881,
+      "learning_rate": 4.0615066689859815e-05,
+      "loss": 1.503,
+      "step": 9796
+    },
+    {
+      "epoch": 0.41458887060709615,
+      "grad_norm": 0.914784848690033,
+      "learning_rate": 4.0549393248913584e-05,
+      "loss": 1.4986,
+      "step": 9827
+    },
+    {
+      "epoch": 0.4158967219339324,
+      "grad_norm": 0.9157377481460571,
+      "learning_rate": 4.048354433517794e-05,
+      "loss": 1.5072,
+      "step": 9858
+    },
+    {
+      "epoch": 0.41720457326076865,
+      "grad_norm": 0.8943291306495667,
+      "learning_rate": 4.0417520691748916e-05,
+      "loss": 1.4853,
+      "step": 9889
+    },
+    {
+      "epoch": 0.41851242458760496,
+      "grad_norm": 0.9054378271102905,
+      "learning_rate": 4.035132306369438e-05,
+      "loss": 1.5004,
+      "step": 9920
+    },
+    {
+      "epoch": 0.4198202759144412,
+      "grad_norm": 0.9269044399261475,
+      "learning_rate": 4.028495219804555e-05,
+      "loss": 1.4741,
+      "step": 9951
+    },
+    {
+      "epoch": 0.42112812724127746,
+      "grad_norm": 0.8953903913497925,
+      "learning_rate": 4.021840884378864e-05,
+      "loss": 1.4843,
+      "step": 9982
+    },
+    {
+      "epoch": 0.42243597856811377,
+      "grad_norm": 0.8900305032730103,
+      "learning_rate": 4.015169375185633e-05,
+      "loss": 1.5267,
+      "step": 10013
+    },
+    {
+      "epoch": 0.42374382989495,
+      "grad_norm": 0.9487763047218323,
+      "learning_rate": 4.0084807675119396e-05,
+      "loss": 1.5108,
+      "step": 10044
+    },
+    {
+      "epoch": 0.42505168122178627,
+      "grad_norm": 0.9137413501739502,
+      "learning_rate": 4.0017751368378106e-05,
+      "loss": 1.4882,
+      "step": 10075
+    },
+    {
+      "epoch": 0.4263595325486225,
+      "grad_norm": 0.9609214067459106,
+      "learning_rate": 3.995052558835377e-05,
+      "loss": 1.4845,
+      "step": 10106
+    },
+    {
+      "epoch": 0.42766738387545883,
+      "grad_norm": 0.8875072002410889,
+      "learning_rate": 3.988313109368017e-05,
+      "loss": 1.5042,
+      "step": 10137
+    },
+    {
+      "epoch": 0.4289752352022951,
+      "grad_norm": 0.8940466642379761,
+      "learning_rate": 3.981556864489504e-05,
+      "loss": 1.4848,
+      "step": 10168
+    },
+    {
+      "epoch": 0.43028308652913133,
+      "grad_norm": 0.9151347279548645,
+      "learning_rate": 3.974783900443142e-05,
+      "loss": 1.5091,
+      "step": 10199
+    },
+    {
+      "epoch": 0.4315909378559676,
+      "grad_norm": 0.8956405520439148,
+      "learning_rate": 3.9679942936609095e-05,
+      "loss": 1.4925,
+      "step": 10230
+    },
+    {
+      "epoch": 0.4328987891828039,
+      "grad_norm": 0.8801243305206299,
+      "learning_rate": 3.961188120762596e-05,
+      "loss": 1.4992,
+      "step": 10261
+    },
+    {
+      "epoch": 0.43420664050964014,
+      "grad_norm": 0.9045059084892273,
+      "learning_rate": 3.954365458554938e-05,
+      "loss": 1.4873,
+      "step": 10292
+    },
+    {
+      "epoch": 0.4355144918364764,
+      "grad_norm": 0.8852213025093079,
+      "learning_rate": 3.947526384030751e-05,
+      "loss": 1.4907,
+      "step": 10323
+    },
+    {
+      "epoch": 0.43682234316331264,
+      "grad_norm": 0.9119607210159302,
+      "learning_rate": 3.9406709743680624e-05,
+      "loss": 1.4879,
+      "step": 10354
+    },
+    {
+      "epoch": 0.43813019449014895,
+      "grad_norm": 0.8808435201644897,
+      "learning_rate": 3.9337993069292366e-05,
+      "loss": 1.473,
+      "step": 10385
+    },
+    {
+      "epoch": 0.4394380458169852,
+      "grad_norm": 0.8821302056312561,
+      "learning_rate": 3.926911459260109e-05,
+      "loss": 1.4883,
+      "step": 10416
+    },
+    {
+      "epoch": 0.44074589714382145,
+      "grad_norm": 0.8727222084999084,
+      "learning_rate": 3.920007509089102e-05,
+      "loss": 1.4802,
+      "step": 10447
+    },
+    {
+      "epoch": 0.4420537484706577,
+      "grad_norm": 0.8907620310783386,
+      "learning_rate": 3.913087534326357e-05,
+      "loss": 1.4947,
+      "step": 10478
+    },
+    {
+      "epoch": 0.443361599797494,
+      "grad_norm": 0.9233911633491516,
+      "learning_rate": 3.9061516130628475e-05,
+      "loss": 1.4844,
+      "step": 10509
+    },
+    {
+      "epoch": 0.44466945112433026,
+      "grad_norm": 0.8893357515335083,
+      "learning_rate": 3.8991998235695025e-05,
+      "loss": 1.4696,
+      "step": 10540
+    },
+    {
+      "epoch": 0.4459773024511665,
+      "grad_norm": 0.8262650966644287,
+      "learning_rate": 3.8922322442963224e-05,
+      "loss": 1.4867,
+      "step": 10571
+    },
+    {
+      "epoch": 0.44728515377800276,
+      "grad_norm": 0.8931017518043518,
+      "learning_rate": 3.885248953871491e-05,
+      "loss": 1.4655,
+      "step": 10602
+    },
+    {
+      "epoch": 0.44859300510483907,
+      "grad_norm": 0.8849929571151733,
+      "learning_rate": 3.8782500311004915e-05,
+      "loss": 1.4905,
+      "step": 10633
+    },
+    {
+      "epoch": 0.4499008564316753,
+      "grad_norm": 0.8966437578201294,
+      "learning_rate": 3.871235554965218e-05,
+      "loss": 1.4861,
+      "step": 10664
+    },
+    {
+      "epoch": 0.4512087077585116,
+      "grad_norm": 0.931607723236084,
+      "learning_rate": 3.864205604623078e-05,
+      "loss": 1.4816,
+      "step": 10695
+    },
+    {
+      "epoch": 0.4525165590853478,
+      "grad_norm": 0.9525107741355896,
+      "learning_rate": 3.857160259406107e-05,
+      "loss": 1.4758,
+      "step": 10726
+    },
+    {
+      "epoch": 0.45382441041218413,
+      "grad_norm": 0.9055147767066956,
+      "learning_rate": 3.8500995988200674e-05,
+      "loss": 1.4869,
+      "step": 10757
+    },
+    {
+      "epoch": 0.4551322617390204,
+      "grad_norm": 0.8673259019851685,
+      "learning_rate": 3.843023702543556e-05,
+      "loss": 1.482,
+      "step": 10788
+    },
+    {
+      "epoch": 0.45644011306585663,
+      "grad_norm": 0.845866858959198,
+      "learning_rate": 3.8359326504270984e-05,
+      "loss": 1.4733,
+      "step": 10819
+    },
+    {
+      "epoch": 0.4577479643926929,
+      "grad_norm": 0.8884342908859253,
+      "learning_rate": 3.828826522492255e-05,
+      "loss": 1.4711,
+      "step": 10850
+    },
+    {
+      "epoch": 0.4590558157195292,
+      "grad_norm": 0.8943782448768616,
+      "learning_rate": 3.821705398930713e-05,
+      "loss": 1.4538,
+      "step": 10881
+    },
+    {
+      "epoch": 0.46036366704636544,
+      "grad_norm": 0.8772262930870056,
+      "learning_rate": 3.814569360103385e-05,
+      "loss": 1.4771,
+      "step": 10912
+    },
+    {
+      "epoch": 0.4616715183732017,
+      "grad_norm": 0.9197453856468201,
+      "learning_rate": 3.807418486539499e-05,
+      "loss": 1.4648,
+      "step": 10943
+    },
+    {
+      "epoch": 0.46297936970003795,
+      "grad_norm": 0.8835433125495911,
+      "learning_rate": 3.80025285893569e-05,
+      "loss": 1.4677,
+      "step": 10974
+    },
+    {
+      "epoch": 0.46428722102687425,
+      "grad_norm": 0.955093264579773,
+      "learning_rate": 3.793072558155093e-05,
+      "loss": 1.4821,
+      "step": 11005
+    },
+    {
+      "epoch": 0.4655950723537105,
+      "grad_norm": 0.9170013070106506,
+      "learning_rate": 3.785877665226426e-05,
+      "loss": 1.481,
+      "step": 11036
+    },
+    {
+      "epoch": 0.46690292368054676,
+      "grad_norm": 0.8826711177825928,
+      "learning_rate": 3.778668261343079e-05,
+      "loss": 1.4713,
+      "step": 11067
+    },
+    {
+      "epoch": 0.468210775007383,
+      "grad_norm": 0.9213606715202332,
+      "learning_rate": 3.771444427862192e-05,
+      "loss": 1.4898,
+      "step": 11098
+    },
+    {
+      "epoch": 0.4695186263342193,
+      "grad_norm": 1.0346989631652832,
+      "learning_rate": 3.7642062463037465e-05,
+      "loss": 1.4768,
+      "step": 11129
+    },
+    {
+      "epoch": 0.47082647766105556,
+      "grad_norm": 0.8965749740600586,
+      "learning_rate": 3.7569537983496373e-05,
+      "loss": 1.4714,
+      "step": 11160
+    },
+    {
+      "epoch": 0.4721343289878918,
+      "grad_norm": 0.88069748878479,
+      "learning_rate": 3.749687165842753e-05,
+      "loss": 1.4938,
+      "step": 11191
+    },
+    {
+      "epoch": 0.47344218031472807,
+      "grad_norm": 0.8329574465751648,
+      "learning_rate": 3.7424064307860536e-05,
+      "loss": 1.4581,
+      "step": 11222
+    },
+    {
+      "epoch": 0.4747500316415644,
+      "grad_norm": 0.8511537313461304,
+      "learning_rate": 3.735111675341645e-05,
+      "loss": 1.4688,
+      "step": 11253
+    },
+    {
+      "epoch": 0.4760578829684006,
+      "grad_norm": 0.8722901344299316,
+      "learning_rate": 3.7278029818298524e-05,
+      "loss": 1.5016,
+      "step": 11284
+    },
+    {
+      "epoch": 0.4773657342952369,
+      "grad_norm": 0.8820895552635193,
+      "learning_rate": 3.720480432728287e-05,
+      "loss": 1.4775,
+      "step": 11315
+    },
+    {
+      "epoch": 0.47867358562207313,
+      "grad_norm": 0.8825634717941284,
+      "learning_rate": 3.71314411067092e-05,
+      "loss": 1.4997,
+      "step": 11346
+    },
+    {
+      "epoch": 0.47998143694890943,
+      "grad_norm": 0.8426871299743652,
+      "learning_rate": 3.70579409844715e-05,
+      "loss": 1.4549,
+      "step": 11377
+    },
+    {
+      "epoch": 0.4812892882757457,
+      "grad_norm": 0.8519338965415955,
+      "learning_rate": 3.698430479000865e-05,
+      "loss": 1.4788,
+      "step": 11408
+    },
+    {
+      "epoch": 0.48259713960258194,
+      "grad_norm": 0.8908571600914001,
+      "learning_rate": 3.691053335429509e-05,
+      "loss": 1.4775,
+      "step": 11439
+    },
+    {
+      "epoch": 0.48390499092941824,
+      "grad_norm": 0.8275105357170105,
+      "learning_rate": 3.683662750983147e-05,
+      "loss": 1.4569,
+      "step": 11470
+    },
+    {
+      "epoch": 0.4852128422562545,
+      "grad_norm": 0.8812130689620972,
+      "learning_rate": 3.676258809063518e-05,
+      "loss": 1.4706,
+      "step": 11501
+    },
+    {
+      "epoch": 0.48652069358309075,
+      "grad_norm": 0.9266872406005859,
+      "learning_rate": 3.6688415932231004e-05,
+      "loss": 1.4699,
+      "step": 11532
+    },
+    {
+      "epoch": 0.487828544909927,
+      "grad_norm": 0.9029215574264526,
+      "learning_rate": 3.661411187164166e-05,
+      "loss": 1.4807,
+      "step": 11563
+    },
+    {
+      "epoch": 0.4891363962367633,
+      "grad_norm": 0.8788023591041565,
+      "learning_rate": 3.65396767473784e-05,
+      "loss": 1.4622,
+      "step": 11594
+    },
+    {
+      "epoch": 0.49044424756359956,
+      "grad_norm": 0.8894121050834656,
+      "learning_rate": 3.6465111399431465e-05,
+      "loss": 1.4748,
+      "step": 11625
+    },
+    {
+      "epoch": 0.4917520988904358,
+      "grad_norm": 0.9032202363014221,
+      "learning_rate": 3.6390416669260674e-05,
+      "loss": 1.4621,
+      "step": 11656
+    },
+    {
+      "epoch": 0.49305995021727206,
+      "grad_norm": 0.9159075021743774,
+      "learning_rate": 3.63155933997859e-05,
+      "loss": 1.4837,
+      "step": 11687
+    },
+    {
+      "epoch": 0.49436780154410837,
+      "grad_norm": 0.850325345993042,
+      "learning_rate": 3.624064243537758e-05,
+      "loss": 1.4703,
+      "step": 11718
+    },
+    {
+      "epoch": 0.4956756528709446,
+      "grad_norm": 0.9051500558853149,
+      "learning_rate": 3.616556462184716e-05,
+      "loss": 1.4905,
+      "step": 11749
+    },
+    {
+      "epoch": 0.49698350419778087,
+      "grad_norm": 0.9070841073989868,
+      "learning_rate": 3.609036080643755e-05,
+      "loss": 1.4626,
+      "step": 11780
+    },
+    {
+      "epoch": 0.4982913555246171,
+      "grad_norm": 0.8970009088516235,
+      "learning_rate": 3.60150318378136e-05,
+      "loss": 1.4704,
+      "step": 11811
+    },
+    {
+      "epoch": 0.4995992068514534,
+      "grad_norm": 0.8439539074897766,
+      "learning_rate": 3.5939578566052465e-05,
+      "loss": 1.4686,
+      "step": 11842
+    },
+    {
+      "epoch": 0.5009070581782896,
+      "grad_norm": 0.8568843603134155,
+      "learning_rate": 3.586400184263408e-05,
+      "loss": 1.451,
+      "step": 11873
+    },
+    {
+      "epoch": 0.5022149095051259,
+      "grad_norm": 0.8979809284210205,
+      "learning_rate": 3.578830252043148e-05,
+      "loss": 1.4808,
+      "step": 11904
+    },
+    {
+      "epoch": 0.5035227608319622,
+      "grad_norm": 0.8958112001419067,
+      "learning_rate": 3.571248145370125e-05,
+      "loss": 1.4836,
+      "step": 11935
+    },
+    {
+      "epoch": 0.5048306121587984,
+      "grad_norm": 0.8810004591941833,
+      "learning_rate": 3.5636539498073794e-05,
+      "loss": 1.4666,
+      "step": 11966
+    },
+    {
+      "epoch": 0.5061384634856347,
+      "grad_norm": 0.855351984500885,
+      "learning_rate": 3.556047751054378e-05,
+      "loss": 1.4653,
+      "step": 11997
+    },
+    {
+      "epoch": 0.507446314812471,
+      "grad_norm": 0.8665292263031006,
+      "learning_rate": 3.548429634946039e-05,
+      "loss": 1.4737,
