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-si-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:daa83bcb1cfc807735dd3c2f6b3f912542882c8a5dabed01c8a67a8e4aeafeb4
+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 sha256:46ef773ca5e5fd5c3d39cff69fdd925abd0f05fce0250dd6d3dede53b1227b18
+size 3662865184

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34b8801a70bf88fef22997cb1e697c929928d795ed8c9dd98f27cbeddb2e2e5d
+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 sha256:7c1541118b669b3dde879df2c894efa90883163bc5d9df605d75b8e694ea7ad9
+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": 0.3073785454408118,
+  "eval_steps": 500,
+  "global_step": 12208,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0007805320206966878,
+      "grad_norm": 24.262310028076172,
+      "learning_rate": 1.0157273918741808e-06,
+      "loss": 9.1957,
+      "step": 31
+    },
+    {
+      "epoch": 0.0015610640413933755,
+      "grad_norm": 29.819591522216797,
+      "learning_rate": 2.0314547837483616e-06,
+      "loss": 7.9757,
+      "step": 62
+    },
+    {
+      "epoch": 0.002341596062090063,
+      "grad_norm": 14.961602210998535,
+      "learning_rate": 3.0471821756225426e-06,
+      "loss": 6.5436,
+      "step": 93
+    },
+    {
+      "epoch": 0.003122128082786751,
+      "grad_norm": 5.151533126831055,
+      "learning_rate": 4.062909567496723e-06,
+      "loss": 5.4812,
+      "step": 124
+    },
+    {
+      "epoch": 0.003902660103483439,
+      "grad_norm": 7.370818138122559,
+      "learning_rate": 5.078636959370905e-06,
+      "loss": 4.8332,
+      "step": 155
+    },
+    {
+      "epoch": 0.004683192124180126,
+      "grad_norm": 7.932437896728516,
+      "learning_rate": 6.094364351245085e-06,
+      "loss": 4.4411,
+      "step": 186
+    },
+    {
+      "epoch": 0.005463724144876814,
+      "grad_norm": 7.834314823150635,
+      "learning_rate": 7.110091743119267e-06,
+      "loss": 4.1978,
+      "step": 217
+    },
+    {
+      "epoch": 0.006244256165573502,
+      "grad_norm": 11.881230354309082,
+      "learning_rate": 8.125819134993446e-06,
+      "loss": 3.9897,
+      "step": 248
+    },
+    {
+      "epoch": 0.00702478818627019,
+      "grad_norm": 6.348697185516357,
+      "learning_rate": 9.141546526867629e-06,
+      "loss": 3.8375,
+      "step": 279
+    },
+    {
+      "epoch": 0.007805320206966878,
+      "grad_norm": 8.414978981018066,
+      "learning_rate": 1.015727391874181e-05,
+      "loss": 3.7681,
+      "step": 310
+    },
+    {
+      "epoch": 0.008585852227663565,
+      "grad_norm": 6.531826972961426,
+      "learning_rate": 1.117300131061599e-05,
+      "loss": 3.6599,
+      "step": 341
+    },
+    {
+      "epoch": 0.009366384248360253,
+      "grad_norm": 9.794255256652832,
+      "learning_rate": 1.218872870249017e-05,
+      "loss": 3.5324,
+      "step": 372
+    },
+    {
+      "epoch": 0.01014691626905694,
+      "grad_norm": 8.084766387939453,
+      "learning_rate": 1.3204456094364351e-05,
+      "loss": 3.4696,
+      "step": 403
+    },
+    {
+      "epoch": 0.010927448289753628,
+      "grad_norm": 7.659717559814453,
+      "learning_rate": 1.4220183486238533e-05,
+      "loss": 3.3832,
+      "step": 434
+    },
+    {
+      "epoch": 0.011707980310450316,
+      "grad_norm": 5.131711959838867,
+      "learning_rate": 1.5235910878112714e-05,
+      "loss": 3.3514,
+      "step": 465
+    },
+    {
+      "epoch": 0.012488512331147004,
+      "grad_norm": 6.3673601150512695,
+      "learning_rate": 1.6251638269986893e-05,
+      "loss": 3.2988,
+      "step": 496
+    },
+    {
+      "epoch": 0.013269044351843692,
+      "grad_norm": 4.5014142990112305,
+      "learning_rate": 1.7267365661861077e-05,
+      "loss": 3.239,
+      "step": 527
+    },
+    {
+      "epoch": 0.01404957637254038,
+      "grad_norm": 5.1420769691467285,
+      "learning_rate": 1.8283093053735257e-05,
+      "loss": 3.1892,
+      "step": 558
+    },
+    {
+      "epoch": 0.014830108393237068,
+      "grad_norm": 5.227200508117676,
+      "learning_rate": 1.9298820445609438e-05,
+      "loss": 3.1732,
+      "step": 589
+    },
+    {
+      "epoch": 0.015610640413933756,
+      "grad_norm": 4.4621734619140625,
+      "learning_rate": 2.031454783748362e-05,
+      "loss": 3.0898,
+      "step": 620
+    },
+    {
+      "epoch": 0.016391172434630442,
+      "grad_norm": 5.213263511657715,
+      "learning_rate": 2.13302752293578e-05,
+      "loss": 3.0832,
+      "step": 651
+    },
+    {
+      "epoch": 0.01717170445532713,
+      "grad_norm": 4.23059606552124,
+      "learning_rate": 2.234600262123198e-05,
+      "loss": 3.0341,
+      "step": 682
+    },
+    {
+      "epoch": 0.017952236476023817,
+      "grad_norm": 3.5276854038238525,
+      "learning_rate": 2.336173001310616e-05,
+      "loss": 3.0241,
+      "step": 713
+    },
+    {
+      "epoch": 0.018732768496720505,
+      "grad_norm": 3.199700355529785,
+      "learning_rate": 2.437745740498034e-05,
+      "loss": 2.9659,
+      "step": 744
+    },
+    {
+      "epoch": 0.019513300517417193,
+      "grad_norm": 9.667389869689941,
+      "learning_rate": 2.5393184796854525e-05,
+      "loss": 2.9292,
+      "step": 775
+    },
+    {
+      "epoch": 0.02029383253811388,
+      "grad_norm": 3.677541732788086,
+      "learning_rate": 2.6408912188728702e-05,
+      "loss": 2.919,
+      "step": 806
+    },
+    {
+      "epoch": 0.02107436455881057,
+      "grad_norm": 3.711683750152588,
+      "learning_rate": 2.7424639580602886e-05,
+      "loss": 2.9141,
+      "step": 837
+    },
+    {
+      "epoch": 0.021854896579507257,
+      "grad_norm": 3.1250174045562744,
+      "learning_rate": 2.8440366972477066e-05,
+      "loss": 2.8585,
+      "step": 868
+    },
+    {
+      "epoch": 0.022635428600203945,
+      "grad_norm": 3.4183220863342285,
+      "learning_rate": 2.9456094364351244e-05,
+      "loss": 2.8206,
+      "step": 899
+    },
+    {
+      "epoch": 0.023415960620900633,
+      "grad_norm": 2.8176679611206055,
+      "learning_rate": 3.0471821756225428e-05,
+      "loss": 2.787,
+      "step": 930
+    },
+    {
+      "epoch": 0.02419649264159732,
+      "grad_norm": 2.7993154525756836,
+      "learning_rate": 3.148754914809961e-05,
+      "loss": 2.7678,
+      "step": 961
+    },
+    {
+      "epoch": 0.02497702466229401,
+      "grad_norm": 2.8017027378082275,
+      "learning_rate": 3.2503276539973785e-05,
+      "loss": 2.7499,
+      "step": 992
+    },
+    {
+      "epoch": 0.025757556682990696,
+      "grad_norm": 2.958606004714966,
+      "learning_rate": 3.351900393184797e-05,
+      "loss": 2.7211,
+      "step": 1023
+    },
+    {
+      "epoch": 0.026538088703687384,
+      "grad_norm": 2.5942046642303467,
+      "learning_rate": 3.453473132372215e-05,
+      "loss": 2.6823,
+      "step": 1054
+    },
+    {
+      "epoch": 0.027318620724384072,
+      "grad_norm": 3.1978206634521484,
+      "learning_rate": 3.555045871559633e-05,
+      "loss": 2.6943,
+      "step": 1085
+    },
+    {
+      "epoch": 0.02809915274508076,
+      "grad_norm": 2.6260809898376465,
+      "learning_rate": 3.6566186107470514e-05,
+      "loss": 2.6574,
+      "step": 1116
+    },
+    {
+      "epoch": 0.028879684765777448,
+      "grad_norm": 2.6633715629577637,
+      "learning_rate": 3.7581913499344695e-05,
+      "loss": 2.6394,
+      "step": 1147
+    },
+    {
+      "epoch": 0.029660216786474135,
+      "grad_norm": 2.5701236724853516,
+      "learning_rate": 3.8597640891218876e-05,
+      "loss": 2.6336,
+      "step": 1178
+    },
+    {
+      "epoch": 0.030440748807170823,
+      "grad_norm": 2.4242734909057617,
+      "learning_rate": 3.9613368283093056e-05,
+      "loss": 2.6285,
+      "step": 1209
+    },
+    {
+      "epoch": 0.03122128082786751,
+      "grad_norm": 2.6410114765167236,
+      "learning_rate": 4.062909567496724e-05,
+      "loss": 2.5821,
+      "step": 1240
+    },
+    {
+      "epoch": 0.032001812848564196,
+      "grad_norm": 2.419649839401245,
+      "learning_rate": 4.164482306684142e-05,
+      "loss": 2.5576,
+      "step": 1271
+    },
+    {
+      "epoch": 0.032782344869260883,
+      "grad_norm": 2.314750909805298,
+      "learning_rate": 4.26605504587156e-05,
+      "loss": 2.5438,
+      "step": 1302
+    },
+    {
+      "epoch": 0.03356287688995757,
+      "grad_norm": 2.288361072540283,
+      "learning_rate": 4.367627785058978e-05,
+      "loss": 2.5197,
+      "step": 1333
+    },
+    {
+      "epoch": 0.03434340891065426,
+      "grad_norm": 2.328840494155884,
+      "learning_rate": 4.469200524246396e-05,
+      "loss": 2.5193,
+      "step": 1364
+    },
+    {
+      "epoch": 0.03512394093135095,
+      "grad_norm": 2.2555599212646484,
+      "learning_rate": 4.570773263433814e-05,
+      "loss": 2.4907,
+      "step": 1395
+    },
+    {
+      "epoch": 0.035904472952047635,
+      "grad_norm": 2.1358766555786133,
+      "learning_rate": 4.672346002621232e-05,
+      "loss": 2.4737,
+      "step": 1426
+    },
+    {
+      "epoch": 0.03668500497274432,
+      "grad_norm": 2.1471140384674072,
+      "learning_rate": 4.77391874180865e-05,
+      "loss": 2.4733,