+      "step": 12028
+    },
+    {
+      "epoch": 0.5087541661393072,
+      "grad_norm": 0.8537725806236267,
+      "learning_rate": 3.540799687451768e-05,
+      "loss": 1.4517,
+      "step": 12059
+    },
+    {
+      "epoch": 0.5100620174661435,
+      "grad_norm": 0.8791072964668274,
+      "learning_rate": 3.533157994674485e-05,
+      "loss": 1.4504,
+      "step": 12090
+    },
+    {
+      "epoch": 0.5113698687929797,
+      "grad_norm": 0.8664337396621704,
+      "learning_rate": 3.5255046428496546e-05,
+      "loss": 1.4733,
+      "step": 12121
+    },
+    {
+      "epoch": 0.512677720119816,
+      "grad_norm": 0.8952924609184265,
+      "learning_rate": 3.517839718344311e-05,
+      "loss": 1.472,
+      "step": 12152
+    },
+    {
+      "epoch": 0.5139855714466524,
+      "grad_norm": 0.8985433578491211,
+      "learning_rate": 3.510163307656086e-05,
+      "loss": 1.452,
+      "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 sha256:4ecde935cd607ffb947b09c1710b3852e02c5808350a9c8894f95cc7f1e96efb
+size 5304

checkpoint-15260/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/Qwen2.5-7B-Instruct-te-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 sha256:2808712b4e812cf5156e42efee430f2b3aba67ef6b2be9607bcc39a65c53a296
+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 sha256:0ffba600bd1afe47e6ae47e453aaf27393db833e71fd8814ee2f40cfa0c693a0
+size 3662865184

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23c1c9ae15843fd497b21689e274014619d80449bd73e17194946dbfd7646399
+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:aad5ee398c5570fd5aeb6728dd7bc87818886dde584c4a79b35e68de711d6c98
+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": 0.6438003628232714,
+  "eval_steps": 500,
+  "global_step": 15260,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0013078513268362654,
+      "grad_norm": 31.18772315979004,
+      "learning_rate": 1.0157273918741808e-06,
+      "loss": 9.3832,
+      "step": 31
+    },
+    {
+      "epoch": 0.0026157026536725307,
+      "grad_norm": 24.045747756958008,
+      "learning_rate": 2.0314547837483616e-06,
+      "loss": 7.9011,
+      "step": 62
+    },
+    {
+      "epoch": 0.003923553980508796,
+      "grad_norm": 16.459999084472656,
+      "learning_rate": 3.0471821756225426e-06,
+      "loss": 6.3655,
+      "step": 93
+    },
+    {
+      "epoch": 0.0052314053073450615,
+      "grad_norm": 5.892439365386963,
+      "learning_rate": 4.062909567496723e-06,
+      "loss": 5.1577,
+      "step": 124
+    },
+    {
+      "epoch": 0.0065392566341813275,
+      "grad_norm": 7.445889949798584,
+      "learning_rate": 5.078636959370905e-06,
+      "loss": 4.4767,
+      "step": 155
+    },
+    {
+      "epoch": 0.007847107961017593,
+      "grad_norm": 8.36017894744873,
+      "learning_rate": 6.094364351245085e-06,
+      "loss": 4.0756,
+      "step": 186
+    },
+    {
+      "epoch": 0.009154959287853858,
+      "grad_norm": 13.23757266998291,
+      "learning_rate": 7.110091743119267e-06,
+      "loss": 3.7893,
+      "step": 217
+    },
+    {
+      "epoch": 0.010462810614690123,
+      "grad_norm": 10.12263011932373,
+      "learning_rate": 8.125819134993446e-06,
+      "loss": 3.6154,
+      "step": 248
+    },
+    {
+      "epoch": 0.01177066194152639,
+      "grad_norm": 6.559150218963623,
+      "learning_rate": 9.141546526867629e-06,
+      "loss": 3.4391,
+      "step": 279
+    },
+    {
+      "epoch": 0.013078513268362655,
+      "grad_norm": 6.898993015289307,
+      "learning_rate": 1.015727391874181e-05,
+      "loss": 3.3229,
+      "step": 310
+    },
+    {
+      "epoch": 0.01438636459519892,
+      "grad_norm": 8.434200286865234,
+      "learning_rate": 1.117300131061599e-05,
+      "loss": 3.225,
+      "step": 341
+    },
+    {
+      "epoch": 0.015694215922035185,
+      "grad_norm": 7.735746383666992,
+      "learning_rate": 1.218872870249017e-05,
+      "loss": 3.1381,
+      "step": 372
+    },
+    {
+      "epoch": 0.01700206724887145,
+      "grad_norm": 7.964824676513672,
+      "learning_rate": 1.3204456094364351e-05,
+      "loss": 3.06,
+      "step": 403
+    },
+    {
+      "epoch": 0.018309918575707716,
+      "grad_norm": 6.081613063812256,
+      "learning_rate": 1.4220183486238533e-05,
+      "loss": 3.0052,
+      "step": 434
+    },
+    {
+      "epoch": 0.01961776990254398,
+      "grad_norm": 6.740341663360596,
+      "learning_rate": 1.5235910878112714e-05,
+      "loss": 2.9035,
+      "step": 465
+    },
+    {
+      "epoch": 0.020925621229380246,
+      "grad_norm": 4.908828258514404,
+      "learning_rate": 1.6251638269986893e-05,
+      "loss": 2.8602,
+      "step": 496
+    },
+    {
+      "epoch": 0.02223347255621651,
+      "grad_norm": 5.6150360107421875,
+      "learning_rate": 1.7267365661861077e-05,
+      "loss": 2.8223,
+      "step": 527
+    },
+    {
+      "epoch": 0.02354132388305278,
+      "grad_norm": 3.5981647968292236,
+      "learning_rate": 1.8283093053735257e-05,
+      "loss": 2.7488,
+      "step": 558
+    },
+    {
+      "epoch": 0.024849175209889045,
+      "grad_norm": 4.921584606170654,
+      "learning_rate": 1.9298820445609438e-05,
+      "loss": 2.741,
+      "step": 589
+    },
+    {
+      "epoch": 0.02615702653672531,
+      "grad_norm": 3.8303065299987793,
+      "learning_rate": 2.031454783748362e-05,
+      "loss": 2.6923,
+      "step": 620
+    },
+    {
+      "epoch": 0.027464877863561575,
+      "grad_norm": 3.3674638271331787,
+      "learning_rate": 2.13302752293578e-05,
+      "loss": 2.6402,
+      "step": 651
+    },
+    {
+      "epoch": 0.02877272919039784,
+      "grad_norm": 4.096519947052002,
+      "learning_rate": 2.234600262123198e-05,
+      "loss": 2.6372,
+      "step": 682
+    },
+    {
+      "epoch": 0.030080580517234105,
+      "grad_norm": 3.10866641998291,
+      "learning_rate": 2.336173001310616e-05,
+      "loss": 2.5979,
+      "step": 713
+    },
+    {
+      "epoch": 0.03138843184407037,
+      "grad_norm": 3.3147943019866943,
+      "learning_rate": 2.437745740498034e-05,
+      "loss": 2.549,
+      "step": 744
+    },
+    {
+      "epoch": 0.032696283170906636,
+      "grad_norm": 3.045280933380127,
+      "learning_rate": 2.5393184796854525e-05,
+      "loss": 2.5487,
+      "step": 775
+    },
+    {
+      "epoch": 0.0340041344977429,
+      "grad_norm": 3.2536299228668213,
+      "learning_rate": 2.6408912188728702e-05,
+      "loss": 2.5138,
+      "step": 806
+    },
+    {
+      "epoch": 0.035311985824579166,
+      "grad_norm": 3.108548641204834,
+      "learning_rate": 2.7424639580602886e-05,
+      "loss": 2.5006,
+      "step": 837
+    },
+    {
+      "epoch": 0.03661983715141543,
+      "grad_norm": 3.048689603805542,
+      "learning_rate": 2.8440366972477066e-05,
+      "loss": 2.4434,
+      "step": 868
+    },
+    {
+      "epoch": 0.037927688478251696,
+      "grad_norm": 2.8378429412841797,
+      "learning_rate": 2.9456094364351244e-05,
+      "loss": 2.4403,
+      "step": 899
+    },
+    {
+      "epoch": 0.03923553980508796,
+      "grad_norm": 2.731419324874878,
+      "learning_rate": 3.0471821756225428e-05,
+      "loss": 2.4028,
+      "step": 930
+    },
+    {
+      "epoch": 0.04054339113192423,
+      "grad_norm": 2.4825587272644043,
+      "learning_rate": 3.148754914809961e-05,
+      "loss": 2.3695,
+      "step": 961
+    },
+    {
+      "epoch": 0.04185124245876049,
+      "grad_norm": 2.5020129680633545,
+      "learning_rate": 3.2503276539973785e-05,
+      "loss": 2.3513,
+      "step": 992
+    },
+    {
+      "epoch": 0.04315909378559676,
+      "grad_norm": 2.374310255050659,
+      "learning_rate": 3.351900393184797e-05,
+      "loss": 2.3221,
+      "step": 1023
+    },
+    {
+      "epoch": 0.04446694511243302,
+      "grad_norm": 2.4097862243652344,
+      "learning_rate": 3.453473132372215e-05,
+      "loss": 2.3366,
+      "step": 1054
+    },
+    {
+      "epoch": 0.045774796439269294,
+      "grad_norm": 2.573655128479004,
+      "learning_rate": 3.555045871559633e-05,
+      "loss": 2.2997,
+      "step": 1085
+    },
+    {
+      "epoch": 0.04708264776610556,
+      "grad_norm": 2.5408434867858887,
+      "learning_rate": 3.6566186107470514e-05,
+      "loss": 2.2729,
+      "step": 1116
+    },
+    {
+      "epoch": 0.048390499092941824,
+      "grad_norm": 2.222527265548706,
+      "learning_rate": 3.7581913499344695e-05,
+      "loss": 2.2716,
+      "step": 1147
+    },
+    {
+      "epoch": 0.04969835041977809,
+      "grad_norm": 2.342715263366699,
+      "learning_rate": 3.8597640891218876e-05,
+      "loss": 2.2661,
+      "step": 1178
+    },
+    {
+      "epoch": 0.051006201746614355,
+      "grad_norm": 2.134208917617798,
+      "learning_rate": 3.9613368283093056e-05,
+      "loss": 2.2206,
+      "step": 1209
+    },
+    {
+      "epoch": 0.05231405307345062,
+      "grad_norm": 2.2482688426971436,
+      "learning_rate": 4.062909567496724e-05,
+      "loss": 2.2207,
+      "step": 1240
+    },
+    {
+      "epoch": 0.053621904400286885,
+      "grad_norm": 2.2316832542419434,
+      "learning_rate": 4.164482306684142e-05,
+      "loss": 2.1847,
+      "step": 1271
+    },
+    {
+      "epoch": 0.05492975572712315,
+      "grad_norm": 2.2321085929870605,
+      "learning_rate": 4.26605504587156e-05,
+      "loss": 2.2079,
+      "step": 1302
+    },
+    {
+      "epoch": 0.056237607053959415,
+      "grad_norm": 2.115349054336548,
+      "learning_rate": 4.367627785058978e-05,
+      "loss": 2.1458,
+      "step": 1333
+    },
+    {
+      "epoch": 0.05754545838079568,
+      "grad_norm": 2.210914373397827,
+      "learning_rate": 4.469200524246396e-05,
+      "loss": 2.1435,
+      "step": 1364
+    },
+    {
+      "epoch": 0.058853309707631946,
+      "grad_norm": 2.1882164478302,
+      "learning_rate": 4.570773263433814e-05,
+      "loss": 2.1389,
+      "step": 1395
+    },
+    {
+      "epoch": 0.06016116103446821,
+      "grad_norm": 2.01705265045166,
+      "learning_rate": 4.672346002621232e-05,
+      "loss": 2.1599,
+      "step": 1426
+    },
+    {
+      "epoch": 0.061469012361304476,
+      "grad_norm": 1.9447391033172607,
+      "learning_rate": 4.77391874180865e-05,
+      "loss": 2.1254,
+      "step": 1457
+    },
+    {
+      "epoch": 0.06277686368814074,
+      "grad_norm": 1.9278348684310913,
+      "learning_rate": 4.875491480996068e-05,
+      "loss": 2.1109,
+      "step": 1488
+    },
+    {
+      "epoch": 0.064084715014977,
+      "grad_norm": 167.2142791748047,
+      "learning_rate": 4.977064220183487e-05,
+      "loss": 2.12,
+      "step": 1519
+    },
+    {
+      "epoch": 0.06539256634181327,
+      "grad_norm": 15.058513641357422,
+      "learning_rate": 4.9999915451558777e-05,
+      "loss": 3.2174,
+      "step": 1550
+    },
+    {
+      "epoch": 0.06670041766864954,
+      "grad_norm": 2.8855061531066895,
+      "learning_rate": 4.999955597496219e-05,
+      "loss": 2.191,
+      "step": 1581
+    },
+    {
+      "epoch": 0.0680082689954858,
+      "grad_norm": 1.9484020471572876,
+      "learning_rate": 4.9998914381774255e-05,
+      "loss": 2.1053,
+      "step": 1612
+    },
+    {
+      "epoch": 0.06931612032232207,
+      "grad_norm": 5.792853832244873,
+      "learning_rate": 4.999799067923527e-05,
+      "loss": 2.1058,
+      "step": 1643
+    },
+    {
+      "epoch": 0.07062397164915833,
+      "grad_norm": 5.8536553382873535,
+      "learning_rate": 4.999678487776908e-05,
+      "loss": 2.0906,
+      "step": 1674
+    },
+    {
+      "epoch": 0.0719318229759946,
+      "grad_norm": 2.8606152534484863,
+      "learning_rate": 4.9995296990983006e-05,
+      "loss": 2.1356,
+      "step": 1705
+    },
+    {
+      "epoch": 0.07323967430283086,
+      "grad_norm": 2.423034191131592,
+      "learning_rate": 4.999352703566763e-05,
+      "loss": 2.0468,
+      "step": 1736
+    },
+    {
+      "epoch": 0.07454752562966713,
+      "grad_norm": 1.7297399044036865,
+      "learning_rate": 4.999147503179668e-05,
+      "loss": 2.0687,
+      "step": 1767
+    },
+    {
+      "epoch": 0.07585537695650339,
+      "grad_norm": 4.29679536819458,
+      "learning_rate": 4.998914100252672e-05,
+      "loss": 2.026,
+      "step": 1798
+    },
+    {
+      "epoch": 0.07716322828333966,
+      "grad_norm": 1.942807674407959,
+      "learning_rate": 4.998652497419696e-05,
+      "loss": 2.034,
+      "step": 1829
+    },
+    {
+      "epoch": 0.07847107961017592,
+      "grad_norm": 1.8823152780532837,
+      "learning_rate": 4.9983626976328927e-05,
+      "loss": 2.0186,
+      "step": 1860
+    },
+    {
+      "epoch": 0.07977893093701219,
+      "grad_norm": 2.135873556137085,
+      "learning_rate": 4.998044704162613e-05,
+      "loss": 2.0047,
+      "step": 1891
+    },
+    {
+      "epoch": 0.08108678226384845,
+      "grad_norm": 3.113102436065674,
+      "learning_rate": 4.9976985205973705e-05,
+      "loss": 1.9954,
+      "step": 1922
+    },
+    {
+      "epoch": 0.08239463359068472,
+      "grad_norm": 2.253596305847168,
+      "learning_rate": 4.997324150843799e-05,