+      "step": 1457
+    },
+    {
+      "epoch": 0.03746553699344101,
+      "grad_norm": 2.1371941566467285,
+      "learning_rate": 4.875491480996068e-05,
+      "loss": 2.432,
+      "step": 1488
+    },
+    {
+      "epoch": 0.0382460690141377,
+      "grad_norm": 1.9789690971374512,
+      "learning_rate": 4.977064220183487e-05,
+      "loss": 2.4407,
+      "step": 1519
+    },
+    {
+      "epoch": 0.039026601034834386,
+      "grad_norm": 2.0055742263793945,
+      "learning_rate": 4.9999915451558777e-05,
+      "loss": 2.4178,
+      "step": 1550
+    },
+    {
+      "epoch": 0.039807133055531074,
+      "grad_norm": 2.095475196838379,
+      "learning_rate": 4.999955597496219e-05,
+      "loss": 2.4198,
+      "step": 1581
+    },
+    {
+      "epoch": 0.04058766507622776,
+      "grad_norm": 2.046337842941284,
+      "learning_rate": 4.9998914381774255e-05,
+      "loss": 2.3936,
+      "step": 1612
+    },
+    {
+      "epoch": 0.04136819709692445,
+      "grad_norm": 1.8528848886489868,
+      "learning_rate": 4.999799067923527e-05,
+      "loss": 2.3893,
+      "step": 1643
+    },
+    {
+      "epoch": 0.04214872911762114,
+      "grad_norm": 1.883175253868103,
+      "learning_rate": 4.999678487776908e-05,
+      "loss": 2.3668,
+      "step": 1674
+    },
+    {
+      "epoch": 0.042929261138317826,
+      "grad_norm": 1.8084770441055298,
+      "learning_rate": 4.9995296990983006e-05,
+      "loss": 2.3702,
+      "step": 1705
+    },
+    {
+      "epoch": 0.043709793159014514,
+      "grad_norm": 1.8336963653564453,
+      "learning_rate": 4.999352703566763e-05,
+      "loss": 2.357,
+      "step": 1736
+    },
+    {
+      "epoch": 0.0444903251797112,
+      "grad_norm": 1.8369375467300415,
+      "learning_rate": 4.999147503179668e-05,
+      "loss": 2.3393,
+      "step": 1767
+    },
+    {
+      "epoch": 0.04527085720040789,
+      "grad_norm": 1.8411383628845215,
+      "learning_rate": 4.998914100252672e-05,
+      "loss": 2.319,
+      "step": 1798
+    },
+    {
+      "epoch": 0.04605138922110458,
+      "grad_norm": 1.785543441772461,
+      "learning_rate": 4.998652497419696e-05,
+      "loss": 2.3259,
+      "step": 1829
+    },
+    {
+      "epoch": 0.046831921241801265,
+      "grad_norm": 1.7194079160690308,
+      "learning_rate": 4.9983626976328927e-05,
+      "loss": 2.3046,
+      "step": 1860
+    },
+    {
+      "epoch": 0.04761245326249795,
+      "grad_norm": 1.7909469604492188,
+      "learning_rate": 4.998044704162613e-05,
+      "loss": 2.307,
+      "step": 1891
+    },
+    {
+      "epoch": 0.04839298528319464,
+      "grad_norm": 1.725806474685669,
+      "learning_rate": 4.9976985205973705e-05,
+      "loss": 2.2992,
+      "step": 1922
+    },
+    {
+      "epoch": 0.04917351730389133,
+      "grad_norm": 1.67300546169281,
+      "learning_rate": 4.997324150843799e-05,
+      "loss": 2.2763,
+      "step": 1953
+    },
+    {
+      "epoch": 0.04995404932458802,
+      "grad_norm": 1.7416061162948608,
+      "learning_rate": 4.99692159912661e-05,
+      "loss": 2.2596,
+      "step": 1984
+    },
+    {
+      "epoch": 0.050734581345284704,
+      "grad_norm": 1.843024492263794,
+      "learning_rate": 4.996490869988546e-05,
+      "loss": 2.2644,
+      "step": 2015
+    },
+    {
+      "epoch": 0.05151511336598139,
+      "grad_norm": 1.6172534227371216,
+      "learning_rate": 4.996031968290326e-05,
+      "loss": 2.271,
+      "step": 2046
+    },
+    {
+      "epoch": 0.05229564538667808,
+      "grad_norm": 1.6510816812515259,
+      "learning_rate": 4.995544899210594e-05,
+      "loss": 2.2445,
+      "step": 2077
+    },
+    {
+      "epoch": 0.05307617740737477,
+      "grad_norm": 1.625775933265686,
+      "learning_rate": 4.9950296682458583e-05,
+      "loss": 2.2432,
+      "step": 2108
+    },
+    {
+      "epoch": 0.053856709428071456,
+      "grad_norm": 1.602299690246582,
+      "learning_rate": 4.994486281210429e-05,
+      "loss": 2.2266,
+      "step": 2139
+    },
+    {
+      "epoch": 0.054637241448768144,
+      "grad_norm": 1.7036757469177246,
+      "learning_rate": 4.9939147442363566e-05,
+      "loss": 2.2292,
+      "step": 2170
+    },
+    {
+      "epoch": 0.05541777346946483,
+      "grad_norm": 1.5851162672042847,
+      "learning_rate": 4.9933150637733574e-05,
+      "loss": 2.2286,
+      "step": 2201
+    },
+    {
+      "epoch": 0.05619830549016152,
+      "grad_norm": 1.6328140497207642,
+      "learning_rate": 4.992687246588743e-05,
+      "loss": 2.2342,
+      "step": 2232
+    },
+    {
+      "epoch": 0.05697883751085821,
+      "grad_norm": 1.4901413917541504,
+      "learning_rate": 4.992031299767347e-05,
+      "loss": 2.2094,
+      "step": 2263
+    },
+    {
+      "epoch": 0.057759369531554895,
+      "grad_norm": 1.5897445678710938,
+      "learning_rate": 4.9913472307114386e-05,
+      "loss": 2.2126,
+      "step": 2294
+    },
+    {
+      "epoch": 0.05853990155225158,
+      "grad_norm": 1.5534899234771729,
+      "learning_rate": 4.9906350471406446e-05,
+      "loss": 2.2125,
+      "step": 2325
+    },
+    {
+      "epoch": 0.05932043357294827,
+      "grad_norm": 1.5713675022125244,
+      "learning_rate": 4.989894757091861e-05,
+      "loss": 2.2007,
+      "step": 2356
+    },
+    {
+      "epoch": 0.06010096559364496,
+      "grad_norm": 1.473955750465393,
+      "learning_rate": 4.989126368919158e-05,
+      "loss": 2.1819,
+      "step": 2387
+    },
+    {
+      "epoch": 0.06088149761434165,
+      "grad_norm": 1.5200265645980835,
+      "learning_rate": 4.988329891293693e-05,
+      "loss": 2.1944,
+      "step": 2418
+    },
+    {
+      "epoch": 0.061662029635038335,
+      "grad_norm": 1.5236589908599854,
+      "learning_rate": 4.987505333203608e-05,
+      "loss": 2.1816,
+      "step": 2449
+    },
+    {
+      "epoch": 0.06244256165573502,
+      "grad_norm": 1.5306485891342163,
+      "learning_rate": 4.9866527039539276e-05,
+      "loss": 2.187,
+      "step": 2480
+    },
+    {
+      "epoch": 0.06322309367643171,
+      "grad_norm": 1.5017462968826294,
+      "learning_rate": 4.9857720131664594e-05,
+      "loss": 2.1706,
+      "step": 2511
+    },
+    {
+      "epoch": 0.06400362569712839,
+      "grad_norm": 4.610604763031006,
+      "learning_rate": 4.9848632707796773e-05,
+      "loss": 2.1528,
+      "step": 2542
+    },
+    {
+      "epoch": 0.06478415771782509,
+      "grad_norm": 1.4580930471420288,
+      "learning_rate": 4.9839264870486155e-05,
+      "loss": 2.1849,
+      "step": 2573
+    },
+    {
+      "epoch": 0.06556468973852177,
+      "grad_norm": 1.5506151914596558,
+      "learning_rate": 4.9829616725447526e-05,
+      "loss": 2.1504,
+      "step": 2604
+    },
+    {
+      "epoch": 0.06634522175921846,
+      "grad_norm": 1.4275034666061401,
+      "learning_rate": 4.981968838155888e-05,
+      "loss": 2.1492,
+      "step": 2635
+    },
+    {
+      "epoch": 0.06712575377991514,
+      "grad_norm": 1.4749577045440674,
+      "learning_rate": 4.980947995086024e-05,
+      "loss": 2.1579,
+      "step": 2666
+    },
+    {
+      "epoch": 0.06790628580061184,
+      "grad_norm": 1.4220107793807983,
+      "learning_rate": 4.979899154855234e-05,
+      "loss": 2.1522,
+      "step": 2697
+    },
+    {
+      "epoch": 0.06868681782130852,
+      "grad_norm": 1.4243831634521484,
+      "learning_rate": 4.9788223292995386e-05,
+      "loss": 2.1258,
+      "step": 2728
+    },
+    {
+      "epoch": 0.06946734984200521,
+      "grad_norm": 1.4925100803375244,
+      "learning_rate": 4.977717530570768e-05,
+      "loss": 2.1379,
+      "step": 2759
+    },
+    {
+      "epoch": 0.0702478818627019,
+      "grad_norm": 1.4839624166488647,
+      "learning_rate": 4.976584771136425e-05,
+      "loss": 2.1588,
+      "step": 2790
+    },
+    {
+      "epoch": 0.07102841388339859,
+      "grad_norm": 1.4130090475082397,
+      "learning_rate": 4.975424063779547e-05,
+      "loss": 2.1461,
+      "step": 2821
+    },
+    {
+      "epoch": 0.07180894590409527,
+      "grad_norm": 1.3940472602844238,
+      "learning_rate": 4.974235421598557e-05,
+      "loss": 2.1416,
+      "step": 2852
+    },
+    {
+      "epoch": 0.07258947792479196,
+      "grad_norm": 1.4502291679382324,
+      "learning_rate": 4.973018858007122e-05,
+      "loss": 2.1315,
+      "step": 2883
+    },
+    {
+      "epoch": 0.07337000994548865,
+      "grad_norm": 1.4334006309509277,
+      "learning_rate": 4.9717743867339963e-05,
+      "loss": 2.122,
+      "step": 2914
+    },
+    {
+      "epoch": 0.07415054196618534,
+      "grad_norm": 1.4366185665130615,
+      "learning_rate": 4.9705020218228695e-05,
+      "loss": 2.1179,
+      "step": 2945
+    },
+    {
+      "epoch": 0.07493107398688202,
+      "grad_norm": 1.437264084815979,
+      "learning_rate": 4.969201777632205e-05,
+      "loss": 2.1171,
+      "step": 2976
+    },
+    {
+      "epoch": 0.07571160600757872,
+      "grad_norm": 1.3713815212249756,
+      "learning_rate": 4.9678736688350846e-05,
+      "loss": 2.1215,
+      "step": 3007
+    },
+    {
+      "epoch": 0.0764921380282754,
+      "grad_norm": 1.5930180549621582,