+      "loss": 1.9744,
+      "step": 1953
+    },
+    {
+      "epoch": 0.08370248491752098,
+      "grad_norm": 5.765998363494873,
+      "learning_rate": 4.99692159912661e-05,
+      "loss": 1.9908,
+      "step": 1984
+    },
+    {
+      "epoch": 0.08501033624435725,
+      "grad_norm": 2.8442440032958984,
+      "learning_rate": 4.996490869988546e-05,
+      "loss": 1.9803,
+      "step": 2015
+    },
+    {
+      "epoch": 0.08631818757119351,
+      "grad_norm": 1.7528963088989258,
+      "learning_rate": 4.996031968290326e-05,
+      "loss": 1.9419,
+      "step": 2046
+    },
+    {
+      "epoch": 0.08762603889802978,
+      "grad_norm": 1.7754414081573486,
+      "learning_rate": 4.995544899210594e-05,
+      "loss": 1.9485,
+      "step": 2077
+    },
+    {
+      "epoch": 0.08893389022486604,
+      "grad_norm": 1.6553430557250977,
+      "learning_rate": 4.9950296682458583e-05,
+      "loss": 1.9469,
+      "step": 2108
+    },
+    {
+      "epoch": 0.09024174155170232,
+      "grad_norm": 1.7296561002731323,
+      "learning_rate": 4.994486281210429e-05,
+      "loss": 1.9195,
+      "step": 2139
+    },
+    {
+      "epoch": 0.09154959287853859,
+      "grad_norm": 1.7001283168792725,
+      "learning_rate": 4.9939147442363566e-05,
+      "loss": 1.9324,
+      "step": 2170
+    },
+    {
+      "epoch": 0.09285744420537485,
+      "grad_norm": 7.332984447479248,
+      "learning_rate": 4.9933150637733574e-05,
+      "loss": 1.9171,
+      "step": 2201
+    },
+    {
+      "epoch": 0.09416529553221112,
+      "grad_norm": 1.6546969413757324,
+      "learning_rate": 4.992687246588743e-05,
+      "loss": 1.9152,
+      "step": 2232
+    },
+    {
+      "epoch": 0.09547314685904738,
+      "grad_norm": 1.843203067779541,
+      "learning_rate": 4.992031299767347e-05,
+      "loss": 1.9015,
+      "step": 2263
+    },
+    {
+      "epoch": 0.09678099818588365,
+      "grad_norm": 4.51094388961792,
+      "learning_rate": 4.9913472307114386e-05,
+      "loss": 1.917,
+      "step": 2294
+    },
+    {
+      "epoch": 0.09808884951271991,
+      "grad_norm": 1.5267099142074585,
+      "learning_rate": 4.9906350471406446e-05,
+      "loss": 1.8985,
+      "step": 2325
+    },
+    {
+      "epoch": 0.09939670083955618,
+      "grad_norm": 2.0826663970947266,
+      "learning_rate": 4.989894757091861e-05,
+      "loss": 1.8968,
+      "step": 2356
+    },
+    {
+      "epoch": 0.10070455216639244,
+      "grad_norm": 1.4929964542388916,
+      "learning_rate": 4.989126368919158e-05,
+      "loss": 1.8711,
+      "step": 2387
+    },
+    {
+      "epoch": 0.10201240349322871,
+      "grad_norm": 1.478498935699463,
+      "learning_rate": 4.988329891293693e-05,
+      "loss": 1.8672,
+      "step": 2418
+    },
+    {
+      "epoch": 0.10332025482006497,
+      "grad_norm": 1.4785969257354736,
+      "learning_rate": 4.987505333203608e-05,
+      "loss": 1.8435,
+      "step": 2449
+    },
+    {
+      "epoch": 0.10462810614690124,
+      "grad_norm": 1.524807333946228,
+      "learning_rate": 4.9866527039539276e-05,
+      "loss": 1.8543,
+      "step": 2480
+    },
+    {
+      "epoch": 0.1059359574737375,
+      "grad_norm": 1.4232748746871948,
+      "learning_rate": 4.9857720131664594e-05,
+      "loss": 1.8463,
+      "step": 2511
+    },
+    {
+      "epoch": 0.10724380880057377,
+      "grad_norm": 1.7178603410720825,
+      "learning_rate": 4.9848632707796773e-05,
+      "loss": 1.8512,
+      "step": 2542
+    },
+    {
+      "epoch": 0.10855166012741004,
+      "grad_norm": 1.4624053239822388,
+      "learning_rate": 4.9839264870486155e-05,
+      "loss": 1.8421,
+      "step": 2573
+    },
+    {
+      "epoch": 0.1098595114542463,
+      "grad_norm": 2.0191211700439453,
+      "learning_rate": 4.9829616725447526e-05,
+      "loss": 1.8393,
+      "step": 2604
+    },
+    {
+      "epoch": 0.11116736278108257,
+      "grad_norm": 1.4346847534179688,
+      "learning_rate": 4.981968838155888e-05,
+      "loss": 1.8149,
+      "step": 2635
+    },
+    {
+      "epoch": 0.11247521410791883,
+      "grad_norm": 1.4674941301345825,
+      "learning_rate": 4.980947995086024e-05,
+      "loss": 1.8215,
+      "step": 2666
+    },
+    {
+      "epoch": 0.1137830654347551,
+      "grad_norm": 1.4122453927993774,
+      "learning_rate": 4.979899154855234e-05,
+      "loss": 1.8265,
+      "step": 2697
+    },
+    {
+      "epoch": 0.11509091676159136,
+      "grad_norm": 1.4748708009719849,
+      "learning_rate": 4.9788223292995386e-05,
+      "loss": 1.8149,
+      "step": 2728
+    },
+    {
+      "epoch": 0.11639876808842763,
+      "grad_norm": 1.40476655960083,
+      "learning_rate": 4.977717530570768e-05,
+      "loss": 1.8316,
+      "step": 2759
+    },
+    {
+      "epoch": 0.11770661941526389,
+      "grad_norm": 1.4909706115722656,
+      "learning_rate": 4.976584771136425e-05,
+      "loss": 1.8208,
+      "step": 2790
+    },
+    {
+      "epoch": 0.11901447074210016,
+      "grad_norm": 1.3661363124847412,
+      "learning_rate": 4.975424063779547e-05,
+      "loss": 1.8038,
+      "step": 2821
+    },
+    {
+      "epoch": 0.12032232206893642,
+      "grad_norm": 1.422453761100769,
+      "learning_rate": 4.974235421598557e-05,
+      "loss": 1.7926,
+      "step": 2852
+    },
+    {
+      "epoch": 0.12163017339577269,
+      "grad_norm": 1.3766013383865356,
+      "learning_rate": 4.973018858007122e-05,
+      "loss": 1.8192,
+      "step": 2883
+    },
+    {
+      "epoch": 0.12293802472260895,
+      "grad_norm": 1.3904545307159424,
+      "learning_rate": 4.9717743867339963e-05,
+      "loss": 1.7653,
+      "step": 2914
+    },
+    {
+      "epoch": 0.12424587604944522,
+      "grad_norm": 1.369018316268921,
+      "learning_rate": 4.9705020218228695e-05,
+      "loss": 1.7879,
+      "step": 2945
+    },
+    {
+      "epoch": 0.12555372737628148,
+      "grad_norm": 1.5040982961654663,
+      "learning_rate": 4.969201777632205e-05,
+      "loss": 1.7777,
+      "step": 2976
+    },
+    {
+      "epoch": 0.12686157870311776,
+      "grad_norm": 1.3161810636520386,
+      "learning_rate": 4.9678736688350846e-05,
+      "loss": 1.7654,
+      "step": 3007
+    },
+    {
+      "epoch": 0.128169430029954,
+      "grad_norm": 1.3379234075546265,
+      "learning_rate": 4.966517710419033e-05,
+      "loss": 1.7699,
+      "step": 3038
+    },
+    {
+      "epoch": 0.1294772813567903,
+      "grad_norm": 1.3384974002838135,
+      "learning_rate": 4.965133917685858e-05,
+      "loss": 1.7915,
+      "step": 3069
+    },
+    {
+      "epoch": 0.13078513268362654,
+      "grad_norm": 1.2991316318511963,
+      "learning_rate": 4.9637223062514714e-05,
+      "loss": 1.7636,
+      "step": 3100
+    },
+    {
+      "epoch": 0.13209298401046282,
+      "grad_norm": 2.500105857849121,
+      "learning_rate": 4.962282892045718e-05,
+      "loss": 1.7573,
+      "step": 3131
+    },
+    {
+      "epoch": 0.13340083533729907,
+      "grad_norm": 1.2635610103607178,
+      "learning_rate": 4.9608156913121904e-05,
+      "loss": 1.7537,
+      "step": 3162
+    },
+    {
+      "epoch": 0.13470868666413535,
+      "grad_norm": 1.2823940515518188,
+      "learning_rate": 4.959320720608049e-05,
+      "loss": 1.7709,
+      "step": 3193
+    },
+    {
+      "epoch": 0.1360165379909716,
+      "grad_norm": 1.2606983184814453,
+      "learning_rate": 4.9577979968038354e-05,
+      "loss": 1.7611,
+      "step": 3224
+    },
+    {
+      "epoch": 0.13732438931780788,
+      "grad_norm": 1.305782437324524,
+      "learning_rate": 4.956247537083282e-05,
+      "loss": 1.7547,
+      "step": 3255
+    },
+    {
+      "epoch": 0.13863224064464413,
+      "grad_norm": 1.2986756563186646,
+      "learning_rate": 4.9546693589431145e-05,
+      "loss": 1.7241,
+      "step": 3286
+    },
+    {
+      "epoch": 0.1399400919714804,
+      "grad_norm": 1.3163083791732788,
+      "learning_rate": 4.9530634801928595e-05,
+      "loss": 1.7352,
+      "step": 3317
+    },
+    {
+      "epoch": 0.14124794329831666,
+      "grad_norm": 1.2844524383544922,
+      "learning_rate": 4.9514299189546395e-05,
+      "loss": 1.7316,
+      "step": 3348
+    },
+    {
+      "epoch": 0.14255579462515294,
+      "grad_norm": 1.2861442565917969,
+      "learning_rate": 4.949768693662973e-05,
+      "loss": 1.7233,
+      "step": 3379
+    },
+    {
+      "epoch": 0.1438636459519892,
+      "grad_norm": 1.2419766187667847,
+      "learning_rate": 4.948079823064559e-05,
+      "loss": 1.7278,
+      "step": 3410
+    },
+    {
+      "epoch": 0.14517149727882547,
+      "grad_norm": 1.2518367767333984,
+      "learning_rate": 4.946363326218074e-05,
+      "loss": 1.7399,
+      "step": 3441
+    },
+    {
+      "epoch": 0.14647934860566172,
+      "grad_norm": 1.217373251914978,
+      "learning_rate": 4.9446192224939525e-05,
+      "loss": 1.7386,
+      "step": 3472
+    },
+    {
+      "epoch": 0.147787199932498,
+      "grad_norm": 1.2229036092758179,
+      "learning_rate": 4.942847531574167e-05,
+      "loss": 1.7096,
+      "step": 3503
+    },
+    {
+      "epoch": 0.14909505125933425,
+      "grad_norm": 1.2012135982513428,
+      "learning_rate": 4.941048273452008e-05,
+      "loss": 1.7195,
+      "step": 3534
+    },
+    {
+      "epoch": 0.15040290258617053,
+      "grad_norm": 1.2632161378860474,
+      "learning_rate": 4.9392214684318605e-05,
+      "loss": 1.7377,
+      "step": 3565
+    },
+    {
+      "epoch": 0.15171075391300679,
+      "grad_norm": 1.2119094133377075,
+      "learning_rate": 4.93736713712897e-05,
+      "loss": 1.7276,
+      "step": 3596
+    },
+    {
+      "epoch": 0.15301860523984306,
+      "grad_norm": 1.2516822814941406,
+      "learning_rate": 4.9354853004692124e-05,
+      "loss": 1.7224,
+      "step": 3627
+    },
+    {
+      "epoch": 0.15432645656667932,
+      "grad_norm": 1.2437561750411987,
+      "learning_rate": 4.93357597968886e-05,
+      "loss": 1.703,
+      "step": 3658
+    },
+    {
+      "epoch": 0.1556343078935156,
+      "grad_norm": 1.4856292009353638,
+      "learning_rate": 4.931639196334338e-05,
+      "loss": 1.7139,
+      "step": 3689
+    },
+    {
+      "epoch": 0.15694215922035185,
+      "grad_norm": 1.202919840812683,
+      "learning_rate": 4.9296749722619826e-05,
+      "loss": 1.7081,
+      "step": 3720
+    },
+    {
+      "epoch": 0.15825001054718812,
+      "grad_norm": 1.1720086336135864,
+      "learning_rate": 4.9276833296377966e-05,
+      "loss": 1.7086,
+      "step": 3751
+    },
+    {
+      "epoch": 0.15955786187402438,
+      "grad_norm": 1.2187249660491943,
+      "learning_rate": 4.925664290937196e-05,
+      "loss": 1.6871,
+      "step": 3782
+    },
+    {
+      "epoch": 0.16086571320086065,
+      "grad_norm": 1.1918401718139648,
+      "learning_rate": 4.9236178789447576e-05,
+      "loss": 1.7058,
+      "step": 3813
+    },
+    {
+      "epoch": 0.1621735645276969,
+      "grad_norm": 1.1956909894943237,
+      "learning_rate": 4.921544116753962e-05,
+      "loss": 1.6986,
+      "step": 3844
+    },
+    {
+      "epoch": 0.16348141585453319,
+      "grad_norm": 1.1646822690963745,
+      "learning_rate": 4.919443027766935e-05,
+      "loss": 1.6797,
+      "step": 3875
+    },
+    {
+      "epoch": 0.16478926718136944,
+      "grad_norm": 1.2145137786865234,
+      "learning_rate": 4.91731463569418e-05,
+      "loss": 1.678,
+      "step": 3906
+    },
+    {
+      "epoch": 0.16609711850820572,
+      "grad_norm": 1.2347453832626343,
+      "learning_rate": 4.915158964554312e-05,
+      "loss": 1.672,
+      "step": 3937
+    },
+    {
+      "epoch": 0.16740496983504197,
+      "grad_norm": 1.1764047145843506,
+      "learning_rate": 4.912976038673786e-05,
+      "loss": 1.6864,
+      "step": 3968
+    },
+    {
+      "epoch": 0.16871282116187825,
+      "grad_norm": 1.1730256080627441,
+      "learning_rate": 4.9107658826866254e-05,
+      "loss": 1.7021,
+      "step": 3999
+    },
+    {
+      "epoch": 0.1700206724887145,
+      "grad_norm": 1.1880205869674683,
+      "learning_rate": 4.908528521534139e-05,
+      "loss": 1.6832,
+      "step": 4030
+    },
+    {
+      "epoch": 0.17132852381555078,
+      "grad_norm": 1.1810024976730347,
+      "learning_rate": 4.906263980464644e-05,
+      "loss": 1.6674,
+      "step": 4061
+    },
+    {
+      "epoch": 0.17263637514238703,
+      "grad_norm": 1.2133933305740356,
+      "learning_rate": 4.903972285033178e-05,
+      "loss": 1.6887,
+      "step": 4092
+    },
+    {
+      "epoch": 0.1739442264692233,
+      "grad_norm": 1.1253775358200073,
+      "learning_rate": 4.901653461101213e-05,
+      "loss": 1.6884,
+      "step": 4123
+    },
+    {
+      "epoch": 0.17525207779605956,
+      "grad_norm": 1.215759038925171,
+      "learning_rate": 4.8993075348363626e-05,
+      "loss": 1.7013,
+      "step": 4154
+    },
+    {
+      "epoch": 0.17655992912289584,
+      "grad_norm": 1.1305285692214966,
+      "learning_rate": 4.896934532712084e-05,
+      "loss": 1.6573,
+      "step": 4185
+    },
+    {
+      "epoch": 0.1778677804497321,