+      "learning_rate": 4.966517710419033e-05,
+      "loss": 2.0961,
+      "step": 3038
+    },
+    {
+      "epoch": 0.07727267004897209,
+      "grad_norm": 1.4208778142929077,
+      "learning_rate": 4.965133917685858e-05,
+      "loss": 2.1193,
+      "step": 3069
+    },
+    {
+      "epoch": 0.07805320206966877,
+      "grad_norm": 1.3563286066055298,
+      "learning_rate": 4.9637223062514714e-05,
+      "loss": 2.0957,
+      "step": 3100
+    },
+    {
+      "epoch": 0.07883373409036547,
+      "grad_norm": 1.382861852645874,
+      "learning_rate": 4.962282892045718e-05,
+      "loss": 2.117,
+      "step": 3131
+    },
+    {
+      "epoch": 0.07961426611106215,
+      "grad_norm": 1.326231837272644,
+      "learning_rate": 4.9608156913121904e-05,
+      "loss": 2.0906,
+      "step": 3162
+    },
+    {
+      "epoch": 0.08039479813175884,
+      "grad_norm": 1.3465954065322876,
+      "learning_rate": 4.959320720608049e-05,
+      "loss": 2.09,
+      "step": 3193
+    },
+    {
+      "epoch": 0.08117533015245552,
+      "grad_norm": 1.3832777738571167,
+      "learning_rate": 4.9577979968038354e-05,
+      "loss": 2.089,
+      "step": 3224
+    },
+    {
+      "epoch": 0.08195586217315222,
+      "grad_norm": 1.4453243017196655,
+      "learning_rate": 4.956247537083282e-05,
+      "loss": 2.0867,
+      "step": 3255
+    },
+    {
+      "epoch": 0.0827363941938489,
+      "grad_norm": 1.310168743133545,
+      "learning_rate": 4.9546693589431145e-05,
+      "loss": 2.0915,
+      "step": 3286
+    },
+    {
+      "epoch": 0.0835169262145456,
+      "grad_norm": 1.354078769683838,
+      "learning_rate": 4.9530634801928595e-05,
+      "loss": 2.0888,
+      "step": 3317
+    },
+    {
+      "epoch": 0.08429745823524228,
+      "grad_norm": 1.3768595457077026,
+      "learning_rate": 4.9514299189546395e-05,
+      "loss": 2.0821,
+      "step": 3348
+    },
+    {
+      "epoch": 0.08507799025593897,
+      "grad_norm": 1.3402544260025024,
+      "learning_rate": 4.949768693662973e-05,
+      "loss": 2.0776,
+      "step": 3379
+    },
+    {
+      "epoch": 0.08585852227663565,
+      "grad_norm": 1.3178027868270874,
+      "learning_rate": 4.948079823064559e-05,
+      "loss": 2.0699,
+      "step": 3410
+    },
+    {
+      "epoch": 0.08663905429733235,
+      "grad_norm": 1.7057585716247559,
+      "learning_rate": 4.946363326218074e-05,
+      "loss": 2.0615,
+      "step": 3441
+    },
+    {
+      "epoch": 0.08741958631802903,
+      "grad_norm": 1.3453648090362549,
+      "learning_rate": 4.9446192224939525e-05,
+      "loss": 2.0788,
+      "step": 3472
+    },
+    {
+      "epoch": 0.08820011833872572,
+      "grad_norm": 1.3319638967514038,
+      "learning_rate": 4.942847531574167e-05,
+      "loss": 2.0619,
+      "step": 3503
+    },
+    {
+      "epoch": 0.0889806503594224,
+      "grad_norm": 1.2845163345336914,
+      "learning_rate": 4.941048273452008e-05,
+      "loss": 2.0728,
+      "step": 3534
+    },
+    {
+      "epoch": 0.0897611823801191,
+      "grad_norm": 1.3615431785583496,
+      "learning_rate": 4.9392214684318605e-05,
+      "loss": 2.0538,
+      "step": 3565
+    },
+    {
+      "epoch": 0.09054171440081578,
+      "grad_norm": 1.2946122884750366,
+      "learning_rate": 4.93736713712897e-05,
+      "loss": 2.0689,
+      "step": 3596
+    },
+    {
+      "epoch": 0.09132224642151247,
+      "grad_norm": 1.294846534729004,
+      "learning_rate": 4.9354853004692124e-05,
+      "loss": 2.0706,
+      "step": 3627
+    },
+    {
+      "epoch": 0.09210277844220915,
+      "grad_norm": 1.298010230064392,
+      "learning_rate": 4.93357597968886e-05,
+      "loss": 2.0406,
+      "step": 3658
+    },
+    {
+      "epoch": 0.09288331046290585,
+      "grad_norm": 1.7569706439971924,
+      "learning_rate": 4.931639196334338e-05,
+      "loss": 2.0736,
+      "step": 3689
+    },
+    {
+      "epoch": 0.09366384248360253,
+      "grad_norm": 1.2595418691635132,
+      "learning_rate": 4.9296749722619826e-05,
+      "loss": 2.0654,
+      "step": 3720
+    },
+    {
+      "epoch": 0.09444437450429922,
+      "grad_norm": 1.3139164447784424,
+      "learning_rate": 4.9276833296377966e-05,
+      "loss": 2.0467,
+      "step": 3751
+    },
+    {
+      "epoch": 0.0952249065249959,
+      "grad_norm": 1.290247917175293,
+      "learning_rate": 4.925664290937196e-05,
+      "loss": 2.0418,
+      "step": 3782
+    },
+    {
+      "epoch": 0.0960054385456926,
+      "grad_norm": 1.2755826711654663,
+      "learning_rate": 4.9236178789447576e-05,
+      "loss": 2.0244,
+      "step": 3813
+    },
+    {
+      "epoch": 0.09678597056638928,
+      "grad_norm": 1.2596077919006348,
+      "learning_rate": 4.921544116753962e-05,
+      "loss": 2.0609,
+      "step": 3844
+    },
+    {
+      "epoch": 0.09756650258708598,
+      "grad_norm": 1.249387264251709,
+      "learning_rate": 4.919443027766935e-05,
+      "loss": 2.0455,
+      "step": 3875
+    },
+    {
+      "epoch": 0.09834703460778266,
+      "grad_norm": 1.255379319190979,
+      "learning_rate": 4.91731463569418e-05,
+      "loss": 2.024,
+      "step": 3906
+    },
+    {
+      "epoch": 0.09912756662847935,
+      "grad_norm": 1.2620748281478882,
+      "learning_rate": 4.915158964554312e-05,
+      "loss": 2.0355,
+      "step": 3937
+    },
+    {
+      "epoch": 0.09990809864917603,
+      "grad_norm": 1.2736345529556274,
+      "learning_rate": 4.912976038673786e-05,
+      "loss": 2.0351,
+      "step": 3968
+    },
+    {
+      "epoch": 0.10068863066987273,
+      "grad_norm": 1.18524169921875,
+      "learning_rate": 4.9107658826866254e-05,
+      "loss": 2.029,
+      "step": 3999
+    },
+    {
+      "epoch": 0.10146916269056941,
+      "grad_norm": 10.429583549499512,
+      "learning_rate": 4.908528521534139e-05,
+      "loss": 2.0226,
+      "step": 4030
+    },
+    {
+      "epoch": 0.1022496947112661,
+      "grad_norm": 1.240295648574829,
+      "learning_rate": 4.906263980464644e-05,
+      "loss": 2.0401,
+      "step": 4061
+    },
+    {
+      "epoch": 0.10303022673196278,
+      "grad_norm": 1.2191627025604248,
+      "learning_rate": 4.903972285033178e-05,
+      "loss": 2.0079,
+      "step": 4092
+    },
+    {
+      "epoch": 0.10381075875265948,
+      "grad_norm": 1.2340337038040161,
+      "learning_rate": 4.901653461101213e-05,
+      "loss": 2.0305,
+      "step": 4123
+    },
+    {
+      "epoch": 0.10459129077335616,
+      "grad_norm": 1.284839153289795,
+      "learning_rate": 4.8993075348363626e-05,
+      "loss": 2.0212,
+      "step": 4154
+    },
+    {
+      "epoch": 0.10537182279405286,
+      "grad_norm": 1.2955284118652344,
+      "learning_rate": 4.896934532712084e-05,
+      "loss": 2.0328,
+      "step": 4185
+    },
+    {
+      "epoch": 0.10615235481474954,
+      "grad_norm": 1.165124535560608,
+      "learning_rate": 4.8945344815073846e-05,
+      "loss": 2.0248,
+      "step": 4216
+    },
+    {
+      "epoch": 0.10693288683544623,
+      "grad_norm": 1.1925835609436035,
+      "learning_rate": 4.892107408306516e-05,
+      "loss": 2.0086,
+      "step": 4247
+    },
+    {
+      "epoch": 0.10771341885614291,
+      "grad_norm": 1.1841633319854736,
+      "learning_rate": 4.889653340498669e-05,
+      "loss": 2.0166,
+      "step": 4278
+    },
+    {
+      "epoch": 0.1084939508768396,
+      "grad_norm": 1.2198415994644165,
+      "learning_rate": 4.8871723057776664e-05,
+      "loss": 2.0164,
+      "step": 4309
+    },
+    {
+      "epoch": 0.10927448289753629,
+      "grad_norm": 1.2284913063049316,
+      "learning_rate": 4.8846643321416476e-05,
+      "loss": 2.015,
+      "step": 4340
+    },
+    {
+      "epoch": 0.11005501491823298,
+      "grad_norm": 1.2090349197387695,
+      "learning_rate": 4.882129447892753e-05,
+      "loss": 2.0094,
+      "step": 4371
+    },
+    {
+      "epoch": 0.11083554693892966,
+      "grad_norm": 1.215232491493225,
+      "learning_rate": 4.8795676816368076e-05,
+      "loss": 2.0045,
+      "step": 4402
+    },
+    {
+      "epoch": 0.11161607895962636,
+      "grad_norm": 1.2804045677185059,
+      "learning_rate": 4.876979062282995e-05,
+      "loss": 1.9899,
+      "step": 4433
+    },
+    {
+      "epoch": 0.11239661098032304,
+      "grad_norm": 1.2405016422271729,
+      "learning_rate": 4.8743636190435325e-05,
+      "loss": 2.0093,
+      "step": 4464
+    },
+    {
+      "epoch": 0.11317714300101973,
+      "grad_norm": 1.1784151792526245,
+      "learning_rate": 4.871721381433344e-05,
+      "loss": 2.0036,
+      "step": 4495
+    },
+    {
+      "epoch": 0.11395767502171641,
+      "grad_norm": 1.185738205909729,
+      "learning_rate": 4.869052379269719e-05,
+      "loss": 2.0033,
+      "step": 4526
+    },
+    {
+      "epoch": 0.11473820704241311,
+      "grad_norm": 1.1984614133834839,
+      "learning_rate": 4.866356642671985e-05,
+      "loss": 2.025,
+      "step": 4557
+    },
+    {
+      "epoch": 0.11551873906310979,
+      "grad_norm": 1.1734029054641724,
+      "learning_rate": 4.8636342020611634e-05,
+      "loss": 2.0023,
+      "step": 4588
+    },
+    {
+      "epoch": 0.11629927108380649,