+      "grad_norm": 1.127212405204773,
+      "learning_rate": 4.8945344815073846e-05,
+      "loss": 1.6769,
+      "step": 4216
+    },
+    {
+      "epoch": 0.17917563177656837,
+      "grad_norm": 1.1379367113113403,
+      "learning_rate": 4.892107408306516e-05,
+      "loss": 1.6583,
+      "step": 4247
+    },
+    {
+      "epoch": 0.18048348310340465,
+      "grad_norm": 1.0926482677459717,
+      "learning_rate": 4.889653340498669e-05,
+      "loss": 1.6674,
+      "step": 4278
+    },
+    {
+      "epoch": 0.1817913344302409,
+      "grad_norm": 1.1098601818084717,
+      "learning_rate": 4.8871723057776664e-05,
+      "loss": 1.6598,
+      "step": 4309
+    },
+    {
+      "epoch": 0.18309918575707718,
+      "grad_norm": 1.129784345626831,
+      "learning_rate": 4.8846643321416476e-05,
+      "loss": 1.6786,
+      "step": 4340
+    },
+    {
+      "epoch": 0.18440703708391343,
+      "grad_norm": 1.1000723838806152,
+      "learning_rate": 4.882129447892753e-05,
+      "loss": 1.6623,
+      "step": 4371
+    },
+    {
+      "epoch": 0.1857148884107497,
+      "grad_norm": 1.2229663133621216,
+      "learning_rate": 4.8795676816368076e-05,
+      "loss": 1.6675,
+      "step": 4402
+    },
+    {
+      "epoch": 0.18702273973758596,
+      "grad_norm": 1.1608648300170898,
+      "learning_rate": 4.876979062282995e-05,
+      "loss": 1.6499,
+      "step": 4433
+    },
+    {
+      "epoch": 0.18833059106442224,
+      "grad_norm": 1.1060220003128052,
+      "learning_rate": 4.8743636190435325e-05,
+      "loss": 1.6453,
+      "step": 4464
+    },
+    {
+      "epoch": 0.1896384423912585,
+      "grad_norm": 1.1028501987457275,
+      "learning_rate": 4.871721381433344e-05,
+      "loss": 1.6393,
+      "step": 4495
+    },
+    {
+      "epoch": 0.19094629371809477,
+      "grad_norm": 1.1736187934875488,
+      "learning_rate": 4.869052379269719e-05,
+      "loss": 1.6563,
+      "step": 4526
+    },
+    {
+      "epoch": 0.19225414504493102,
+      "grad_norm": 1.1284164190292358,
+      "learning_rate": 4.866356642671985e-05,
+      "loss": 1.6535,
+      "step": 4557
+    },
+    {
+      "epoch": 0.1935619963717673,
+      "grad_norm": 1.1155307292938232,
+      "learning_rate": 4.8636342020611634e-05,
+      "loss": 1.6417,
+      "step": 4588
+    },
+    {
+      "epoch": 0.19486984769860355,
+      "grad_norm": 1.1379483938217163,
+      "learning_rate": 4.860885088159626e-05,
+      "loss": 1.6432,
+      "step": 4619
+    },
+    {
+      "epoch": 0.19617769902543983,
+      "grad_norm": 1.1166200637817383,
+      "learning_rate": 4.858109331990751e-05,
+      "loss": 1.6545,
+      "step": 4650
+    },
+    {
+      "epoch": 0.19748555035227608,
+      "grad_norm": 1.081626296043396,
+      "learning_rate": 4.855306964878567e-05,
+      "loss": 1.6402,
+      "step": 4681
+    },
+    {
+      "epoch": 0.19879340167911236,
+      "grad_norm": 1.0875532627105713,
+      "learning_rate": 4.8524780184474084e-05,
+      "loss": 1.6498,
+      "step": 4712
+    },
+    {
+      "epoch": 0.2001012530059486,
+      "grad_norm": 1.0928492546081543,
+      "learning_rate": 4.8496225246215496e-05,
+      "loss": 1.6341,
+      "step": 4743
+    },
+    {
+      "epoch": 0.2014091043327849,
+      "grad_norm": 1.1116279363632202,
+      "learning_rate": 4.8467405156248505e-05,
+      "loss": 1.6389,
+      "step": 4774
+    },
+    {
+      "epoch": 0.20271695565962114,
+      "grad_norm": 1.0984513759613037,
+      "learning_rate": 4.843832023980392e-05,
+      "loss": 1.6277,
+      "step": 4805
+    },
+    {
+      "epoch": 0.20402480698645742,
+      "grad_norm": 1.09713876247406,
+      "learning_rate": 4.840897082510106e-05,
+      "loss": 1.6244,
+      "step": 4836
+    },
+    {
+      "epoch": 0.20533265831329367,
+      "grad_norm": 1.089237928390503,
+      "learning_rate": 4.8379357243344084e-05,
+      "loss": 1.6136,
+      "step": 4867
+    },
+    {
+      "epoch": 0.20664050964012995,
+      "grad_norm": 1.1337491273880005,
+      "learning_rate": 4.8349479828718236e-05,
+      "loss": 1.641,
+      "step": 4898
+    },
+    {
+      "epoch": 0.2079483609669662,
+      "grad_norm": 1.1337246894836426,
+      "learning_rate": 4.8319338918386075e-05,
+      "loss": 1.6163,
+      "step": 4929
+    },
+    {
+      "epoch": 0.20925621229380248,
+      "grad_norm": 1.112273097038269,
+      "learning_rate": 4.828893485248369e-05,
+      "loss": 1.6384,
+      "step": 4960
+    },
+    {
+      "epoch": 0.21056406362063873,
+      "grad_norm": 1.049856424331665,
+      "learning_rate": 4.825826797411682e-05,
+      "loss": 1.6245,
+      "step": 4991
+    },
+    {
+      "epoch": 0.211871914947475,
+      "grad_norm": 2.468637704849243,
+      "learning_rate": 4.822733862935702e-05,
+      "loss": 1.6165,
+      "step": 5022
+    },
+    {
+      "epoch": 0.21317976627431126,
+      "grad_norm": 1.0854454040527344,
+      "learning_rate": 4.819614716723775e-05,
+      "loss": 1.6252,
+      "step": 5053
+    },
+    {
+      "epoch": 0.21448761760114754,
+      "grad_norm": 1.0815082788467407,
+      "learning_rate": 4.8164693939750425e-05,
+      "loss": 1.6096,
+      "step": 5084
+    },
+    {
+      "epoch": 0.2157954689279838,
+      "grad_norm": 1.053945541381836,
+      "learning_rate": 4.813297930184042e-05,
+      "loss": 1.6296,
+      "step": 5115
+    },
+    {
+      "epoch": 0.21710332025482007,
+      "grad_norm": 1.06475031375885,
+      "learning_rate": 4.810100361140314e-05,
+      "loss": 1.629,
+      "step": 5146
+    },
+    {
+      "epoch": 0.21841117158165632,
+      "grad_norm": 1.1072969436645508,
+      "learning_rate": 4.8068767229279885e-05,
+      "loss": 1.6244,
+      "step": 5177
+    },
+    {
+      "epoch": 0.2197190229084926,
+      "grad_norm": 1.0536466836929321,
+      "learning_rate": 4.8036270519253854e-05,
+      "loss": 1.6474,
+      "step": 5208
+    },
+    {
+      "epoch": 0.22102687423532885,
+      "grad_norm": 1.1039215326309204,
+      "learning_rate": 4.8003513848046e-05,
+      "loss": 1.6354,
+      "step": 5239
+    },
+    {
+      "epoch": 0.22233472556216513,
+      "grad_norm": 1.0463244915008545,
+      "learning_rate": 4.79704975853109e-05,
+      "loss": 1.6154,
+      "step": 5270
+    },
+    {
+      "epoch": 0.22364257688900138,
+      "grad_norm": 1.0931519269943237,
+      "learning_rate": 4.793722210363262e-05,
+      "loss": 1.6037,
+      "step": 5301
+    },
+    {
+      "epoch": 0.22495042821583766,
+      "grad_norm": 1.0838814973831177,
+      "learning_rate": 4.7903687778520414e-05,
+      "loss": 1.6352,
+      "step": 5332
+    },
+    {
+      "epoch": 0.2262582795426739,
+      "grad_norm": 1.0400842428207397,
+      "learning_rate": 4.7869894988404593e-05,
+      "loss": 1.5924,
+      "step": 5363
+    },
+    {
+      "epoch": 0.2275661308695102,
+      "grad_norm": 1.0707345008850098,
+      "learning_rate": 4.783584411463221e-05,
+      "loss": 1.6211,
+      "step": 5394
+    },
+    {
+      "epoch": 0.22887398219634644,
+      "grad_norm": 1.0422611236572266,
+      "learning_rate": 4.780153554146274e-05,
+      "loss": 1.5969,
+      "step": 5425
+    },
+    {
+      "epoch": 0.23018183352318272,
+      "grad_norm": 1.0401543378829956,
+      "learning_rate": 4.7766969656063766e-05,
+      "loss": 1.5974,
+      "step": 5456
+    },
+    {
+      "epoch": 0.23148968485001897,
+      "grad_norm": 1.0429288148880005,
+      "learning_rate": 4.773214684850662e-05,
+      "loss": 1.6043,
+      "step": 5487
+    },
+    {
+      "epoch": 0.23279753617685525,
+      "grad_norm": 1.098827600479126,
+      "learning_rate": 4.769706751176193e-05,
+      "loss": 1.5984,
+      "step": 5518
+    },
+    {
+      "epoch": 0.2341053875036915,
+      "grad_norm": 1.0090724229812622,
+      "learning_rate": 4.7661732041695264e-05,
+      "loss": 1.6012,
+      "step": 5549
+    },
+    {
+      "epoch": 0.23541323883052778,
+      "grad_norm": 1.0732818841934204,
+      "learning_rate": 4.762614083706258e-05,
+      "loss": 1.5996,
+      "step": 5580
+    },
+    {
+      "epoch": 0.23672109015736403,
+      "grad_norm": 1.082144856452942,
+      "learning_rate": 4.759029429950581e-05,
+      "loss": 1.6127,
+      "step": 5611
+    },
+    {
+      "epoch": 0.2380289414842003,
+      "grad_norm": 1.0642670392990112,
+      "learning_rate": 4.7554192833548235e-05,
+      "loss": 1.5962,
+      "step": 5642
+    },
+    {
+      "epoch": 0.23933679281103656,
+      "grad_norm": 1.1351134777069092,
+      "learning_rate": 4.751783684659e-05,
+      "loss": 1.5983,
+      "step": 5673
+    },
+    {
+      "epoch": 0.24064464413787284,
+      "grad_norm": 1.09076726436615,
+      "learning_rate": 4.748122674890348e-05,
+      "loss": 1.6162,
+      "step": 5704
+    },
+    {
+      "epoch": 0.24195249546470912,
+      "grad_norm": 1.0234689712524414,
+      "learning_rate": 4.7444362953628654e-05,
+      "loss": 1.596,
+      "step": 5735
+    },
+    {
+      "epoch": 0.24326034679154537,
+      "grad_norm": 1.1209464073181152,
+      "learning_rate": 4.7407245876768424e-05,
+      "loss": 1.602,
+      "step": 5766
+    },
+    {
+      "epoch": 0.24456819811838165,
+      "grad_norm": 1.0940710306167603,
+      "learning_rate": 4.736987593718397e-05,
+      "loss": 1.5992,
+      "step": 5797
+    },
+    {
+      "epoch": 0.2458760494452179,
+      "grad_norm": 1.0460273027420044,
+      "learning_rate": 4.733225355658999e-05,
+      "loss": 1.5881,
+      "step": 5828
+    },
+    {
+      "epoch": 0.24718390077205418,
+      "grad_norm": 1.0842856168746948,
+      "learning_rate": 4.7294379159549926e-05,
+      "loss": 1.594,
+      "step": 5859
+    },
+    {
+      "epoch": 0.24849175209889043,
+      "grad_norm": 1.0244876146316528,
+      "learning_rate": 4.725625317347119e-05,
+      "loss": 1.583,
+      "step": 5890
+    },
+    {
+      "epoch": 0.2497996034257267,
+      "grad_norm": 1.0182656049728394,
+      "learning_rate": 4.7217876028600374e-05,
+      "loss": 1.5839,
+      "step": 5921
+    },
+    {
+      "epoch": 0.25110745475256296,
+      "grad_norm": 1.0451878309249878,
+      "learning_rate": 4.717924815801832e-05,
+      "loss": 1.6051,
+      "step": 5952
+    },
+    {
+      "epoch": 0.2524153060793992,
+      "grad_norm": 1.0340505838394165,
+      "learning_rate": 4.714036999763532e-05,
+      "loss": 1.5969,
+      "step": 5983
+    },
+    {
+      "epoch": 0.2537231574062355,
+      "grad_norm": 1.0457735061645508,
+      "learning_rate": 4.7101241986186116e-05,
+      "loss": 1.5971,
+      "step": 6014
+    },
+    {
+      "epoch": 0.2550310087330718,
+      "grad_norm": 1.034166693687439,
+      "learning_rate": 4.7061864565225e-05,
+      "loss": 1.5982,
+      "step": 6045
+    },
+    {
+      "epoch": 0.256338860059908,
+      "grad_norm": 1.0326176881790161,
+      "learning_rate": 4.702223817912081e-05,
+      "loss": 1.5691,
+      "step": 6076
+    },
+    {
+      "epoch": 0.2576467113867443,
+      "grad_norm": 1.0339311361312866,
+      "learning_rate": 4.698236327505195e-05,
+      "loss": 1.5726,
+      "step": 6107
+    },
+    {
+      "epoch": 0.2589545627135806,
+      "grad_norm": 1.022299885749817,
+      "learning_rate": 4.694224030300127e-05,
+      "loss": 1.5935,
+      "step": 6138
+    },
+    {
+      "epoch": 0.26026241404041683,
+      "grad_norm": 1.009255051612854,
+      "learning_rate": 4.690186971575107e-05,
+      "loss": 1.574,
+      "step": 6169
+    },
+    {
+      "epoch": 0.2615702653672531,
+      "grad_norm": 1.0181437730789185,
+      "learning_rate": 4.6861251968877916e-05,
+      "loss": 1.57,
+      "step": 6200
+    },
+    {
+      "epoch": 0.26287811669408934,
+      "grad_norm": 1.0302594900131226,
+      "learning_rate": 4.68203875207476e-05,
+      "loss": 1.5785,
+      "step": 6231
+    },
+    {
+      "epoch": 0.26418596802092564,
+      "grad_norm": 1.006404161453247,
+      "learning_rate": 4.677927683250983e-05,
+      "loss": 1.5798,
+      "step": 6262
+    },
+    {
+      "epoch": 0.2654938193477619,
+      "grad_norm": 0.993584394454956,
+      "learning_rate": 4.6737920368093156e-05,
+      "loss": 1.5558,
+      "step": 6293
+    },
+    {
+      "epoch": 0.26680167067459815,
+      "grad_norm": 0.9635722637176514,
+      "learning_rate": 4.669631859419965e-05,
+      "loss": 1.5716,
+      "step": 6324
+    },
+    {
+      "epoch": 0.2681095220014344,
+      "grad_norm": 0.9815465211868286,
+      "learning_rate": 4.6654471980299676e-05,
+      "loss": 1.5472,
+      "step": 6355
+    },
+    {
+      "epoch": 0.2694173733282707,
+      "grad_norm": 0.9921912550926208,
+      "learning_rate": 4.661238099862658e-05,
+      "loss": 1.5786,
+      "step": 6386
+    },
+    {
+      "epoch": 0.27072522465510696,
+      "grad_norm": 1.0193076133728027,
+      "learning_rate": 4.657004612417138e-05,
+      "loss": 1.5672,
+      "step": 6417
+    },
+    {
+      "epoch": 0.2720330759819432,
+      "grad_norm": 0.9979498982429504,
+      "learning_rate": 4.6527467834677374e-05,
+      "loss": 1.5549,
+      "step": 6448
+    },
+    {