+      "grad_norm": 1.198611855506897,
+      "learning_rate": 4.860885088159626e-05,
+      "loss": 2.0031,
+      "step": 4619
+    },
+    {
+      "epoch": 0.11707980310450317,
+      "grad_norm": 1.1793649196624756,
+      "learning_rate": 4.858109331990751e-05,
+      "loss": 1.9806,
+      "step": 4650
+    },
+    {
+      "epoch": 0.11786033512519985,
+      "grad_norm": 1.1945818662643433,
+      "learning_rate": 4.855306964878567e-05,
+      "loss": 1.9855,
+      "step": 4681
+    },
+    {
+      "epoch": 0.11864086714589654,
+      "grad_norm": 1.1875253915786743,
+      "learning_rate": 4.8524780184474084e-05,
+      "loss": 1.9883,
+      "step": 4712
+    },
+    {
+      "epoch": 0.11942139916659322,
+      "grad_norm": 1.1512328386306763,
+      "learning_rate": 4.8496225246215496e-05,
+      "loss": 1.9807,
+      "step": 4743
+    },
+    {
+      "epoch": 0.12020193118728992,
+      "grad_norm": 1.2059484720230103,
+      "learning_rate": 4.8467405156248505e-05,
+      "loss": 2.0103,
+      "step": 4774
+    },
+    {
+      "epoch": 0.1209824632079866,
+      "grad_norm": 1.1759779453277588,
+      "learning_rate": 4.843832023980392e-05,
+      "loss": 1.9754,
+      "step": 4805
+    },
+    {
+      "epoch": 0.1217629952286833,
+      "grad_norm": 1.2004414796829224,
+      "learning_rate": 4.840897082510106e-05,
+      "loss": 1.9893,
+      "step": 4836
+    },
+    {
+      "epoch": 0.12254352724937997,
+      "grad_norm": 1.1744251251220703,
+      "learning_rate": 4.8379357243344084e-05,
+      "loss": 1.9848,
+      "step": 4867
+    },
+    {
+      "epoch": 0.12332405927007667,
+      "grad_norm": 1.1731071472167969,
+      "learning_rate": 4.8349479828718236e-05,
+      "loss": 1.9945,
+      "step": 4898
+    },
+    {
+      "epoch": 0.12410459129077335,
+      "grad_norm": 1.2002074718475342,
+      "learning_rate": 4.8319338918386075e-05,
+      "loss": 1.9869,
+      "step": 4929
+    },
+    {
+      "epoch": 0.12488512331147004,
+      "grad_norm": 1.147085189819336,
+      "learning_rate": 4.828893485248369e-05,
+      "loss": 1.9876,
+      "step": 4960
+    },
+    {
+      "epoch": 0.12566565533216673,
+      "grad_norm": 1.1605637073516846,
+      "learning_rate": 4.825826797411682e-05,
+      "loss": 1.9858,
+      "step": 4991
+    },
+    {
+      "epoch": 0.12644618735286342,
+      "grad_norm": 1.1823869943618774,
+      "learning_rate": 4.822733862935702e-05,
+      "loss": 1.9617,
+      "step": 5022
+    },
+    {
+      "epoch": 0.12722671937356012,
+      "grad_norm": 1.1143817901611328,
+      "learning_rate": 4.819614716723775e-05,
+      "loss": 1.9756,
+      "step": 5053
+    },
+    {
+      "epoch": 0.12800725139425678,
+      "grad_norm": 1.1646877527236938,
+      "learning_rate": 4.8164693939750425e-05,
+      "loss": 2.0005,
+      "step": 5084
+    },
+    {
+      "epoch": 0.12878778341495348,
+      "grad_norm": 1.1390529870986938,
+      "learning_rate": 4.813297930184042e-05,
+      "loss": 1.9943,
+      "step": 5115
+    },
+    {
+      "epoch": 0.12956831543565017,
+      "grad_norm": 1.1759583950042725,
+      "learning_rate": 4.810100361140314e-05,
+      "loss": 1.9772,
+      "step": 5146
+    },
+    {
+      "epoch": 0.13034884745634687,
+      "grad_norm": 1.1465727090835571,
+      "learning_rate": 4.8068767229279885e-05,
+      "loss": 1.9563,
+      "step": 5177
+    },
+    {
+      "epoch": 0.13112937947704353,
+      "grad_norm": 1.2573471069335938,
+      "learning_rate": 4.8036270519253854e-05,
+      "loss": 1.9735,
+      "step": 5208
+    },
+    {
+      "epoch": 0.13190991149774023,
+      "grad_norm": 1.1301871538162231,
+      "learning_rate": 4.8003513848046e-05,
+      "loss": 1.987,
+      "step": 5239
+    },
+    {
+      "epoch": 0.13269044351843692,
+      "grad_norm": 1.1424096822738647,
+      "learning_rate": 4.79704975853109e-05,
+      "loss": 1.9661,
+      "step": 5270
+    },
+    {
+      "epoch": 0.13347097553913362,
+      "grad_norm": 1.131800889968872,
+      "learning_rate": 4.793722210363262e-05,
+      "loss": 1.9828,
+      "step": 5301
+    },
+    {
+      "epoch": 0.13425150755983029,
+      "grad_norm": 1.1227242946624756,
+      "learning_rate": 4.7903687778520414e-05,
+      "loss": 1.975,
+      "step": 5332
+    },
+    {
+      "epoch": 0.13503203958052698,
+      "grad_norm": 1.143832802772522,
+      "learning_rate": 4.7869894988404593e-05,
+      "loss": 1.9619,
+      "step": 5363
+    },
+    {
+      "epoch": 0.13581257160122367,
+      "grad_norm": 1.1281683444976807,
+      "learning_rate": 4.783584411463221e-05,
+      "loss": 1.9603,
+      "step": 5394
+    },
+    {
+      "epoch": 0.13659310362192037,
+      "grad_norm": 1.134901762008667,
+      "learning_rate": 4.780153554146274e-05,
+      "loss": 1.9888,
+      "step": 5425
+    },
+    {
+      "epoch": 0.13737363564261704,
+      "grad_norm": 1.1317532062530518,
+      "learning_rate": 4.7766969656063766e-05,
+      "loss": 1.9793,
+      "step": 5456
+    },
+    {
+      "epoch": 0.13815416766331373,
+      "grad_norm": 1.2516345977783203,
+      "learning_rate": 4.773214684850662e-05,
+      "loss": 1.9839,
+      "step": 5487
+    },
+    {
+      "epoch": 0.13893469968401043,
+      "grad_norm": 1.107391119003296,
+      "learning_rate": 4.769706751176193e-05,
+      "loss": 1.9606,
+      "step": 5518
+    },
+    {
+      "epoch": 0.13971523170470712,
+      "grad_norm": 1.1041492223739624,
+      "learning_rate": 4.7661732041695264e-05,
+      "loss": 1.9688,
+      "step": 5549
+    },
+    {
+      "epoch": 0.1404957637254038,
+      "grad_norm": 1.1099929809570312,
+      "learning_rate": 4.762614083706258e-05,
+      "loss": 1.9821,
+      "step": 5580
+    },
+    {
+      "epoch": 0.14127629574610048,
+      "grad_norm": 1.167151927947998,
+      "learning_rate": 4.759029429950581e-05,
+      "loss": 1.9669,
+      "step": 5611
+    },
+    {
+      "epoch": 0.14205682776679718,
+      "grad_norm": 1.0942577123641968,
+      "learning_rate": 4.7554192833548235e-05,
+      "loss": 1.9565,
+      "step": 5642
+    },
+    {
+      "epoch": 0.14283735978749387,
+      "grad_norm": 1.0859640836715698,
+      "learning_rate": 4.751783684659e-05,
+      "loss": 1.9634,
+      "step": 5673
+    },
+    {
+      "epoch": 0.14361789180819054,
+      "grad_norm": 2.420607089996338,
+      "learning_rate": 4.748122674890348e-05,
+      "loss": 1.9365,
+      "step": 5704
+    },
+    {
+      "epoch": 0.14439842382888723,
+      "grad_norm": 1.0996880531311035,
+      "learning_rate": 4.7444362953628654e-05,
+      "loss": 1.9718,
+      "step": 5735
+    },
+    {
+      "epoch": 0.14517895584958393,
+      "grad_norm": 1.1183338165283203,
+      "learning_rate": 4.7407245876768424e-05,
+      "loss": 1.9564,
+      "step": 5766
+    },
+    {
+      "epoch": 0.14595948787028062,
+      "grad_norm": 1.1093947887420654,
+      "learning_rate": 4.736987593718397e-05,
+      "loss": 1.9516,
+      "step": 5797
+    },
+    {
+      "epoch": 0.1467400198909773,
+      "grad_norm": 1.141797423362732,
+      "learning_rate": 4.733225355658999e-05,
+      "loss": 1.929,
+      "step": 5828
+    },
+    {
+      "epoch": 0.14752055191167399,
+      "grad_norm": 1.1214358806610107,
+      "learning_rate": 4.7294379159549926e-05,
+      "loss": 1.9297,
+      "step": 5859
+    },
+    {
+      "epoch": 0.14830108393237068,
+      "grad_norm": 1.1025431156158447,
+      "learning_rate": 4.725625317347119e-05,
+      "loss": 1.9226,
+      "step": 5890
+    },
+    {
+      "epoch": 0.14908161595306738,
+      "grad_norm": 1.1094226837158203,
+      "learning_rate": 4.7217876028600374e-05,
+      "loss": 1.946,
+      "step": 5921
+    },
+    {
+      "epoch": 0.14986214797376404,
+      "grad_norm": 1.0909287929534912,
+      "learning_rate": 4.717924815801832e-05,
+      "loss": 1.9511,
+      "step": 5952
+    },
+    {
+      "epoch": 0.15064267999446074,
+      "grad_norm": 1.0755189657211304,
+      "learning_rate": 4.714036999763532e-05,
+      "loss": 1.939,
+      "step": 5983
+    },
+    {
+      "epoch": 0.15142321201515743,
+      "grad_norm": 1.1426901817321777,
+      "learning_rate": 4.7101241986186116e-05,
+      "loss": 1.93,
+      "step": 6014
+    },
+    {
+      "epoch": 0.15220374403585413,
+      "grad_norm": 1.1208311319351196,
+      "learning_rate": 4.7061864565225e-05,
+      "loss": 1.9516,
+      "step": 6045
+    },
+    {
+      "epoch": 0.1529842760565508,
+      "grad_norm": 1.0931717157363892,
+      "learning_rate": 4.702223817912081e-05,
+      "loss": 1.9314,
+      "step": 6076
+    },
+    {
+      "epoch": 0.1537648080772475,
+      "grad_norm": 1.075864553451538,
+      "learning_rate": 4.698236327505195e-05,
+      "loss": 1.935,
+      "step": 6107
+    },
+    {
+      "epoch": 0.15454534009794418,
+      "grad_norm": 1.090559720993042,
+      "learning_rate": 4.694224030300127e-05,
+      "loss": 1.9431,
+      "step": 6138
+    },
+    {
+      "epoch": 0.15532587211864088,
+      "grad_norm": 1.0956670045852661,
+      "learning_rate": 4.690186971575107e-05,
+      "loss": 1.9678,
+      "step": 6169
+    },
+    {