+      "epoch": 0.27334092730877946,
+      "grad_norm": 1.0342402458190918,
+      "learning_rate": 4.648464661063478e-05,
+      "loss": 1.5808,
+      "step": 6479
+    },
+    {
+      "epoch": 0.27464877863561576,
+      "grad_norm": 0.9821639060974121,
+      "learning_rate": 4.6441582935275264e-05,
+      "loss": 1.5642,
+      "step": 6510
+    },
+    {
+      "epoch": 0.275956629962452,
+      "grad_norm": 1.002773404121399,
+      "learning_rate": 4.6398277294566586e-05,
+      "loss": 1.5646,
+      "step": 6541
+    },
+    {
+      "epoch": 0.27726448128928827,
+      "grad_norm": 1.0241411924362183,
+      "learning_rate": 4.6354730177207e-05,
+      "loss": 1.5744,
+      "step": 6572
+    },
+    {
+      "epoch": 0.2785723326161245,
+      "grad_norm": 1.0101004838943481,
+      "learning_rate": 4.6310942074619787e-05,
+      "loss": 1.5905,
+      "step": 6603
+    },
+    {
+      "epoch": 0.2798801839429608,
+      "grad_norm": 1.0355374813079834,
+      "learning_rate": 4.626691348094777e-05,
+      "loss": 1.5713,
+      "step": 6634
+    },
+    {
+      "epoch": 0.2811880352697971,
+      "grad_norm": 1.0100233554840088,
+      "learning_rate": 4.622264489304762e-05,
+      "loss": 1.5491,
+      "step": 6665
+    },
+    {
+      "epoch": 0.2824958865966333,
+      "grad_norm": 1.0172356367111206,
+      "learning_rate": 4.617813681048434e-05,
+      "loss": 1.562,
+      "step": 6696
+    },
+    {
+      "epoch": 0.2838037379234696,
+      "grad_norm": 0.994799017906189,
+      "learning_rate": 4.61333897355256e-05,
+      "loss": 1.5526,
+      "step": 6727
+    },
+    {
+      "epoch": 0.2851115892503059,
+      "grad_norm": 1.1320250034332275,
+      "learning_rate": 4.608840417313604e-05,
+      "loss": 1.5616,
+      "step": 6758
+    },
+    {
+      "epoch": 0.28641944057714214,
+      "grad_norm": 1.013725996017456,
+      "learning_rate": 4.6043180630971646e-05,
+      "loss": 1.5345,
+      "step": 6789
+    },
+    {
+      "epoch": 0.2877272919039784,
+      "grad_norm": 1.045462727546692,
+      "learning_rate": 4.599771961937391e-05,
+      "loss": 1.56,
+      "step": 6820
+    },
+    {
+      "epoch": 0.28903514323081464,
+      "grad_norm": 1.0075098276138306,
+      "learning_rate": 4.5952021651364204e-05,
+      "loss": 1.5825,
+      "step": 6851
+    },
+    {
+      "epoch": 0.29034299455765095,
+      "grad_norm": 0.9952128529548645,
+      "learning_rate": 4.590608724263786e-05,
+      "loss": 1.5581,
+      "step": 6882
+    },
+    {
+      "epoch": 0.2916508458844872,
+      "grad_norm": 0.9492574334144592,
+      "learning_rate": 4.585991691155845e-05,
+      "loss": 1.554,
+      "step": 6913
+    },
+    {
+      "epoch": 0.29295869721132345,
+      "grad_norm": 0.9850384593009949,
+      "learning_rate": 4.581351117915188e-05,
+      "loss": 1.5614,
+      "step": 6944
+    },
+    {
+      "epoch": 0.2942665485381597,
+      "grad_norm": 0.9840113520622253,
+      "learning_rate": 4.5766870569100534e-05,
+      "loss": 1.5631,
+      "step": 6975
+    },
+    {
+      "epoch": 0.295574399864996,
+      "grad_norm": 0.9830542802810669,
+      "learning_rate": 4.571999560773736e-05,
+      "loss": 1.5597,
+      "step": 7006
+    },
+    {
+      "epoch": 0.29688225119183226,
+      "grad_norm": 0.9737412929534912,
+      "learning_rate": 4.5672886824039915e-05,
+      "loss": 1.5412,
+      "step": 7037
+    },
+    {
+      "epoch": 0.2981901025186685,
+      "grad_norm": 1.0272278785705566,
+      "learning_rate": 4.5625544749624435e-05,
+      "loss": 1.5724,
+      "step": 7068
+    },
+    {
+      "epoch": 0.29949795384550476,
+      "grad_norm": 0.973682165145874,
+      "learning_rate": 4.5577969918739794e-05,
+      "loss": 1.5739,
+      "step": 7099
+    },
+    {
+      "epoch": 0.30080580517234107,
+      "grad_norm": 0.9709253907203674,
+      "learning_rate": 4.5530162868261486e-05,
+      "loss": 1.5666,
+      "step": 7130
+    },
+    {
+      "epoch": 0.3021136564991773,
+      "grad_norm": 0.9426018595695496,
+      "learning_rate": 4.548212413768558e-05,
+      "loss": 1.5542,
+      "step": 7161
+    },
+    {
+      "epoch": 0.30342150782601357,
+      "grad_norm": 1.026181697845459,
+      "learning_rate": 4.543385426912261e-05,
+      "loss": 1.5235,
+      "step": 7192
+    },
+    {
+      "epoch": 0.3047293591528499,
+      "grad_norm": 0.9783868193626404,
+      "learning_rate": 4.53853538072915e-05,
+      "loss": 1.5591,
+      "step": 7223
+    },
+    {
+      "epoch": 0.30603721047968613,
+      "grad_norm": 0.9816028475761414,
+      "learning_rate": 4.533662329951336e-05,
+      "loss": 1.5484,
+      "step": 7254
+    },
+    {
+      "epoch": 0.3073450618065224,
+      "grad_norm": 0.9516949653625488,
+      "learning_rate": 4.528766329570536e-05,
+      "loss": 1.5251,
+      "step": 7285
+    },
+    {
+      "epoch": 0.30865291313335863,
+      "grad_norm": 0.9601557850837708,
+      "learning_rate": 4.523847434837447e-05,
+      "loss": 1.5668,
+      "step": 7316
+    },
+    {
+      "epoch": 0.30996076446019494,
+      "grad_norm": 0.9607630372047424,
+      "learning_rate": 4.518905701261128e-05,
+      "loss": 1.5576,
+      "step": 7347
+    },
+    {
+      "epoch": 0.3112686157870312,
+      "grad_norm": 0.9606896638870239,
+      "learning_rate": 4.5139411846083715e-05,
+      "loss": 1.5441,
+      "step": 7378
+    },
+    {
+      "epoch": 0.31257646711386744,
+      "grad_norm": 1.0111651420593262,
+      "learning_rate": 4.508953940903073e-05,
+      "loss": 1.5586,
+      "step": 7409
+    },
+    {
+      "epoch": 0.3138843184407037,
+      "grad_norm": 0.9388339519500732,
+      "learning_rate": 4.5039440264255994e-05,
+      "loss": 1.5472,
+      "step": 7440
+    },
+    {
+      "epoch": 0.31519216976754,
+      "grad_norm": 0.9507540464401245,
+      "learning_rate": 4.498911497712155e-05,
+      "loss": 1.5579,
+      "step": 7471
+    },
+    {
+      "epoch": 0.31650002109437625,
+      "grad_norm": 0.9572455286979675,
+      "learning_rate": 4.493856411554142e-05,
+      "loss": 1.5433,
+      "step": 7502
+    },
+    {
+      "epoch": 0.3178078724212125,
+      "grad_norm": 0.9485601782798767,
+      "learning_rate": 4.4887788249975206e-05,
+      "loss": 1.5513,
+      "step": 7533
+    },
+    {
+      "epoch": 0.31911572374804875,
+      "grad_norm": 0.9995166063308716,
+      "learning_rate": 4.4836787953421656e-05,
+      "loss": 1.5289,
+      "step": 7564
+    },
+    {
+      "epoch": 0.32042357507488506,
+      "grad_norm": 1.1004894971847534,
+      "learning_rate": 4.478556380141218e-05,
+      "loss": 1.5306,
+      "step": 7595
+    },
+    {
+      "epoch": 0.3217314264017213,
+      "grad_norm": 0.9642030000686646,
+      "learning_rate": 4.4734116372004375e-05,
+      "loss": 1.5497,
+      "step": 7626
+    },
+    {
+      "epoch": 0.32303927772855756,
+      "grad_norm": 0.9486343860626221,
+      "learning_rate": 4.4682446245775477e-05,
+      "loss": 1.5458,
+      "step": 7657
+    },
+    {
+      "epoch": 0.3243471290553938,
+      "grad_norm": 0.942319929599762,
+      "learning_rate": 4.463055400581586e-05,
+      "loss": 1.5306,
+      "step": 7688
+    },
+    {
+      "epoch": 0.3256549803822301,
+      "grad_norm": 0.9433887004852295,
+      "learning_rate": 4.4578440237722374e-05,
+      "loss": 1.5394,
+      "step": 7719
+    },
+    {
+      "epoch": 0.32696283170906637,
+      "grad_norm": 0.9954056739807129,
+      "learning_rate": 4.452610552959183e-05,
+      "loss": 1.551,
+      "step": 7750
+    },
+    {
+      "epoch": 0.3282706830359026,
+      "grad_norm": 0.9406622052192688,
+      "learning_rate": 4.447355047201428e-05,
+      "loss": 1.5481,
+      "step": 7781
+    },
+    {
+      "epoch": 0.3295785343627389,
+      "grad_norm": 0.9743403792381287,
+      "learning_rate": 4.4420775658066414e-05,
+      "loss": 1.533,
+      "step": 7812
+    },
+    {
+      "epoch": 0.3308863856895752,
+      "grad_norm": 0.9561812877655029,
+      "learning_rate": 4.436778168330484e-05,
+      "loss": 1.5615,
+      "step": 7843
+    },
+    {
+      "epoch": 0.33219423701641143,
+      "grad_norm": 0.9623595476150513,
+      "learning_rate": 4.4314569145759353e-05,
+      "loss": 1.5463,
+      "step": 7874
+    },
+    {
+      "epoch": 0.3335020883432477,
+      "grad_norm": 0.9475456476211548,
+      "learning_rate": 4.42611386459262e-05,
+      "loss": 1.558,
+      "step": 7905
+    },
+    {
+      "epoch": 0.33480993967008393,
+      "grad_norm": 0.9283867478370667,
+      "learning_rate": 4.420749078676133e-05,
+      "loss": 1.5237,
+      "step": 7936
+    },
+    {
+      "epoch": 0.33611779099692024,
+      "grad_norm": 0.9494192004203796,
+      "learning_rate": 4.4153626173673516e-05,
+      "loss": 1.5315,
+      "step": 7967
+    },
+    {
+      "epoch": 0.3374256423237565,
+      "grad_norm": 0.9378790855407715,
+      "learning_rate": 4.409954541451762e-05,
+      "loss": 1.5378,
+      "step": 7998
+    },
+    {
+      "epoch": 0.33873349365059274,
+      "grad_norm": 0.9318397045135498,
+      "learning_rate": 4.404524911958764e-05,
+      "loss": 1.5199,
+      "step": 8029
+    },
+    {
+      "epoch": 0.340041344977429,
+      "grad_norm": 0.9440187215805054,
+      "learning_rate": 4.399073790160989e-05,
+      "loss": 1.5313,
+      "step": 8060
+    },
+    {
+      "epoch": 0.3413491963042653,
+      "grad_norm": 0.9643428921699524,
+      "learning_rate": 4.393601237573607e-05,
+      "loss": 1.5267,
+      "step": 8091
+    },
+    {
+      "epoch": 0.34265704763110155,
+      "grad_norm": 0.9626632928848267,
+      "learning_rate": 4.388107315953628e-05,
+      "loss": 1.5312,
+      "step": 8122
+    },
+    {
+      "epoch": 0.3439648989579378,
+      "grad_norm": 0.9867373704910278,
+      "learning_rate": 4.382592087299212e-05,
+      "loss": 1.5162,
+      "step": 8153
+    },
+    {
+      "epoch": 0.34527275028477405,
+      "grad_norm": 0.9584757685661316,
+      "learning_rate": 4.377055613848964e-05,
+      "loss": 1.5201,
+      "step": 8184
+    },
+    {
+      "epoch": 0.34658060161161036,
+      "grad_norm": 0.9587807655334473,
+      "learning_rate": 4.3714979580812355e-05,
+      "loss": 1.55,
+      "step": 8215
+    },
+    {
+      "epoch": 0.3478884529384466,
+      "grad_norm": 0.948785662651062,
+      "learning_rate": 4.365919182713416e-05,
+      "loss": 1.5392,
+      "step": 8246
+    },
+    {
+      "epoch": 0.34919630426528286,
+      "grad_norm": 0.9717795252799988,
+      "learning_rate": 4.360319350701226e-05,
+      "loss": 1.5112,
+      "step": 8277
+    },
+    {
+      "epoch": 0.3505041555921191,
+      "grad_norm": 0.9338726997375488,
+      "learning_rate": 4.3546985252380115e-05,
+      "loss": 1.5371,
+      "step": 8308
+    },
+    {
+      "epoch": 0.3518120069189554,
+      "grad_norm": 0.9878547191619873,
+      "learning_rate": 4.349056769754021e-05,
+      "loss": 1.5349,
+      "step": 8339
+    },
+    {
+      "epoch": 0.3531198582457917,
+      "grad_norm": 1.0211338996887207,
+      "learning_rate": 4.3433941479156994e-05,
+      "loss": 1.5234,
+      "step": 8370
+    },
+    {
+      "epoch": 0.3544277095726279,
+      "grad_norm": 0.944474458694458,
+      "learning_rate": 4.3377107236249647e-05,
+      "loss": 1.5306,
+      "step": 8401
+    },
+    {
+      "epoch": 0.3557355608994642,
+      "grad_norm": 0.9218102097511292,
+      "learning_rate": 4.332006561018488e-05,
+      "loss": 1.5113,
+      "step": 8432
+    },
+    {
+      "epoch": 0.3570434122263005,
+      "grad_norm": 0.9429653286933899,
+      "learning_rate": 4.3262817244669683e-05,
+      "loss": 1.5095,
+      "step": 8463
+    },
+    {
+      "epoch": 0.35835126355313673,
+      "grad_norm": 0.8979545831680298,
+      "learning_rate": 4.3205362785744083e-05,
+      "loss": 1.522,
+      "step": 8494
+    },
+    {
+      "epoch": 0.359659114879973,
+      "grad_norm": 0.9040619134902954,
+      "learning_rate": 4.314770288177384e-05,
+      "loss": 1.5197,
+      "step": 8525
+    },
+    {
+      "epoch": 0.3609669662068093,
+      "grad_norm": 0.9038030505180359,
+      "learning_rate": 4.308983818344313e-05,
+      "loss": 1.5218,
+      "step": 8556
+    },
+    {
+      "epoch": 0.36227481753364554,
+      "grad_norm": 0.9493038654327393,
+      "learning_rate": 4.3031769343747206e-05,
+      "loss": 1.5306,
+      "step": 8587
+    },
+    {
+      "epoch": 0.3635826688604818,
+      "grad_norm": 0.9084991812705994,
+      "learning_rate": 4.297349701798505e-05,
+      "loss": 1.5146,
+      "step": 8618
+    },
+    {
+      "epoch": 0.36489052018731805,
+      "grad_norm": 0.9597145915031433,
+      "learning_rate": 4.2915021863751916e-05,
+      "loss": 1.5202,
+      "step": 8649
+    },
+    {
+      "epoch": 0.36619837151415435,
+      "grad_norm": 0.9139339923858643,
+      "learning_rate": 4.285634454093198e-05,
+      "loss": 1.5082,
+      "step": 8680
+    },
+    {
+      "epoch": 0.3675062228409906,
+      "grad_norm": 0.955664336681366,
+      "learning_rate": 4.279746571169086e-05,
+      "loss": 1.5073,