+      "epoch": 0.15610640413933755,
+      "grad_norm": 1.125927448272705,
+      "learning_rate": 4.6861251968877916e-05,
+      "loss": 1.9292,
+      "step": 6200
+    },
+    {
+      "epoch": 0.15688693616003424,
+      "grad_norm": 1.0844208002090454,
+      "learning_rate": 4.68203875207476e-05,
+      "loss": 1.9189,
+      "step": 6231
+    },
+    {
+      "epoch": 0.15766746818073094,
+      "grad_norm": 1.064327597618103,
+      "learning_rate": 4.677927683250983e-05,
+      "loss": 1.928,
+      "step": 6262
+    },
+    {
+      "epoch": 0.15844800020142763,
+      "grad_norm": 1.1281861066818237,
+      "learning_rate": 4.6737920368093156e-05,
+      "loss": 1.9437,
+      "step": 6293
+    },
+    {
+      "epoch": 0.1592285322221243,
+      "grad_norm": 1.0674384832382202,
+      "learning_rate": 4.669631859419965e-05,
+      "loss": 1.9347,
+      "step": 6324
+    },
+    {
+      "epoch": 0.160009064242821,
+      "grad_norm": 1.105566382408142,
+      "learning_rate": 4.6654471980299676e-05,
+      "loss": 1.9229,
+      "step": 6355
+    },
+    {
+      "epoch": 0.1607895962635177,
+      "grad_norm": 1.0582126379013062,
+      "learning_rate": 4.661238099862658e-05,
+      "loss": 1.9321,
+      "step": 6386
+    },
+    {
+      "epoch": 0.16157012828421438,
+      "grad_norm": 1.1147974729537964,
+      "learning_rate": 4.657004612417138e-05,
+      "loss": 1.9289,
+      "step": 6417
+    },
+    {
+      "epoch": 0.16235066030491105,
+      "grad_norm": 1.0804343223571777,
+      "learning_rate": 4.6527467834677374e-05,
+      "loss": 1.9307,
+      "step": 6448
+    },
+    {
+      "epoch": 0.16313119232560774,
+      "grad_norm": 1.0830508470535278,
+      "learning_rate": 4.648464661063478e-05,
+      "loss": 1.9408,
+      "step": 6479
+    },
+    {
+      "epoch": 0.16391172434630444,
+      "grad_norm": 1.0533562898635864,
+      "learning_rate": 4.6441582935275264e-05,
+      "loss": 1.9347,
+      "step": 6510
+    },
+    {
+      "epoch": 0.16469225636700113,
+      "grad_norm": 1.044925332069397,
+      "learning_rate": 4.6398277294566586e-05,
+      "loss": 1.9112,
+      "step": 6541
+    },
+    {
+      "epoch": 0.1654727883876978,
+      "grad_norm": 1.087296962738037,
+      "learning_rate": 4.6354730177207e-05,
+      "loss": 1.9381,
+      "step": 6572
+    },
+    {
+      "epoch": 0.1662533204083945,
+      "grad_norm": 1.0853668451309204,
+      "learning_rate": 4.6310942074619787e-05,
+      "loss": 1.9224,
+      "step": 6603
+    },
+    {
+      "epoch": 0.1670338524290912,
+      "grad_norm": 1.0661752223968506,
+      "learning_rate": 4.626691348094777e-05,
+      "loss": 1.9386,
+      "step": 6634
+    },
+    {
+      "epoch": 0.16781438444978788,
+      "grad_norm": 1.0393208265304565,
+      "learning_rate": 4.622264489304762e-05,
+      "loss": 1.9266,
+      "step": 6665
+    },
+    {
+      "epoch": 0.16859491647048455,
+      "grad_norm": 1.0324763059616089,
+      "learning_rate": 4.617813681048434e-05,
+      "loss": 1.919,
+      "step": 6696
+    },
+    {
+      "epoch": 0.16937544849118125,
+      "grad_norm": 1.0684878826141357,
+      "learning_rate": 4.61333897355256e-05,
+      "loss": 1.9321,
+      "step": 6727
+    },
+    {
+      "epoch": 0.17015598051187794,
+      "grad_norm": 1.0477505922317505,
+      "learning_rate": 4.608840417313604e-05,
+      "loss": 1.9449,
+      "step": 6758
+    },
+    {
+      "epoch": 0.17093651253257464,
+      "grad_norm": 1.0684869289398193,
+      "learning_rate": 4.6043180630971646e-05,
+      "loss": 1.9252,
+      "step": 6789
+    },
+    {
+      "epoch": 0.1717170445532713,
+      "grad_norm": 1.0869554281234741,
+      "learning_rate": 4.599771961937391e-05,
+      "loss": 1.9183,
+      "step": 6820
+    },
+    {
+      "epoch": 0.172497576573968,
+      "grad_norm": 1.0297125577926636,
+      "learning_rate": 4.5952021651364204e-05,
+      "loss": 1.9123,
+      "step": 6851
+    },
+    {
+      "epoch": 0.1732781085946647,
+      "grad_norm": 1.0670006275177002,
+      "learning_rate": 4.590608724263786e-05,
+      "loss": 1.9353,
+      "step": 6882
+    },
+    {
+      "epoch": 0.1740586406153614,
+      "grad_norm": 1.0744417905807495,
+      "learning_rate": 4.585991691155845e-05,
+      "loss": 1.8979,
+      "step": 6913
+    },
+    {
+      "epoch": 0.17483917263605805,
+      "grad_norm": 1.0910695791244507,
+      "learning_rate": 4.581351117915188e-05,
+      "loss": 1.9153,
+      "step": 6944
+    },
+    {
+      "epoch": 0.17561970465675475,
+      "grad_norm": 1.083776593208313,
+      "learning_rate": 4.5766870569100534e-05,
+      "loss": 1.9026,
+      "step": 6975
+    },
+    {
+      "epoch": 0.17640023667745144,
+      "grad_norm": 1.0857270956039429,
+      "learning_rate": 4.571999560773736e-05,
+      "loss": 1.9279,
+      "step": 7006
+    },
+    {
+      "epoch": 0.1771807686981481,
+      "grad_norm": 1.0350106954574585,
+      "learning_rate": 4.5672886824039915e-05,
+      "loss": 1.9236,
+      "step": 7037
+    },
+    {
+      "epoch": 0.1779613007188448,
+      "grad_norm": 1.0498634576797485,
+      "learning_rate": 4.5625544749624435e-05,
+      "loss": 1.8934,
+      "step": 7068
+    },
+    {
+      "epoch": 0.1787418327395415,
+      "grad_norm": 1.0836471319198608,
+      "learning_rate": 4.5577969918739794e-05,
+      "loss": 1.9131,
+      "step": 7099
+    },
+    {
+      "epoch": 0.1795223647602382,
+      "grad_norm": 1.0414760112762451,
+      "learning_rate": 4.5530162868261486e-05,
+      "loss": 1.8792,
+      "step": 7130
+    },
+    {
+      "epoch": 0.18030289678093486,
+      "grad_norm": 1.0747581720352173,
+      "learning_rate": 4.548212413768558e-05,
+      "loss": 1.8973,
+      "step": 7161
+    },
+    {
+      "epoch": 0.18108342880163156,
+      "grad_norm": 1.0464451313018799,
+      "learning_rate": 4.543385426912261e-05,
+      "loss": 1.907,
+      "step": 7192
+    },
+    {
+      "epoch": 0.18186396082232825,
+      "grad_norm": 1.0159403085708618,
+      "learning_rate": 4.53853538072915e-05,
+      "loss": 1.9111,
+      "step": 7223
+    },
+    {
+      "epoch": 0.18264449284302495,
+      "grad_norm": 1.093883991241455,
+      "learning_rate": 4.533662329951336e-05,
+      "loss": 1.8927,
+      "step": 7254
+    },
+    {
+      "epoch": 0.18342502486372161,
+      "grad_norm": 1.0358048677444458,
+      "learning_rate": 4.528766329570536e-05,
+      "loss": 1.9164,
+      "step": 7285
+    },
+    {
+      "epoch": 0.1842055568844183,
+      "grad_norm": 1.051798939704895,
+      "learning_rate": 4.523847434837447e-05,
+      "loss": 1.9084,
+      "step": 7316
+    },
+    {
+      "epoch": 0.184986088905115,
+      "grad_norm": 1.0729514360427856,
+      "learning_rate": 4.518905701261128e-05,
+      "loss": 1.9089,
+      "step": 7347
+    },
+    {
+      "epoch": 0.1857666209258117,
+      "grad_norm": 1.0399775505065918,
+      "learning_rate": 4.5139411846083715e-05,
+      "loss": 1.922,
+      "step": 7378
+    },
+    {
+      "epoch": 0.18654715294650837,
+      "grad_norm": 1.0500715970993042,
+      "learning_rate": 4.508953940903073e-05,
+      "loss": 1.9118,
+      "step": 7409
+    },
+    {
+      "epoch": 0.18732768496720506,
+      "grad_norm": 1.0770058631896973,
+      "learning_rate": 4.5039440264255994e-05,
+      "loss": 1.9059,
+      "step": 7440
+    },
+    {
+      "epoch": 0.18810821698790176,
+      "grad_norm": 1.0471183061599731,
+      "learning_rate": 4.498911497712155e-05,
+      "loss": 1.9119,
+      "step": 7471
+    },
+    {
+      "epoch": 0.18888874900859845,
+      "grad_norm": 1.038761019706726,
+      "learning_rate": 4.493856411554142e-05,
+      "loss": 1.8798,
+      "step": 7502
+    },
+    {
+      "epoch": 0.18966928102929512,
+      "grad_norm": 1.0365252494812012,
+      "learning_rate": 4.4887788249975206e-05,
+      "loss": 1.8983,
+      "step": 7533
+    },
+    {
+      "epoch": 0.1904498130499918,
+      "grad_norm": 1.1033800840377808,
+      "learning_rate": 4.4836787953421656e-05,
+      "loss": 1.8911,
+      "step": 7564
+    },
+    {
+      "epoch": 0.1912303450706885,
+      "grad_norm": 1.064213514328003,
+      "learning_rate": 4.478556380141218e-05,
+      "loss": 1.8995,
+      "step": 7595
+    },
+    {
+      "epoch": 0.1920108770913852,
+      "grad_norm": 0.997905969619751,
+      "learning_rate": 4.4734116372004375e-05,
+      "loss": 1.8705,
+      "step": 7626
+    },
+    {
+      "epoch": 0.19279140911208187,
+      "grad_norm": 1.0392402410507202,
+      "learning_rate": 4.4682446245775477e-05,
+      "loss": 1.9105,
+      "step": 7657
+    },
+    {
+      "epoch": 0.19357194113277856,
+      "grad_norm": 1.0340332984924316,
+      "learning_rate": 4.463055400581586e-05,
+      "loss": 1.9074,
+      "step": 7688
+    },
+    {
+      "epoch": 0.19435247315347526,
+      "grad_norm": 1.0196648836135864,
+      "learning_rate": 4.4578440237722374e-05,
+      "loss": 1.9059,
+      "step": 7719
+    },
+    {
+      "epoch": 0.19513300517417195,
+      "grad_norm": 0.99578458070755,
+      "learning_rate": 4.452610552959183e-05,
+      "loss": 1.8974,
+      "step": 7750