+      "step": 8711
+    },
+    {
+      "epoch": 0.36881407416782686,
+      "grad_norm": 0.975068986415863,
+      "learning_rate": 4.2738386040468136e-05,
+      "loss": 1.5086,
+      "step": 8742
+    },
+    {
+      "epoch": 0.3701219254946631,
+      "grad_norm": 0.9280393719673157,
+      "learning_rate": 4.2679106193969866e-05,
+      "loss": 1.5342,
+      "step": 8773
+    },
+    {
+      "epoch": 0.3714297768214994,
+      "grad_norm": 0.9098469614982605,
+      "learning_rate": 4.261962684116106e-05,
+      "loss": 1.5305,
+      "step": 8804
+    },
+    {
+      "epoch": 0.37273762814833566,
+      "grad_norm": 0.9359835386276245,
+      "learning_rate": 4.2559948653258145e-05,
+      "loss": 1.5172,
+      "step": 8835
+    },
+    {
+      "epoch": 0.3740454794751719,
+      "grad_norm": 0.9431541562080383,
+      "learning_rate": 4.250007230372134e-05,
+      "loss": 1.5128,
+      "step": 8866
+    },
+    {
+      "epoch": 0.37535333080200817,
+      "grad_norm": 0.8999470472335815,
+      "learning_rate": 4.2439998468247126e-05,
+      "loss": 1.5025,
+      "step": 8897
+    },
+    {
+      "epoch": 0.3766611821288445,
+      "grad_norm": 0.9414424300193787,
+      "learning_rate": 4.2379727824760566e-05,
+      "loss": 1.5135,
+      "step": 8928
+    },
+    {
+      "epoch": 0.3779690334556807,
+      "grad_norm": 0.9347614049911499,
+      "learning_rate": 4.231926105340768e-05,
+      "loss": 1.5252,
+      "step": 8959
+    },
+    {
+      "epoch": 0.379276884782517,
+      "grad_norm": 0.9166226983070374,
+      "learning_rate": 4.225859883654776e-05,
+      "loss": 1.519,
+      "step": 8990
+    },
+    {
+      "epoch": 0.3805847361093532,
+      "grad_norm": 0.9614241719245911,
+      "learning_rate": 4.219774185874569e-05,
+      "loss": 1.494,
+      "step": 9021
+    },
+    {
+      "epoch": 0.38189258743618953,
+      "grad_norm": 0.9002947211265564,
+      "learning_rate": 4.213669080676418e-05,
+      "loss": 1.5093,
+      "step": 9052
+    },
+    {
+      "epoch": 0.3832004387630258,
+      "grad_norm": 0.8749356269836426,
+      "learning_rate": 4.2075446369556056e-05,
+      "loss": 1.512,
+      "step": 9083
+    },
+    {
+      "epoch": 0.38450829008986204,
+      "grad_norm": 0.954454243183136,
+      "learning_rate": 4.201400923825648e-05,
+      "loss": 1.4987,
+      "step": 9114
+    },
+    {
+      "epoch": 0.3858161414166983,
+      "grad_norm": 0.9184893369674683,
+      "learning_rate": 4.195238010617511e-05,
+      "loss": 1.5195,
+      "step": 9145
+    },
+    {
+      "epoch": 0.3871239927435346,
+      "grad_norm": 0.9145151376724243,
+      "learning_rate": 4.1890559668788344e-05,
+      "loss": 1.5149,
+      "step": 9176
+    },
+    {
+      "epoch": 0.38843184407037085,
+      "grad_norm": 0.9118244051933289,
+      "learning_rate": 4.1828548623731405e-05,
+      "loss": 1.5179,
+      "step": 9207
+    },
+    {
+      "epoch": 0.3897396953972071,
+      "grad_norm": 0.918662428855896,
+      "learning_rate": 4.1766347670790506e-05,
+      "loss": 1.5023,
+      "step": 9238
+    },
+    {
+      "epoch": 0.39104754672404335,
+      "grad_norm": 0.9427615404129028,
+      "learning_rate": 4.170395751189495e-05,
+      "loss": 1.5093,
+      "step": 9269
+    },
+    {
+      "epoch": 0.39235539805087966,
+      "grad_norm": 0.8825695514678955,
+      "learning_rate": 4.164137885110921e-05,
+      "loss": 1.5056,
+      "step": 9300
+    },
+    {
+      "epoch": 0.3936632493777159,
+      "grad_norm": 0.9850104451179504,
+      "learning_rate": 4.157861239462495e-05,
+      "loss": 1.5308,
+      "step": 9331
+    },
+    {
+      "epoch": 0.39497110070455216,
+      "grad_norm": 0.9645696878433228,
+      "learning_rate": 4.1515658850753114e-05,
+      "loss": 1.4933,
+      "step": 9362
+    },
+    {
+      "epoch": 0.3962789520313884,
+      "grad_norm": 0.9052213430404663,
+      "learning_rate": 4.145251892991588e-05,
+      "loss": 1.5072,
+      "step": 9393
+    },
+    {
+      "epoch": 0.3975868033582247,
+      "grad_norm": 0.9212966561317444,
+      "learning_rate": 4.138919334463868e-05,
+      "loss": 1.5041,
+      "step": 9424
+    },
+    {
+      "epoch": 0.39889465468506097,
+      "grad_norm": 0.8963611721992493,
+      "learning_rate": 4.1325682809542124e-05,
+      "loss": 1.5121,
+      "step": 9455
+    },
+    {
+      "epoch": 0.4002025060118972,
+      "grad_norm": 0.9025225639343262,
+      "learning_rate": 4.126198804133398e-05,
+      "loss": 1.5018,
+      "step": 9486
+    },
+    {
+      "epoch": 0.40151035733873347,
+      "grad_norm": 0.9104238748550415,
+      "learning_rate": 4.1198109758801055e-05,
+      "loss": 1.5107,
+      "step": 9517
+    },
+    {
+      "epoch": 0.4028182086655698,
+      "grad_norm": 0.9045152068138123,
+      "learning_rate": 4.113404868280107e-05,
+      "loss": 1.4841,
+      "step": 9548
+    },
+    {
+      "epoch": 0.40412605999240603,
+      "grad_norm": 0.950362503528595,
+      "learning_rate": 4.106980553625457e-05,
+      "loss": 1.5274,
+      "step": 9579
+    },
+    {
+      "epoch": 0.4054339113192423,
+      "grad_norm": 0.8988200426101685,
+      "learning_rate": 4.100538104413674e-05,
+      "loss": 1.5144,
+      "step": 9610
+    },
+    {
+      "epoch": 0.40674176264607853,
+      "grad_norm": 0.9193787574768066,
+      "learning_rate": 4.09407759334692e-05,
+      "loss": 1.5083,
+      "step": 9641
+    },
+    {
+      "epoch": 0.40804961397291484,
+      "grad_norm": 0.885677695274353,
+      "learning_rate": 4.087599093331186e-05,
+      "loss": 1.4969,
+      "step": 9672
+    },
+    {
+      "epoch": 0.4093574652997511,
+      "grad_norm": 0.9060222506523132,
+      "learning_rate": 4.081102677475462e-05,
+      "loss": 1.4821,
+      "step": 9703
+    },
+    {
+      "epoch": 0.41066531662658734,
+      "grad_norm": 0.9060747623443604,
+      "learning_rate": 4.0745884190909194e-05,
+      "loss": 1.4851,
+      "step": 9734
+    },
+    {
+      "epoch": 0.4119731679534236,
+      "grad_norm": 0.8934387564659119,
+      "learning_rate": 4.0680563916900796e-05,
+      "loss": 1.4874,
+      "step": 9765
+    },
+    {
+      "epoch": 0.4132810192802599,
+      "grad_norm": 0.8983092904090881,
+      "learning_rate": 4.0615066689859815e-05,
+      "loss": 1.503,
+      "step": 9796
+    },
+    {
+      "epoch": 0.41458887060709615,
+      "grad_norm": 0.914784848690033,
+      "learning_rate": 4.0549393248913584e-05,
+      "loss": 1.4986,
+      "step": 9827
+    },
+    {
+      "epoch": 0.4158967219339324,
+      "grad_norm": 0.9157377481460571,
+      "learning_rate": 4.048354433517794e-05,
+      "loss": 1.5072,
+      "step": 9858
+    },
+    {
+      "epoch": 0.41720457326076865,
+      "grad_norm": 0.8943291306495667,
+      "learning_rate": 4.0417520691748916e-05,
+      "loss": 1.4853,
+      "step": 9889
+    },
+    {
+      "epoch": 0.41851242458760496,
+      "grad_norm": 0.9054378271102905,
+      "learning_rate": 4.035132306369438e-05,
+      "loss": 1.5004,
+      "step": 9920
+    },
+    {
+      "epoch": 0.4198202759144412,
+      "grad_norm": 0.9269044399261475,
+      "learning_rate": 4.028495219804555e-05,
+      "loss": 1.4741,
+      "step": 9951
+    },
+    {
+      "epoch": 0.42112812724127746,
+      "grad_norm": 0.8953903913497925,
+      "learning_rate": 4.021840884378864e-05,
+      "loss": 1.4843,
+      "step": 9982
+    },
+    {
+      "epoch": 0.42243597856811377,
+      "grad_norm": 0.8900305032730103,
+      "learning_rate": 4.015169375185633e-05,
+      "loss": 1.5267,
+      "step": 10013
+    },
+    {
+      "epoch": 0.42374382989495,
+      "grad_norm": 0.9487763047218323,
+      "learning_rate": 4.0084807675119396e-05,
+      "loss": 1.5108,
+      "step": 10044
+    },
+    {
+      "epoch": 0.42505168122178627,
+      "grad_norm": 0.9137413501739502,
+      "learning_rate": 4.0017751368378106e-05,
+      "loss": 1.4882,
+      "step": 10075
+    },
+    {
+      "epoch": 0.4263595325486225,
+      "grad_norm": 0.9609214067459106,
+      "learning_rate": 3.995052558835377e-05,
+      "loss": 1.4845,
+      "step": 10106
+    },
+    {
+      "epoch": 0.42766738387545883,
+      "grad_norm": 0.8875072002410889,
+      "learning_rate": 3.988313109368017e-05,
+      "loss": 1.5042,
+      "step": 10137
+    },
+    {
+      "epoch": 0.4289752352022951,
+      "grad_norm": 0.8940466642379761,
+      "learning_rate": 3.981556864489504e-05,
+      "loss": 1.4848,
+      "step": 10168
+    },
+    {
+      "epoch": 0.43028308652913133,
+      "grad_norm": 0.9151347279548645,
+      "learning_rate": 3.974783900443142e-05,
+      "loss": 1.5091,
+      "step": 10199
+    },
+    {
+      "epoch": 0.4315909378559676,
+      "grad_norm": 0.8956405520439148,
+      "learning_rate": 3.9679942936609095e-05,
+      "loss": 1.4925,
+      "step": 10230
+    },
+    {
+      "epoch": 0.4328987891828039,
+      "grad_norm": 0.8801243305206299,
+      "learning_rate": 3.961188120762596e-05,
+      "loss": 1.4992,
+      "step": 10261
+    },
+    {
+      "epoch": 0.43420664050964014,
+      "grad_norm": 0.9045059084892273,
+      "learning_rate": 3.954365458554938e-05,
+      "loss": 1.4873,
+      "step": 10292
+    },
+    {
+      "epoch": 0.4355144918364764,
+      "grad_norm": 0.8852213025093079,
+      "learning_rate": 3.947526384030751e-05,
+      "loss": 1.4907,
+      "step": 10323
+    },
+    {
+      "epoch": 0.43682234316331264,
+      "grad_norm": 0.9119607210159302,
+      "learning_rate": 3.9406709743680624e-05,
+      "loss": 1.4879,
+      "step": 10354
+    },
+    {
+      "epoch": 0.43813019449014895,
+      "grad_norm": 0.8808435201644897,
+      "learning_rate": 3.9337993069292366e-05,
+      "loss": 1.473,
+      "step": 10385
+    },
+    {
+      "epoch": 0.4394380458169852,
+      "grad_norm": 0.8821302056312561,
+      "learning_rate": 3.926911459260109e-05,
+      "loss": 1.4883,
+      "step": 10416
+    },
+    {
+      "epoch": 0.44074589714382145,
+      "grad_norm": 0.8727222084999084,
+      "learning_rate": 3.920007509089102e-05,
+      "loss": 1.4802,
+      "step": 10447
+    },
+    {
+      "epoch": 0.4420537484706577,
+      "grad_norm": 0.8907620310783386,
+      "learning_rate": 3.913087534326357e-05,
+      "loss": 1.4947,
+      "step": 10478
+    },
+    {
+      "epoch": 0.443361599797494,
+      "grad_norm": 0.9233911633491516,
+      "learning_rate": 3.9061516130628475e-05,
+      "loss": 1.4844,
+      "step": 10509
+    },
+    {
+      "epoch": 0.44466945112433026,
+      "grad_norm": 0.8893357515335083,
+      "learning_rate": 3.8991998235695025e-05,
+      "loss": 1.4696,
+      "step": 10540
+    },
+    {
+      "epoch": 0.4459773024511665,
+      "grad_norm": 0.8262650966644287,
+      "learning_rate": 3.8922322442963224e-05,
+      "loss": 1.4867,
+      "step": 10571
+    },
+    {
+      "epoch": 0.44728515377800276,
+      "grad_norm": 0.8931017518043518,
+      "learning_rate": 3.885248953871491e-05,
+      "loss": 1.4655,
+      "step": 10602
+    },
+    {
+      "epoch": 0.44859300510483907,
+      "grad_norm": 0.8849929571151733,
+      "learning_rate": 3.8782500311004915e-05,
+      "loss": 1.4905,
+      "step": 10633
+    },
+    {
+      "epoch": 0.4499008564316753,
+      "grad_norm": 0.8966437578201294,
+      "learning_rate": 3.871235554965218e-05,
+      "loss": 1.4861,
+      "step": 10664
+    },
+    {
+      "epoch": 0.4512087077585116,
+      "grad_norm": 0.931607723236084,
+      "learning_rate": 3.864205604623078e-05,
+      "loss": 1.4816,
+      "step": 10695
+    },
+    {
+      "epoch": 0.4525165590853478,
+      "grad_norm": 0.9525107741355896,
+      "learning_rate": 3.857160259406107e-05,
+      "loss": 1.4758,
+      "step": 10726
+    },
+    {
+      "epoch": 0.45382441041218413,
+      "grad_norm": 0.9055147767066956,
+      "learning_rate": 3.8500995988200674e-05,
+      "loss": 1.4869,
+      "step": 10757
+    },
+    {
+      "epoch": 0.4551322617390204,
+      "grad_norm": 0.8673259019851685,
+      "learning_rate": 3.843023702543556e-05,
+      "loss": 1.482,
+      "step": 10788
+    },
+    {
+      "epoch": 0.45644011306585663,
+      "grad_norm": 0.845866858959198,
+      "learning_rate": 3.8359326504270984e-05,
+      "loss": 1.4733,
+      "step": 10819
+    },
+    {
+      "epoch": 0.4577479643926929,
+      "grad_norm": 0.8884342908859253,
+      "learning_rate": 3.828826522492255e-05,
+      "loss": 1.4711,
+      "step": 10850
+    },
+    {
+      "epoch": 0.4590558157195292,
+      "grad_norm": 0.8943782448768616,
+      "learning_rate": 3.821705398930713e-05,
+      "loss": 1.4538,
+      "step": 10881
+    },
+    {
+      "epoch": 0.46036366704636544,
+      "grad_norm": 0.8772262930870056,
+      "learning_rate": 3.814569360103385e-05,
+      "loss": 1.4771,
+      "step": 10912
+    },
+    {
+      "epoch": 0.4616715183732017,
+      "grad_norm": 0.9197453856468201,
+      "learning_rate": 3.807418486539499e-05,
+      "loss": 1.4648,
+      "step": 10943
+    },
+    {
+      "epoch": 0.46297936970003795,
+      "grad_norm": 0.8835433125495911,
+      "learning_rate": 3.80025285893569e-05,
+      "loss": 1.4677,
+      "step": 10974
+    },
+    {
+      "epoch": 0.46428722102687425,
+      "grad_norm": 0.955093264579773,
+      "learning_rate": 3.793072558155093e-05,
+      "loss": 1.4821,
+      "step": 11005
+    },
+    {
+      "epoch": 0.4655950723537105,
+      "grad_norm": 0.9170013070106506,
+      "learning_rate": 3.785877665226426e-05,
+      "loss": 1.481,
+      "step": 11036
+    },
+    {
+      "epoch": 0.46690292368054676,
+      "grad_norm": 0.8826711177825928,
+      "learning_rate": 3.778668261343079e-05,
+      "loss": 1.4713,
+      "step": 11067
+    },
+    {
+      "epoch": 0.468210775007383,
+      "grad_norm": 0.9213606715202332,
+      "learning_rate": 3.771444427862192e-05,
+      "loss": 1.4898,
+      "step": 11098
+    },
+    {
+      "epoch": 0.4695186263342193,
+      "grad_norm": 1.0346989631652832,
+      "learning_rate": 3.7642062463037465e-05,
+      "loss": 1.4768,
+      "step": 11129
+    },
+    {
+      "epoch": 0.47082647766105556,
+      "grad_norm": 0.8965749740600586,
+      "learning_rate": 3.7569537983496373e-05,
+      "loss": 1.4714,
+      "step": 11160
+    },
+    {
+      "epoch": 0.4721343289878918,
+      "grad_norm": 0.88069748878479,
+      "learning_rate": 3.749687165842753e-05,
+      "loss": 1.4938,
+      "step": 11191
+    },
+    {
+      "epoch": 0.47344218031472807,
+      "grad_norm": 0.8329574465751648,
+      "learning_rate": 3.7424064307860536e-05,
+      "loss": 1.4581,
+      "step": 11222
+    },
+    {
+      "epoch": 0.4747500316415644,
+      "grad_norm": 0.8511537313461304,
+      "learning_rate": 3.735111675341645e-05,
+      "loss": 1.4688,
+      "step": 11253
+    },
+    {
+      "epoch": 0.4760578829684006,
+      "grad_norm": 0.8722901344299316,
+      "learning_rate": 3.7278029818298524e-05,
+      "loss": 1.5016,
+      "step": 11284
+    },
+    {
+      "epoch": 0.4773657342952369,
+      "grad_norm": 0.8820895552635193,
+      "learning_rate": 3.720480432728287e-05,
+      "loss": 1.4775,
+      "step": 11315
+    },
+    {
+      "epoch": 0.47867358562207313,
+      "grad_norm": 0.8825634717941284,
+      "learning_rate": 3.71314411067092e-05,
+      "loss": 1.4997,
+      "step": 11346
+    },
+    {
+      "epoch": 0.47998143694890943,
+      "grad_norm": 0.8426871299743652,
+      "learning_rate": 3.70579409844715e-05,
+      "loss": 1.4549,
+      "step": 11377
+    },
+    {
+      "epoch": 0.4812892882757457,
+      "grad_norm": 0.8519338965415955,
+      "learning_rate": 3.698430479000865e-05,
+      "loss": 1.4788,
+      "step": 11408
+    },
+    {
+      "epoch": 0.48259713960258194,
+      "grad_norm": 0.8908571600914001,
+      "learning_rate": 3.691053335429509e-05,
+      "loss": 1.4775,
+      "step": 11439
+    },
+    {
+      "epoch": 0.48390499092941824,
+      "grad_norm": 0.8275105357170105,
+      "learning_rate": 3.683662750983147e-05,
+      "loss": 1.4569,
+      "step": 11470
+    },
+    {
+      "epoch": 0.4852128422562545,
+      "grad_norm": 0.8812130689620972,
+      "learning_rate": 3.676258809063518e-05,
+      "loss": 1.4706,
+      "step": 11501
+    },
+    {
+      "epoch": 0.48652069358309075,
+      "grad_norm": 0.9266872406005859,
+      "learning_rate": 3.6688415932231004e-05,
+      "loss": 1.4699,
+      "step": 11532
+    },
+    {
+      "epoch": 0.487828544909927,
+      "grad_norm": 0.9029215574264526,
+      "learning_rate": 3.661411187164166e-05,
+      "loss": 1.4807,
+      "step": 11563
+    },
+    {
+      "epoch": 0.4891363962367633,
+      "grad_norm": 0.8788023591041565,
+      "learning_rate": 3.65396767473784e-05,
+      "loss": 1.4622,
+      "step": 11594
+    },
+    {
+      "epoch": 0.49044424756359956,
+      "grad_norm": 0.8894121050834656,
+      "learning_rate": 3.6465111399431465e-05,
+      "loss": 1.4748,
+      "step": 11625
+    },
+    {
+      "epoch": 0.4917520988904358,
+      "grad_norm": 0.9032202363014221,
+      "learning_rate": 3.6390416669260674e-05,
+      "loss": 1.4621,
+      "step": 11656
+    },
+    {
+      "epoch": 0.49305995021727206,
+      "grad_norm": 0.9159075021743774,
+      "learning_rate": 3.63155933997859e-05,
+      "loss": 1.4837,
+      "step": 11687
+    },
+    {
+      "epoch": 0.49436780154410837,
+      "grad_norm": 0.850325345993042,
+      "learning_rate": 3.624064243537758e-05,
+      "loss": 1.4703,
+      "step": 11718
+    },
+    {
+      "epoch": 0.4956756528709446,
+      "grad_norm": 0.9051500558853149,
+      "learning_rate": 3.616556462184716e-05,
+      "loss": 1.4905,
+      "step": 11749
+    },
+    {
+      "epoch": 0.49698350419778087,
+      "grad_norm": 0.9070841073989868,
+      "learning_rate": 3.609036080643755e-05,
+      "loss": 1.4626,
+      "step": 11780
+    },
+    {
+      "epoch": 0.4982913555246171,
+      "grad_norm": 0.8970009088516235,
+      "learning_rate": 3.60150318378136e-05,
+      "loss": 1.4704,
+      "step": 11811
+    },
+    {
+      "epoch": 0.4995992068514534,
+      "grad_norm": 0.8439539074897766,
+      "learning_rate": 3.5939578566052465e-05,
+      "loss": 1.4686,
+      "step": 11842
+    },
+    {
+      "epoch": 0.5009070581782896,
+      "grad_norm": 0.8568843603134155,
+      "learning_rate": 3.586400184263408e-05,
+      "loss": 1.451,
+      "step": 11873
+    },
+    {
+      "epoch": 0.5022149095051259,
+      "grad_norm": 0.8979809284210205,
+      "learning_rate": 3.578830252043148e-05,
+      "loss": 1.4808,
+      "step": 11904
+    },
+    {
+      "epoch": 0.5035227608319622,
+      "grad_norm": 0.8958112001419067,
+      "learning_rate": 3.571248145370125e-05,
+      "loss": 1.4836,
+      "step": 11935
+    },
+    {
+      "epoch": 0.5048306121587984,
+      "grad_norm": 0.8810004591941833,
+      "learning_rate": 3.5636539498073794e-05,
+      "loss": 1.4666,
+      "step": 11966
+    },
+    {
+      "epoch": 0.5061384634856347,
+      "grad_norm": 0.855351984500885,
+      "learning_rate": 3.556047751054378e-05,
+      "loss": 1.4653,
+      "step": 11997
+    },
+    {
+      "epoch": 0.507446314812471,
+      "grad_norm": 0.8665292263031006,
+      "learning_rate": 3.548429634946039e-05,
+      "loss": 1.4737,
+      "step": 12028
+    },
+    {
+      "epoch": 0.5087541661393072,
+      "grad_norm": 0.8537725806236267,
+      "learning_rate": 3.540799687451768e-05,
+      "loss": 1.4517,
+      "step": 12059
+    },
+    {
+      "epoch": 0.5100620174661435,
+      "grad_norm": 0.8791072964668274,
+      "learning_rate": 3.533157994674485e-05,
+      "loss": 1.4504,
+      "step": 12090
+    },
+    {
+      "epoch": 0.5113698687929797,
+      "grad_norm": 0.8664337396621704,
+      "learning_rate": 3.5255046428496546e-05,
+      "loss": 1.4733,
+      "step": 12121
+    },
+    {
+      "epoch": 0.512677720119816,
+      "grad_norm": 0.8952924609184265,
+      "learning_rate": 3.517839718344311e-05,
+      "loss": 1.472,
+      "step": 12152
+    },
+    {
+      "epoch": 0.5139855714466524,
+      "grad_norm": 0.8985433578491211,
+      "learning_rate": 3.510163307656086e-05,
+      "loss": 1.452,
+      "step": 12183
+    },
+    {
+      "epoch": 0.5152934227734886,
+      "grad_norm": 0.8967877626419067,
+      "learning_rate": 3.5024754974122324e-05,
+      "loss": 1.4516,
+      "step": 12214
+    },
+    {
+      "epoch": 0.5166012741003249,
+      "grad_norm": 0.8831754922866821,
+      "learning_rate": 3.494776374368643e-05,
+      "loss": 1.467,
+      "step": 12245
+    },
+    {
+      "epoch": 0.5179091254271612,
+      "grad_norm": 0.8881738781929016,
+      "learning_rate": 3.4870660254088724e-05,
+      "loss": 1.444,
+      "step": 12276
+    },
+    {
+      "epoch": 0.5192169767539974,
+      "grad_norm": 0.8571346998214722,
+      "learning_rate": 3.479344537543164e-05,
+      "loss": 1.4695,
+      "step": 12307
+    },
+    {
+      "epoch": 0.5205248280808337,
+      "grad_norm": 0.8962191343307495,
+      "learning_rate": 3.4716119979074565e-05,
+      "loss": 1.4539,
+      "step": 12338
+    },
+    {
+      "epoch": 0.5218326794076699,
+      "grad_norm": 0.8515344262123108,
+      "learning_rate": 3.463868493762412e-05,
+      "loss": 1.4691,
+      "step": 12369
+    },
+    {
+      "epoch": 0.5231405307345062,
+      "grad_norm": 0.8616427183151245,
+      "learning_rate": 3.456114112492418e-05,
+      "loss": 1.4655,
+      "step": 12400
+    },
+    {
+      "epoch": 0.5244483820613425,
+      "grad_norm": 0.8810769319534302,
+      "learning_rate": 3.4483489416046164e-05,
+      "loss": 1.4662,
+      "step": 12431
+    },
+    {
+      "epoch": 0.5257562333881787,
+      "grad_norm": 0.8603881001472473,
+      "learning_rate": 3.440573068727905e-05,
+      "loss": 1.4863,
+      "step": 12462
+    },
+    {
+      "epoch": 0.527064084715015,
+      "grad_norm": 0.8843648433685303,
+      "learning_rate": 3.4327865816119495e-05,
+      "loss": 1.4665,
+      "step": 12493
+    },
+    {
+      "epoch": 0.5283719360418513,
+      "grad_norm": 0.8736210465431213,
+      "learning_rate": 3.4249895681262025e-05,
+      "loss": 1.4626,
+      "step": 12524
+    },
+    {
+      "epoch": 0.5296797873686875,
+      "grad_norm": 0.8971989750862122,
+      "learning_rate": 3.417182116258899e-05,
+      "loss": 1.4413,
+      "step": 12555
+    },
+    {
+      "epoch": 0.5309876386955238,
+      "grad_norm": 0.855297327041626,
+      "learning_rate": 3.409364314116074e-05,
+      "loss": 1.4792,
+      "step": 12586
+    },
+    {
+      "epoch": 0.53229549002236,
+      "grad_norm": 0.8786769509315491,
+      "learning_rate": 3.401536249920559e-05,
+      "loss": 1.4526,
+      "step": 12617
+    },
+    {
+      "epoch": 0.5336033413491963,
+      "grad_norm": 0.8810843229293823,
+      "learning_rate": 3.393698012010998e-05,
+      "loss": 1.4836,
+      "step": 12648
+    },
+    {
+      "epoch": 0.5349111926760326,
+      "grad_norm": 0.8931439518928528,
+      "learning_rate": 3.385849688840839e-05,
+      "loss": 1.4375,
+      "step": 12679
+    },
+    {
+      "epoch": 0.5362190440028688,
+      "grad_norm": 0.8540153503417969,
+      "learning_rate": 3.3779913689773414e-05,
+      "loss": 1.4493,
+      "step": 12710
+    },
+    {
+      "epoch": 0.5375268953297051,
+      "grad_norm": 0.8924010992050171,
+      "learning_rate": 3.370123141100578e-05,
+      "loss": 1.4416,
+      "step": 12741
+    },
+    {
+      "epoch": 0.5388347466565414,
+      "grad_norm": 0.8814260959625244,
+      "learning_rate": 3.3622450940024305e-05,
+      "loss": 1.4619,
+      "step": 12772
+    },
+    {
+      "epoch": 0.5401425979833776,
+      "grad_norm": 0.8524183630943298,
+      "learning_rate": 3.35435731658559e-05,
+      "loss": 1.4469,
+      "step": 12803
+    },
+    {
+      "epoch": 0.5414504493102139,
+      "grad_norm": 0.860457718372345,
+      "learning_rate": 3.346459897862552e-05,
+      "loss": 1.4552,
+      "step": 12834
+    },
+    {
+      "epoch": 0.5427583006370502,
+      "grad_norm": 0.859676718711853,
+      "learning_rate": 3.338552926954613e-05,
+      "loss": 1.4585,
+      "step": 12865
+    },
+    {
+      "epoch": 0.5440661519638864,
+      "grad_norm": 0.8739502429962158,
+      "learning_rate": 3.330636493090868e-05,
+      "loss": 1.4506,
+      "step": 12896
+    },
+    {
+      "epoch": 0.5453740032907227,
+      "grad_norm": 0.8808159828186035,
+      "learning_rate": 3.322710685607193e-05,
+      "loss": 1.4612,
+      "step": 12927
+    },
+    {
+      "epoch": 0.5466818546175589,
+      "grad_norm": 0.8579108119010925,
+      "learning_rate": 3.314775593945251e-05,
+      "loss": 1.4462,
+      "step": 12958
+    },
+    {
+      "epoch": 0.5479897059443952,
+      "grad_norm": 0.9209607839584351,
+      "learning_rate": 3.3068313076514714e-05,
+      "loss": 1.4464,
+      "step": 12989
+    },
+    {
+      "epoch": 0.5492975572712315,
+      "grad_norm": 0.8351584672927856,
+      "learning_rate": 3.298877916376047e-05,
+      "loss": 1.4478,
+      "step": 13020
+    },
+    {
+      "epoch": 0.5506054085980677,
+      "grad_norm": 0.8345361351966858,
+      "learning_rate": 3.290915509871915e-05,
+      "loss": 1.428,
+      "step": 13051
+    },
+    {
+      "epoch": 0.551913259924904,
+      "grad_norm": 1.180969476699829,
+      "learning_rate": 3.282944177993753e-05,
+      "loss": 1.442,
+      "step": 13082
+    },
+    {
+      "epoch": 0.5532211112517403,
+      "grad_norm": 0.8715757131576538,
+      "learning_rate": 3.274964010696957e-05,
+      "loss": 1.4536,
+      "step": 13113
+    },
+    {
+      "epoch": 0.5545289625785765,
+      "grad_norm": 0.8906053304672241,
+      "learning_rate": 3.266975098036629e-05,
+      "loss": 1.4512,
+      "step": 13144
+    },
+    {
+      "epoch": 0.5558368139054128,
+      "grad_norm": 0.8323124647140503,
+      "learning_rate": 3.258977530166562e-05,
+      "loss": 1.4515,
+      "step": 13175
+    },
+    {
+      "epoch": 0.557144665232249,
+      "grad_norm": 0.835608959197998,
+      "learning_rate": 3.250971397338227e-05,
+      "loss": 1.4563,