+    },
+    {
+      "epoch": 0.19591353719486862,
+      "grad_norm": 1.026090145111084,
+      "learning_rate": 4.447355047201428e-05,
+      "loss": 1.8886,
+      "step": 7781
+    },
+    {
+      "epoch": 0.19669406921556531,
+      "grad_norm": 0.9945096969604492,
+      "learning_rate": 4.4420775658066414e-05,
+      "loss": 1.8879,
+      "step": 7812
+    },
+    {
+      "epoch": 0.197474601236262,
+      "grad_norm": 1.0226850509643555,
+      "learning_rate": 4.436778168330484e-05,
+      "loss": 1.8936,
+      "step": 7843
+    },
+    {
+      "epoch": 0.1982551332569587,
+      "grad_norm": 1.0433967113494873,
+      "learning_rate": 4.4314569145759353e-05,
+      "loss": 1.882,
+      "step": 7874
+    },
+    {
+      "epoch": 0.19903566527765537,
+      "grad_norm": 1.0612221956253052,
+      "learning_rate": 4.42611386459262e-05,
+      "loss": 1.8879,
+      "step": 7905
+    },
+    {
+      "epoch": 0.19981619729835207,
+      "grad_norm": 1.0252665281295776,
+      "learning_rate": 4.420749078676133e-05,
+      "loss": 1.9005,
+      "step": 7936
+    },
+    {
+      "epoch": 0.20059672931904876,
+      "grad_norm": 1.015100359916687,
+      "learning_rate": 4.4153626173673516e-05,
+      "loss": 1.8944,
+      "step": 7967
+    },
+    {
+      "epoch": 0.20137726133974546,
+      "grad_norm": 1.0417771339416504,
+      "learning_rate": 4.409954541451762e-05,
+      "loss": 1.8837,
+      "step": 7998
+    },
+    {
+      "epoch": 0.20215779336044212,
+      "grad_norm": 1.026708960533142,
+      "learning_rate": 4.404524911958764e-05,
+      "loss": 1.92,
+      "step": 8029
+    },
+    {
+      "epoch": 0.20293832538113882,
+      "grad_norm": 1.0414159297943115,
+      "learning_rate": 4.399073790160989e-05,
+      "loss": 1.8709,
+      "step": 8060
+    },
+    {
+      "epoch": 0.2037188574018355,
+      "grad_norm": 1.014039397239685,
+      "learning_rate": 4.393601237573607e-05,
+      "loss": 1.8842,
+      "step": 8091
+    },
+    {
+      "epoch": 0.2044993894225322,
+      "grad_norm": 1.0103037357330322,
+      "learning_rate": 4.388107315953628e-05,
+      "loss": 1.8889,
+      "step": 8122
+    },
+    {
+      "epoch": 0.20527992144322887,
+      "grad_norm": 1.0166395902633667,
+      "learning_rate": 4.382592087299212e-05,
+      "loss": 1.8808,
+      "step": 8153
+    },
+    {
+      "epoch": 0.20606045346392557,
+      "grad_norm": 1.023850679397583,
+      "learning_rate": 4.377055613848964e-05,
+      "loss": 1.8918,
+      "step": 8184
+    },
+    {
+      "epoch": 0.20684098548462226,
+      "grad_norm": 1.0251572132110596,
+      "learning_rate": 4.3714979580812355e-05,
+      "loss": 1.882,
+      "step": 8215
+    },
+    {
+      "epoch": 0.20762151750531896,
+      "grad_norm": 1.0183281898498535,
+      "learning_rate": 4.365919182713416e-05,
+      "loss": 1.8844,
+      "step": 8246
+    },
+    {
+      "epoch": 0.20840204952601563,
+      "grad_norm": 1.0135486125946045,
+      "learning_rate": 4.360319350701226e-05,
+      "loss": 1.8814,
+      "step": 8277
+    },
+    {
+      "epoch": 0.20918258154671232,
+      "grad_norm": 1.0247812271118164,
+      "learning_rate": 4.3546985252380115e-05,
+      "loss": 1.8818,
+      "step": 8308
+    },
+    {
+      "epoch": 0.20996311356740902,
+      "grad_norm": 1.0123242139816284,
+      "learning_rate": 4.349056769754021e-05,
+      "loss": 1.8723,
+      "step": 8339
+    },
+    {
+      "epoch": 0.2107436455881057,
+      "grad_norm": 1.0139250755310059,
+      "learning_rate": 4.3433941479156994e-05,
+      "loss": 1.8858,
+      "step": 8370
+    },
+    {
+      "epoch": 0.21152417760880238,
+      "grad_norm": 4.008477687835693,
+      "learning_rate": 4.3377107236249647e-05,
+      "loss": 1.8735,
+      "step": 8401
+    },
+    {
+      "epoch": 0.21230470962949907,
+      "grad_norm": 1.0454871654510498,
+      "learning_rate": 4.332006561018488e-05,
+      "loss": 1.8824,
+      "step": 8432
+    },
+    {
+      "epoch": 0.21308524165019577,
+      "grad_norm": 1.0586799383163452,
+      "learning_rate": 4.3262817244669683e-05,
+      "loss": 1.8992,
+      "step": 8463
+    },
+    {
+      "epoch": 0.21386577367089246,
+      "grad_norm": 1.0073469877243042,
+      "learning_rate": 4.3205362785744083e-05,
+      "loss": 1.8766,
+      "step": 8494
+    },
+    {
+      "epoch": 0.21464630569158913,
+      "grad_norm": 0.9976999759674072,
+      "learning_rate": 4.314770288177384e-05,
+      "loss": 1.8864,
+      "step": 8525
+    },
+    {
+      "epoch": 0.21542683771228582,
+      "grad_norm": 0.9928112030029297,
+      "learning_rate": 4.308983818344313e-05,
+      "loss": 1.8874,
+      "step": 8556
+    },
+    {
+      "epoch": 0.21620736973298252,
+      "grad_norm": 1.038405418395996,
+      "learning_rate": 4.3031769343747206e-05,
+      "loss": 1.8725,
+      "step": 8587
+    },
+    {
+      "epoch": 0.2169879017536792,
+      "grad_norm": 1.0328835248947144,
+      "learning_rate": 4.297349701798505e-05,
+      "loss": 1.8884,
+      "step": 8618
+    },
+    {
+      "epoch": 0.21776843377437588,
+      "grad_norm": 1.0254933834075928,
+      "learning_rate": 4.2915021863751916e-05,
+      "loss": 1.8611,
+      "step": 8649
+    },
+    {
+      "epoch": 0.21854896579507258,
+      "grad_norm": 0.99531090259552,
+      "learning_rate": 4.285634454093198e-05,
+      "loss": 1.8889,
+      "step": 8680
+    },
+    {
+      "epoch": 0.21932949781576927,
+      "grad_norm": 1.0536468029022217,
+      "learning_rate": 4.279746571169086e-05,
+      "loss": 1.8875,
+      "step": 8711
+    },
+    {
+      "epoch": 0.22011002983646596,
+      "grad_norm": 0.9915075898170471,
+      "learning_rate": 4.2738386040468136e-05,
+      "loss": 1.8901,
+      "step": 8742
+    },
+    {
+      "epoch": 0.22089056185716263,
+      "grad_norm": 0.9883093237876892,
+      "learning_rate": 4.2679106193969866e-05,
+      "loss": 1.8704,
+      "step": 8773
+    },
+    {
+      "epoch": 0.22167109387785933,
+      "grad_norm": 1.0425434112548828,
+      "learning_rate": 4.261962684116106e-05,
+      "loss": 1.8643,
+      "step": 8804
+    },
+    {
+      "epoch": 0.22245162589855602,
+      "grad_norm": 1.0154091119766235,
+      "learning_rate": 4.2559948653258145e-05,
+      "loss": 1.8806,
+      "step": 8835
+    },
+    {
+      "epoch": 0.22323215791925272,
+      "grad_norm": 1.0432935953140259,
+      "learning_rate": 4.250007230372134e-05,
+      "loss": 1.8928,
+      "step": 8866
+    },
+    {
+      "epoch": 0.22401268993994938,
+      "grad_norm": 0.9709262251853943,
+      "learning_rate": 4.2439998468247126e-05,
+      "loss": 1.8591,
+      "step": 8897
+    },
+    {
+      "epoch": 0.22479322196064608,
+      "grad_norm": 0.9708088636398315,
+      "learning_rate": 4.2379727824760566e-05,
+      "loss": 1.8797,
+      "step": 8928
+    },
+    {
+      "epoch": 0.22557375398134277,
+      "grad_norm": 0.9911683201789856,
+      "learning_rate": 4.231926105340768e-05,
+      "loss": 1.8456,
+      "step": 8959
+    },
+    {
+      "epoch": 0.22635428600203947,
+      "grad_norm": 0.99161297082901,
+      "learning_rate": 4.225859883654776e-05,
+      "loss": 1.8712,
+      "step": 8990
+    },
+    {
+      "epoch": 0.22713481802273613,
+      "grad_norm": 1.0025807619094849,
+      "learning_rate": 4.219774185874569e-05,
+      "loss": 1.8814,
+      "step": 9021
+    },
+    {
+      "epoch": 0.22791535004343283,
+      "grad_norm": 0.9597026109695435,
+      "learning_rate": 4.213669080676418e-05,
+      "loss": 1.8799,
+      "step": 9052
+    },
+    {
+      "epoch": 0.22869588206412952,
+      "grad_norm": 1.0001273155212402,
+      "learning_rate": 4.2075446369556056e-05,
+      "loss": 1.8469,
+      "step": 9083
+    },
+    {
+      "epoch": 0.22947641408482622,
+      "grad_norm": 0.9670659303665161,
+      "learning_rate": 4.201400923825648e-05,
+      "loss": 1.8612,
+      "step": 9114
+    },
+    {
+      "epoch": 0.23025694610552289,
+      "grad_norm": 1.018050193786621,
+      "learning_rate": 4.195238010617511e-05,
+      "loss": 1.8656,
+      "step": 9145
+    },
+    {
+      "epoch": 0.23103747812621958,
+      "grad_norm": 0.9838584661483765,
+      "learning_rate": 4.1890559668788344e-05,
+      "loss": 1.8527,
+      "step": 9176
+    },
+    {
+      "epoch": 0.23181801014691628,
+      "grad_norm": 0.9968937635421753,
+      "learning_rate": 4.1828548623731405e-05,
+      "loss": 1.8753,
+      "step": 9207
+    },
+    {
+      "epoch": 0.23259854216761297,
+      "grad_norm": 0.9698464870452881,
+      "learning_rate": 4.1766347670790506e-05,
+      "loss": 1.8716,
+      "step": 9238
+    },
+    {
+      "epoch": 0.23337907418830964,
+      "grad_norm": 0.9592704772949219,
+      "learning_rate": 4.170395751189495e-05,
+      "loss": 1.8698,
+      "step": 9269
+    },
+    {
+      "epoch": 0.23415960620900633,
+      "grad_norm": 0.9904705286026001,
+      "learning_rate": 4.164137885110921e-05,
+      "loss": 1.8661,
+      "step": 9300
+    },
+    {
+      "epoch": 0.23494013822970303,
+      "grad_norm": 1.0243868827819824,
+      "learning_rate": 4.157861239462495e-05,