+      "step": 13206
+    },
+    {
+      "epoch": 0.5584525165590853,
+      "grad_norm": 0.8299891948699951,
+      "learning_rate": 3.2429567898997404e-05,
+      "loss": 1.4551,
+      "step": 13237
+    },
+    {
+      "epoch": 0.5597603678859217,
+      "grad_norm": 0.8563460111618042,
+      "learning_rate": 3.234933798294859e-05,
+      "loss": 1.4282,
+      "step": 13268
+    },
+    {
+      "epoch": 0.5610682192127578,
+      "grad_norm": 0.8846110701560974,
+      "learning_rate": 3.2269025130619535e-05,
+      "loss": 1.441,
+      "step": 13299
+    },
+    {
+      "epoch": 0.5623760705395942,
+      "grad_norm": 0.8108500242233276,
+      "learning_rate": 3.218863024832985e-05,
+      "loss": 1.4702,
+      "step": 13330
+    },
+    {
+      "epoch": 0.5636839218664305,
+      "grad_norm": 0.8752537369728088,
+      "learning_rate": 3.2108154243324864e-05,
+      "loss": 1.4361,
+      "step": 13361
+    },
+    {
+      "epoch": 0.5649917731932667,
+      "grad_norm": 0.8647633790969849,
+      "learning_rate": 3.2027598023765345e-05,
+      "loss": 1.4365,
+      "step": 13392
+    },
+    {
+      "epoch": 0.566299624520103,
+      "grad_norm": 0.8434934616088867,
+      "learning_rate": 3.194696249871729e-05,
+      "loss": 1.4495,
+      "step": 13423
+    },
+    {
+      "epoch": 0.5676074758469392,
+      "grad_norm": 0.8327639102935791,
+      "learning_rate": 3.186624857814164e-05,
+      "loss": 1.463,
+      "step": 13454
+    },
+    {
+      "epoch": 0.5689153271737755,
+      "grad_norm": 0.8536667823791504,
+      "learning_rate": 3.178545717288401e-05,
+      "loss": 1.4334,
+      "step": 13485
+    },
+    {
+      "epoch": 0.5702231785006118,
+      "grad_norm": 0.8552531003952026,
+      "learning_rate": 3.170458919466444e-05,
+      "loss": 1.453,
+      "step": 13516
+    },
+    {
+      "epoch": 0.571531029827448,
+      "grad_norm": 0.8317746520042419,
+      "learning_rate": 3.1623645556067063e-05,
+      "loss": 1.4586,
+      "step": 13547
+    },
+    {
+      "epoch": 0.5728388811542843,
+      "grad_norm": 0.858818531036377,
+      "learning_rate": 3.154262717052985e-05,
+      "loss": 1.4386,
+      "step": 13578
+    },
+    {
+      "epoch": 0.5741467324811206,
+      "grad_norm": 0.8759421110153198,
+      "learning_rate": 3.146153495233426e-05,
+      "loss": 1.4411,
+      "step": 13609
+    },
+    {
+      "epoch": 0.5754545838079568,
+      "grad_norm": 0.9180925488471985,
+      "learning_rate": 3.1380369816594944e-05,
+      "loss": 1.4412,
+      "step": 13640
+    },
+    {
+      "epoch": 0.5767624351347931,
+      "grad_norm": 0.8536112904548645,
+      "learning_rate": 3.129913267924946e-05,
+      "loss": 1.426,
+      "step": 13671
+    },
+    {
+      "epoch": 0.5780702864616293,
+      "grad_norm": 0.8422097563743591,
+      "learning_rate": 3.121782445704782e-05,
+      "loss": 1.4446,
+      "step": 13702
+    },
+    {
+      "epoch": 0.5793781377884656,
+      "grad_norm": 0.8785713315010071,
+      "learning_rate": 3.11364460675423e-05,
+      "loss": 1.4583,
+      "step": 13733
+    },
+    {
+      "epoch": 0.5806859891153019,
+      "grad_norm": 0.8932250738143921,
+      "learning_rate": 3.1054998429076934e-05,
+      "loss": 1.4767,
+      "step": 13764
+    },
+    {
+      "epoch": 0.5819938404421381,
+      "grad_norm": 0.8232563138008118,
+      "learning_rate": 3.097348246077728e-05,
+      "loss": 1.4384,
+      "step": 13795
+    },
+    {
+      "epoch": 0.5833016917689744,
+      "grad_norm": 0.8628634810447693,
+      "learning_rate": 3.0891899082539924e-05,
+      "loss": 1.4198,
+      "step": 13826
+    },
+    {
+      "epoch": 0.5846095430958107,
+      "grad_norm": 0.8697309494018555,
+      "learning_rate": 3.0810249215022233e-05,
+      "loss": 1.4431,
+      "step": 13857
+    },
+    {
+      "epoch": 0.5859173944226469,
+      "grad_norm": 0.8559725880622864,
+      "learning_rate": 3.0728533779631865e-05,
+      "loss": 1.4556,
+      "step": 13888
+    },
+    {
+      "epoch": 0.5872252457494832,
+      "grad_norm": 0.8450871109962463,
+      "learning_rate": 3.064675369851637e-05,
+      "loss": 1.4357,
+      "step": 13919
+    },
+    {
+      "epoch": 0.5885330970763194,
+      "grad_norm": 0.8583346009254456,
+      "learning_rate": 3.056490989455289e-05,
+      "loss": 1.4503,
+      "step": 13950
+    },
+    {
+      "epoch": 0.5898409484031557,
+      "grad_norm": 0.8461182117462158,
+      "learning_rate": 3.0483003291337596e-05,
+      "loss": 1.4379,
+      "step": 13981
+    },
+    {
+      "epoch": 0.591148799729992,
+      "grad_norm": 0.8465268015861511,
+      "learning_rate": 3.040103481317539e-05,
+      "loss": 1.4427,
+      "step": 14012
+    },
+    {
+      "epoch": 0.5924566510568282,
+      "grad_norm": 0.8772551417350769,
+      "learning_rate": 3.03190053850694e-05,
+      "loss": 1.4382,
+      "step": 14043
+    },
+    {
+      "epoch": 0.5937645023836645,
+      "grad_norm": 0.8575912714004517,
+      "learning_rate": 3.0236915932710573e-05,
+      "loss": 1.4395,
+      "step": 14074
+    },
+    {
+      "epoch": 0.5950723537105008,
+      "grad_norm": 0.8548452258110046,
+      "learning_rate": 3.0154767382467232e-05,
+      "loss": 1.4569,
+      "step": 14105
+    },
+    {
+      "epoch": 0.596380205037337,
+      "grad_norm": 0.8532379865646362,
+      "learning_rate": 3.0072560661374582e-05,
+      "loss": 1.455,
+      "step": 14136
+    },
+    {
+      "epoch": 0.5976880563641733,
+      "grad_norm": 0.8995953798294067,
+      "learning_rate": 2.999029669712431e-05,
+      "loss": 1.4284,
+      "step": 14167
+    },
+    {
+      "epoch": 0.5989959076910095,
+      "grad_norm": 0.8514725565910339,
+      "learning_rate": 2.990797641805408e-05,
+      "loss": 1.4421,
+      "step": 14198
+    },
+    {
+      "epoch": 0.6003037590178458,
+      "grad_norm": 0.8758474588394165,
+      "learning_rate": 2.982560075313704e-05,
+      "loss": 1.4499,
+      "step": 14229
+    },
+    {
+      "epoch": 0.6016116103446821,
+      "grad_norm": 0.8488143086433411,
+      "learning_rate": 2.9743170631971368e-05,
+      "loss": 1.4372,
+      "step": 14260
+    },
+    {
+      "epoch": 0.6029194616715183,
+      "grad_norm": 0.8220718502998352,
+      "learning_rate": 2.9660686984769792e-05,
+      "loss": 1.4386,
+      "step": 14291
+    },
+    {
+      "epoch": 0.6042273129983546,
+      "grad_norm": 0.8164191842079163,
+      "learning_rate": 2.9578150742349047e-05,
+      "loss": 1.4483,
+      "step": 14322
+    },
+    {
+      "epoch": 0.6055351643251909,
+      "grad_norm": 0.8328901529312134,
+      "learning_rate": 2.949556283611942e-05,
+      "loss": 1.415,
+      "step": 14353
+    },
+    {
+      "epoch": 0.6068430156520271,
+      "grad_norm": 0.8837373852729797,
+      "learning_rate": 2.9412924198074206e-05,
+      "loss": 1.424,
+      "step": 14384
+    },
+    {
+      "epoch": 0.6081508669788634,
+      "grad_norm": 0.8237875699996948,
+      "learning_rate": 2.9330235760779208e-05,
+      "loss": 1.4431,
+      "step": 14415
+    },
+    {
+      "epoch": 0.6094587183056998,
+      "grad_norm": 0.8620266318321228,
+      "learning_rate": 2.9247498457362188e-05,
+      "loss": 1.4524,
+      "step": 14446
+    },
+    {
+      "epoch": 0.610766569632536,
+      "grad_norm": 0.8520477414131165,
+      "learning_rate": 2.9164713221502373e-05,
+      "loss": 1.4223,
+      "step": 14477
+    },
+    {
+      "epoch": 0.6120744209593723,
+      "grad_norm": 0.8385702967643738,
+      "learning_rate": 2.9081880987419912e-05,
+      "loss": 1.4357,
+      "step": 14508
+    },
+    {
+      "epoch": 0.6133822722862085,
+      "grad_norm": 0.8283481597900391,
+      "learning_rate": 2.8999002689865296e-05,
+      "loss": 1.4366,
+      "step": 14539
+    },
+    {
+      "epoch": 0.6146901236130448,
+      "grad_norm": 0.8642637133598328,
+      "learning_rate": 2.8916079264108852e-05,
+      "loss": 1.4541,
+      "step": 14570
+    },
+    {
+      "epoch": 0.6159979749398811,
+      "grad_norm": 0.8478630781173706,
+      "learning_rate": 2.883311164593017e-05,
+      "loss": 1.4401,
+      "step": 14601
+    },
+    {
+      "epoch": 0.6173058262667173,
+      "grad_norm": 0.8753395080566406,
+      "learning_rate": 2.875010077160754e-05,
+      "loss": 1.4702,
+      "step": 14632
+    },
+    {
+      "epoch": 0.6186136775935536,
+      "grad_norm": 0.827409029006958,
+      "learning_rate": 2.866704757790741e-05,
+      "loss": 1.4677,
+      "step": 14663
+    },
+    {
+      "epoch": 0.6199215289203899,
+      "grad_norm": 0.8742043375968933,
+      "learning_rate": 2.858395300207376e-05,
+      "loss": 1.4291,
+      "step": 14694
+    },
+    {
+      "epoch": 0.6212293802472261,
+      "grad_norm": 0.8350484371185303,
+      "learning_rate": 2.8500817981817607e-05,
+      "loss": 1.4475,
+      "step": 14725
+    },
+    {
+      "epoch": 0.6225372315740624,
+      "grad_norm": 0.8273993134498596,
+      "learning_rate": 2.8417643455306336e-05,
+      "loss": 1.4303,
+      "step": 14756
+    },
+    {
+      "epoch": 0.6238450829008986,
+      "grad_norm": 0.8380706310272217,
+      "learning_rate": 2.8334430361153185e-05,
+      "loss": 1.4479,
+      "step": 14787
+    },
+    {
+      "epoch": 0.6251529342277349,
+      "grad_norm": 0.8500368595123291,
+      "learning_rate": 2.8251179638406612e-05,
+      "loss": 1.4293,
+      "step": 14818
+    },
+    {
+      "epoch": 0.6264607855545712,
+      "grad_norm": 0.837519109249115,
+      "learning_rate": 2.8167892226539704e-05,
+      "loss": 1.4433,
+      "step": 14849
+    },
+    {
+      "epoch": 0.6277686368814074,
+      "grad_norm": 0.8816763758659363,
+      "learning_rate": 2.8084569065439588e-05,
+      "loss": 1.4225,
+      "step": 14880
+    },
+    {
+      "epoch": 0.6290764882082437,
+      "grad_norm": 0.8599192500114441,
+      "learning_rate": 2.8001211095396807e-05,
+      "loss": 1.4494,
+      "step": 14911
+    },
+    {
+      "epoch": 0.63038433953508,
+      "grad_norm": 0.8788051009178162,
+      "learning_rate": 2.791781925709473e-05,
+      "loss": 1.424,
+      "step": 14942
+    },
+    {
+      "epoch": 0.6316921908619162,
+      "grad_norm": 0.8713638186454773,
+      "learning_rate": 2.7834394491598908e-05,
+      "loss": 1.4386,
+      "step": 14973
+    },
+    {
+      "epoch": 0.6330000421887525,
+      "grad_norm": 0.883663535118103,
+      "learning_rate": 2.7750937740346485e-05,
+      "loss": 1.4509,
+      "step": 15004
+    },
+    {
+      "epoch": 0.6343078935155887,
+      "grad_norm": 0.8379449248313904,
+      "learning_rate": 2.7667449945135564e-05,
+      "loss": 1.4257,
+      "step": 15035
+    },
+    {
+      "epoch": 0.635615744842425,
+      "grad_norm": 0.8503741025924683,
+      "learning_rate": 2.7583932048114557e-05,
+      "loss": 1.429,
+      "step": 15066
+    },
+    {
+      "epoch": 0.6369235961692613,
+      "grad_norm": 0.8763847351074219,
+      "learning_rate": 2.7500384991771587e-05,
+      "loss": 1.4362,
+      "step": 15097
+    },
+    {
+      "epoch": 0.6382314474960975,
+      "grad_norm": 0.8516677021980286,
+      "learning_rate": 2.7416809718923825e-05,
+      "loss": 1.4248,
+      "step": 15128
+    },
+    {
+      "epoch": 0.6395392988229338,
+      "grad_norm": 0.8780989050865173,
+      "learning_rate": 2.7333207172706864e-05,
+      "loss": 1.4154,
+      "step": 15159
+    },
+    {
+      "epoch": 0.6408471501497701,
+      "grad_norm": 0.8541295528411865,
+      "learning_rate": 2.7249578296564088e-05,
+      "loss": 1.4364,
+      "step": 15190
+    },
+    {
+      "epoch": 0.6421550014766063,
+      "grad_norm": 0.8412326574325562,
+      "learning_rate": 2.7165924034235973e-05,
+      "loss": 1.4317,
+      "step": 15221
+    },
+    {
+      "epoch": 0.6434628528034426,
+      "grad_norm": 0.8619037866592407,
+      "learning_rate": 2.708224532974953e-05,
+      "loss": 1.4421,
+      "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 sha256:4ecde935cd607ffb947b09c1710b3852e02c5808350a9c8894f95cc7f1e96efb
+size 5304

checkpoint-18312/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/Qwen2.5-7B-Instruct-te-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 sha256:3b712bb45320d8a27bc8926e88ca81a55801ce47e020d58716c2e61abd7eabf1
+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 sha256:8859d39823e9d0c373fc5576f953e73be9e1cf2bccf2c4ac6e7ece4891b607de
+size 3662865184

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:157af006658547ecd902a07d6c01933384a9296427a161b20044ed1964568049
+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:a9e5f3510621b667ef1f8a5a8e5741a1ca531920f40e250688937dcbe7c65439
+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 sha256:4ecde935cd607ffb947b09c1710b3852e02c5808350a9c8894f95cc7f1e96efb
+size 5304

checkpoint-21364/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/Qwen2.5-7B-Instruct-te-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 sha256:9579e48852f381ff4d0fdf747364b87dff8f846be557b03e94389d0d17139cb2
+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