+      "loss": 1.8658,
+      "step": 9331
+    },
+    {
+      "epoch": 0.2357206702503997,
+      "grad_norm": 0.9936602711677551,
+      "learning_rate": 4.1515658850753114e-05,
+      "loss": 1.8475,
+      "step": 9362
+    },
+    {
+      "epoch": 0.2365012022710964,
+      "grad_norm": 0.9626069068908691,
+      "learning_rate": 4.145251892991588e-05,
+      "loss": 1.8507,
+      "step": 9393
+    },
+    {
+      "epoch": 0.23728173429179308,
+      "grad_norm": 0.9688258767127991,
+      "learning_rate": 4.138919334463868e-05,
+      "loss": 1.8628,
+      "step": 9424
+    },
+    {
+      "epoch": 0.23806226631248978,
+      "grad_norm": 0.9996054172515869,
+      "learning_rate": 4.1325682809542124e-05,
+      "loss": 1.8734,
+      "step": 9455
+    },
+    {
+      "epoch": 0.23884279833318645,
+      "grad_norm": 1.0037505626678467,
+      "learning_rate": 4.126198804133398e-05,
+      "loss": 1.8778,
+      "step": 9486
+    },
+    {
+      "epoch": 0.23962333035388314,
+      "grad_norm": 0.9751474857330322,
+      "learning_rate": 4.1198109758801055e-05,
+      "loss": 1.8615,
+      "step": 9517
+    },
+    {
+      "epoch": 0.24040386237457984,
+      "grad_norm": 0.9760595560073853,
+      "learning_rate": 4.113404868280107e-05,
+      "loss": 1.8614,
+      "step": 9548
+    },
+    {
+      "epoch": 0.24118439439527653,
+      "grad_norm": 1.0009572505950928,
+      "learning_rate": 4.106980553625457e-05,
+      "loss": 1.8762,
+      "step": 9579
+    },
+    {
+      "epoch": 0.2419649264159732,
+      "grad_norm": 0.983182966709137,
+      "learning_rate": 4.100538104413674e-05,
+      "loss": 1.857,
+      "step": 9610
+    },
+    {
+      "epoch": 0.2427454584366699,
+      "grad_norm": 1.0748534202575684,
+      "learning_rate": 4.09407759334692e-05,
+      "loss": 1.8658,
+      "step": 9641
+    },
+    {
+      "epoch": 0.2435259904573666,
+      "grad_norm": 0.9747381806373596,
+      "learning_rate": 4.087599093331186e-05,
+      "loss": 1.8484,
+      "step": 9672
+    },
+    {
+      "epoch": 0.24430652247806328,
+      "grad_norm": 0.9784808158874512,
+      "learning_rate": 4.081102677475462e-05,
+      "loss": 1.8492,
+      "step": 9703
+    },
+    {
+      "epoch": 0.24508705449875995,
+      "grad_norm": 0.9820215106010437,
+      "learning_rate": 4.0745884190909194e-05,
+      "loss": 1.8516,
+      "step": 9734
+    },
+    {
+      "epoch": 0.24586758651945664,
+      "grad_norm": 0.9536774158477783,
+      "learning_rate": 4.0680563916900796e-05,
+      "loss": 1.8444,
+      "step": 9765
+    },
+    {
+      "epoch": 0.24664811854015334,
+      "grad_norm": 0.9706370234489441,
+      "learning_rate": 4.0615066689859815e-05,
+      "loss": 1.8477,
+      "step": 9796
+    },
+    {
+      "epoch": 0.24742865056085003,
+      "grad_norm": 0.9700275659561157,
+      "learning_rate": 4.0549393248913584e-05,
+      "loss": 1.8515,
+      "step": 9827
+    },
+    {
+      "epoch": 0.2482091825815467,
+      "grad_norm": 0.9522431492805481,
+      "learning_rate": 4.048354433517794e-05,
+      "loss": 1.8287,
+      "step": 9858
+    },
+    {
+      "epoch": 0.2489897146022434,
+      "grad_norm": 0.9691547155380249,
+      "learning_rate": 4.0417520691748916e-05,
+      "loss": 1.8594,
+      "step": 9889
+    },
+    {
+      "epoch": 0.2497702466229401,
+      "grad_norm": 0.9588534235954285,
+      "learning_rate": 4.035132306369438e-05,
+      "loss": 1.8459,
+      "step": 9920
+    },
+    {
+      "epoch": 0.2505507786436368,
+      "grad_norm": 0.9900926351547241,
+      "learning_rate": 4.028495219804555e-05,
+      "loss": 1.8608,
+      "step": 9951
+    },
+    {
+      "epoch": 0.25133131066433345,
+      "grad_norm": 0.9539284110069275,
+      "learning_rate": 4.021840884378864e-05,
+      "loss": 1.8522,
+      "step": 9982
+    },
+    {
+      "epoch": 0.2521118426850302,
+      "grad_norm": 0.9557245969772339,
+      "learning_rate": 4.015169375185633e-05,
+      "loss": 1.8743,
+      "step": 10013
+    },
+    {
+      "epoch": 0.25289237470572684,
+      "grad_norm": 0.9317564964294434,
+      "learning_rate": 4.0084807675119396e-05,
+      "loss": 1.8384,
+      "step": 10044
+    },
+    {
+      "epoch": 0.2536729067264235,
+      "grad_norm": 0.9944160580635071,
+      "learning_rate": 4.0017751368378106e-05,
+      "loss": 1.857,
+      "step": 10075
+    },
+    {
+      "epoch": 0.25445343874712023,
+      "grad_norm": 0.9859464168548584,
+      "learning_rate": 3.995052558835377e-05,
+      "loss": 1.8484,
+      "step": 10106
+    },
+    {
+      "epoch": 0.2552339707678169,
+      "grad_norm": 1.0093594789505005,
+      "learning_rate": 3.988313109368017e-05,
+      "loss": 1.8506,
+      "step": 10137
+    },
+    {
+      "epoch": 0.25601450278851356,
+      "grad_norm": 0.9451240301132202,
+      "learning_rate": 3.981556864489504e-05,
+      "loss": 1.8732,
+      "step": 10168
+    },
+    {
+      "epoch": 0.2567950348092103,
+      "grad_norm": 0.972819447517395,
+      "learning_rate": 3.974783900443142e-05,
+      "loss": 1.856,
+      "step": 10199
+    },
+    {
+      "epoch": 0.25757556682990695,
+      "grad_norm": 0.996379554271698,
+      "learning_rate": 3.9679942936609095e-05,
+      "loss": 1.8299,
+      "step": 10230
+    },
+    {
+      "epoch": 0.2583560988506037,
+      "grad_norm": 2.503967046737671,
+      "learning_rate": 3.961188120762596e-05,
+      "loss": 1.8484,
+      "step": 10261
+    },
+    {
+      "epoch": 0.25913663087130034,
+      "grad_norm": 0.9491912126541138,
+      "learning_rate": 3.954365458554938e-05,
+      "loss": 1.8528,
+      "step": 10292
+    },
+    {
+      "epoch": 0.259917162891997,
+      "grad_norm": 0.9642863273620605,
+      "learning_rate": 3.947526384030751e-05,
+      "loss": 1.863,
+      "step": 10323
+    },
+    {
+      "epoch": 0.26069769491269373,
+      "grad_norm": 0.9915285706520081,
+      "learning_rate": 3.9406709743680624e-05,
+      "loss": 1.8191,
+      "step": 10354
+    },
+    {
+      "epoch": 0.2614782269333904,
+      "grad_norm": 1.0176483392715454,
+      "learning_rate": 3.9337993069292366e-05,
+      "loss": 1.8396,
+      "step": 10385
+    },
+    {
+      "epoch": 0.26225875895408707,
+      "grad_norm": 0.9567158222198486,
+      "learning_rate": 3.926911459260109e-05,
+      "loss": 1.8617,
+      "step": 10416
+    },
+    {
+      "epoch": 0.2630392909747838,
+      "grad_norm": 0.9236714839935303,
+      "learning_rate": 3.920007509089102e-05,
+      "loss": 1.8362,
+      "step": 10447
+    },
+    {
+      "epoch": 0.26381982299548046,
+      "grad_norm": 0.9428004026412964,
+      "learning_rate": 3.913087534326357e-05,
+      "loss": 1.8447,
+      "step": 10478
+    },
+    {
+      "epoch": 0.2646003550161772,
+      "grad_norm": 0.941067099571228,
+      "learning_rate": 3.9061516130628475e-05,
+      "loss": 1.8329,
+      "step": 10509
+    },
+    {
+      "epoch": 0.26538088703687385,
+      "grad_norm": 0.9685031175613403,
+      "learning_rate": 3.8991998235695025e-05,
+      "loss": 1.8543,
+      "step": 10540
+    },
+    {
+      "epoch": 0.2661614190575705,
+      "grad_norm": 0.9629632234573364,
+      "learning_rate": 3.8922322442963224e-05,
+      "loss": 1.8118,
+      "step": 10571
+    },
+    {
+      "epoch": 0.26694195107826724,
+      "grad_norm": 0.9536260366439819,
+      "learning_rate": 3.885248953871491e-05,
+      "loss": 1.8379,
+      "step": 10602
+    },
+    {
+      "epoch": 0.2677224830989639,
+      "grad_norm": 0.9781749248504639,
+      "learning_rate": 3.8782500311004915e-05,
+      "loss": 1.8419,
+      "step": 10633
+    },
+    {
+      "epoch": 0.26850301511966057,
+      "grad_norm": 0.9313937425613403,
+      "learning_rate": 3.871235554965218e-05,
+      "loss": 1.8467,
+      "step": 10664
+    },
+    {
+      "epoch": 0.2692835471403573,
+      "grad_norm": 0.9775392413139343,
+      "learning_rate": 3.864205604623078e-05,
+      "loss": 1.8209,
+      "step": 10695
+    },
+    {
+      "epoch": 0.27006407916105396,
+      "grad_norm": 0.965977132320404,
+      "learning_rate": 3.857160259406107e-05,
+      "loss": 1.8558,
+      "step": 10726
+    },
+    {
+      "epoch": 0.2708446111817507,
+      "grad_norm": 0.9789881706237793,
+      "learning_rate": 3.8500995988200674e-05,
+      "loss": 1.8523,
+      "step": 10757
+    },
+    {
+      "epoch": 0.27162514320244735,
+      "grad_norm": 0.9083163738250732,
+      "learning_rate": 3.843023702543556e-05,
+      "loss": 1.8274,
+      "step": 10788
+    },
+    {
+      "epoch": 0.272405675223144,
+      "grad_norm": 0.9248176217079163,
+      "learning_rate": 3.8359326504270984e-05,
+      "loss": 1.8316,
+      "step": 10819
+    },
+    {
+      "epoch": 0.27318620724384074,
+      "grad_norm": 0.9702487587928772,
+      "learning_rate": 3.828826522492255e-05,
+      "loss": 1.8344,
+      "step": 10850
+    },
+    {
+      "epoch": 0.2739667392645374,
+      "grad_norm": 0.9324803948402405,
+      "learning_rate": 3.821705398930713e-05,
+      "loss": 1.8544,
+      "step": 10881
+    },
+    {
+      "epoch": 0.2747472712852341,
+      "grad_norm": 0.9495794773101807,
+      "learning_rate": 3.814569360103385e-05,
+      "loss": 1.8446,
+      "step": 10912
+    },
+    {
+      "epoch": 0.2755278033059308,
+      "grad_norm": 0.9734468460083008,
+      "learning_rate": 3.807418486539499e-05,
+      "loss": 1.8434,
+      "step": 10943
+    },
+    {
+      "epoch": 0.27630833532662746,
+      "grad_norm": 0.9376105666160583,
+      "learning_rate": 3.80025285893569e-05,
+      "loss": 1.8339,
+      "step": 10974
+    },
+    {
+      "epoch": 0.2770888673473242,
+      "grad_norm": 0.9637653827667236,
+      "learning_rate": 3.793072558155093e-05,
+      "loss": 1.8445,
+      "step": 11005
+    },
+    {
+      "epoch": 0.27786939936802085,
+      "grad_norm": 0.9537612199783325,
+      "learning_rate": 3.785877665226426e-05,
+      "loss": 1.8332,
+      "step": 11036
+    },
+    {
+      "epoch": 0.2786499313887175,
+      "grad_norm": 0.9774130582809448,
+      "learning_rate": 3.778668261343079e-05,
+      "loss": 1.8269,
+      "step": 11067
+    },
+    {
+      "epoch": 0.27943046340941424,
+      "grad_norm": 0.9648153781890869,
+      "learning_rate": 3.771444427862192e-05,
+      "loss": 1.8301,
+      "step": 11098
+    },
+    {
+      "epoch": 0.2802109954301109,
+      "grad_norm": 0.9317411184310913,
+      "learning_rate": 3.7642062463037465e-05,
+      "loss": 1.836,
+      "step": 11129
+    },
+    {
+      "epoch": 0.2809915274508076,
+      "grad_norm": 0.9821638464927673,
+      "learning_rate": 3.7569537983496373e-05,
+      "loss": 1.846,
+      "step": 11160
+    },
+    {
+      "epoch": 0.2817720594715043,
+      "grad_norm": 0.9444936513900757,
+      "learning_rate": 3.749687165842753e-05,
+      "loss": 1.8248,
+      "step": 11191
+    },
+    {
+      "epoch": 0.28255259149220097,
+      "grad_norm": 0.9421222805976868,
+      "learning_rate": 3.7424064307860536e-05,
+      "loss": 1.8521,
+      "step": 11222
+    },
+    {
+      "epoch": 0.2833331235128977,
+      "grad_norm": 0.9378920793533325,
+      "learning_rate": 3.735111675341645e-05,
+      "loss": 1.8361,
+      "step": 11253
+    },
+    {
+      "epoch": 0.28411365553359436,
+      "grad_norm": 0.9363348484039307,
+      "learning_rate": 3.7278029818298524e-05,
+      "loss": 1.8276,
+      "step": 11284
+    },
+    {
+      "epoch": 0.284894187554291,
+      "grad_norm": 0.9247562885284424,
+      "learning_rate": 3.720480432728287e-05,
+      "loss": 1.8354,
+      "step": 11315
+    },
+    {
+      "epoch": 0.28567471957498775,
+      "grad_norm": 0.9505523443222046,
+      "learning_rate": 3.71314411067092e-05,
+      "loss": 1.807,
+      "step": 11346
+    },
+    {
+      "epoch": 0.2864552515956844,
+      "grad_norm": 0.9292653799057007,
+      "learning_rate": 3.70579409844715e-05,
+      "loss": 1.8281,
+      "step": 11377
+    },
+    {
+      "epoch": 0.2872357836163811,
+      "grad_norm": 0.9625663161277771,
+      "learning_rate": 3.698430479000865e-05,
+      "loss": 1.8211,
+      "step": 11408
+    },
+    {
+      "epoch": 0.2880163156370778,
+      "grad_norm": 0.9280233979225159,
+      "learning_rate": 3.691053335429509e-05,
+      "loss": 1.8177,
+      "step": 11439
+    },
+    {
+      "epoch": 0.28879684765777447,
+      "grad_norm": 0.9617031216621399,
+      "learning_rate": 3.683662750983147e-05,
+      "loss": 1.831,
+      "step": 11470
+    },
+    {
+      "epoch": 0.2895773796784712,
+      "grad_norm": 0.9631845951080322,
+      "learning_rate": 3.676258809063518e-05,
+      "loss": 1.8154,
+      "step": 11501
+    },
+    {
+      "epoch": 0.29035791169916786,
+      "grad_norm": 0.9200331568717957,
+      "learning_rate": 3.6688415932231004e-05,
+      "loss": 1.8452,
+      "step": 11532
+    },
+    {
+      "epoch": 0.2911384437198645,
+      "grad_norm": 0.9431037902832031,
+      "learning_rate": 3.661411187164166e-05,
+      "loss": 1.8221,
+      "step": 11563
+    },
+    {
+      "epoch": 0.29191897574056125,
+      "grad_norm": 0.9307507276535034,
+      "learning_rate": 3.65396767473784e-05,
+      "loss": 1.8092,
+      "step": 11594
+    },
+    {
+      "epoch": 0.2926995077612579,
+      "grad_norm": 0.9896314144134521,
+      "learning_rate": 3.6465111399431465e-05,
+      "loss": 1.826,
+      "step": 11625
+    },
+    {
+      "epoch": 0.2934800397819546,
+      "grad_norm": 0.9361921548843384,
+      "learning_rate": 3.6390416669260674e-05,
+      "loss": 1.8207,
+      "step": 11656
+    },
+    {
+      "epoch": 0.2942605718026513,
+      "grad_norm": 0.9492716789245605,
+      "learning_rate": 3.63155933997859e-05,
+      "loss": 1.822,
+      "step": 11687
+    },
+    {
+      "epoch": 0.29504110382334797,
+      "grad_norm": 0.9642727375030518,
+      "learning_rate": 3.624064243537758e-05,
+      "loss": 1.8165,
+      "step": 11718
+    },
+    {
+      "epoch": 0.29582163584404464,
+      "grad_norm": 0.9700178503990173,
+      "learning_rate": 3.616556462184716e-05,
+      "loss": 1.8093,
+      "step": 11749
+    },
+    {
+      "epoch": 0.29660216786474136,
+      "grad_norm": 0.90894615650177,
+      "learning_rate": 3.609036080643755e-05,
+      "loss": 1.8312,
+      "step": 11780
+    },
+    {
+      "epoch": 0.29738269988543803,
+      "grad_norm": 0.9441593885421753,
+      "learning_rate": 3.60150318378136e-05,
+      "loss": 1.8324,
+      "step": 11811
+    },
+    {
+      "epoch": 0.29816323190613475,
+      "grad_norm": 0.9351882338523865,
+      "learning_rate": 3.5939578566052465e-05,
+      "loss": 1.8303,
+      "step": 11842
+    },
+    {
+      "epoch": 0.2989437639268314,
+      "grad_norm": 0.9438377618789673,
+      "learning_rate": 3.586400184263408e-05,
+      "loss": 1.8164,
+      "step": 11873
+    },
+    {
+      "epoch": 0.2997242959475281,
+      "grad_norm": 0.9775059819221497,
+      "learning_rate": 3.578830252043148e-05,
+      "loss": 1.8146,
+      "step": 11904
+    },
+    {
+      "epoch": 0.3005048279682248,
+      "grad_norm": 0.9342683553695679,
+      "learning_rate": 3.571248145370125e-05,
+      "loss": 1.8324,
+      "step": 11935
+    },
+    {
+      "epoch": 0.3012853599889215,
+      "grad_norm": 0.9539228081703186,
+      "learning_rate": 3.5636539498073794e-05,
+      "loss": 1.8112,
+      "step": 11966
+    },
+    {
+      "epoch": 0.30206589200961814,
+      "grad_norm": 1.0048060417175293,
+      "learning_rate": 3.556047751054378e-05,
+      "loss": 1.8261,
+      "step": 11997
+    },
+    {
+      "epoch": 0.30284642403031486,
+      "grad_norm": 0.9269846081733704,
+      "learning_rate": 3.548429634946039e-05,
+      "loss": 1.8256,
+      "step": 12028
+    },
+    {
+      "epoch": 0.30362695605101153,
+      "grad_norm": 0.937609076499939,
+      "learning_rate": 3.540799687451768e-05,
+      "loss": 1.8222,
+      "step": 12059
+    },
+    {
+      "epoch": 0.30440748807170825,
+      "grad_norm": 0.9538866281509399,
+      "learning_rate": 3.533157994674485e-05,
+      "loss": 1.8214,
+      "step": 12090
+    },
+    {
+      "epoch": 0.3051880200924049,
+      "grad_norm": 0.9644604325294495,
+      "learning_rate": 3.5255046428496546e-05,
+      "loss": 1.8117,
+      "step": 12121
+    },
+    {
+      "epoch": 0.3059685521131016,
+      "grad_norm": 1.0498855113983154,
+      "learning_rate": 3.517839718344311e-05,
+      "loss": 1.8249,
+      "step": 12152
+    },
+    {
+      "epoch": 0.3067490841337983,
+      "grad_norm": 0.952634334564209,
+      "learning_rate": 3.510163307656086e-05,
+      "loss": 1.8263,
+      "step": 12183
+    }
+  ],
+  "logging_steps": 31,
+  "max_steps": 30517,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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 sha256:4d814be76984e23fb3bd9dc1672f03b4559e9f604318f29ab3bebb0989cab850
+size 5304

checkpoint-15260/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/Qwen2.5-7B-Instruct-si-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 sha256:042bafc10e817b70aa7aa2442a48c7c3dd7d66b67e5ab6784f946091761bed10
+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:d856e142af67f84a059080b8e1774dcb050f87d127aadde001ca6a9af010556b
+size 3662865184

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdb40f4d281f64981f83459ba6290f50fdf1f4acfd1045410d9215082d5a5d6d
+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 sha256:0acbabe83701dae135093c785ed6087f738c5f849e1e90dca1a0264c34d0cc29
+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": 0.38422318180101467,
+  "eval_steps": 500,
+  "global_step": 15260,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0007805320206966878,
+      "grad_norm": 24.262310028076172,
+      "learning_rate": 1.0157273918741808e-06,
+      "loss": 9.1957,
+      "step": 31
+    },
+    {
+      "epoch": 0.0015610640413933755,
+      "grad_norm": 29.819591522216797,
+      "learning_rate": 2.0314547837483616e-06,
+      "loss": 7.9757,
+      "step": 62
+    },
+    {
+      "epoch": 0.002341596062090063,
+      "grad_norm": 14.961602210998535,
+      "learning_rate": 3.0471821756225426e-06,
+      "loss": 6.5436,
+      "step": 93
+    },
+    {
+      "epoch": 0.003122128082786751,
+      "grad_norm": 5.151533126831055,
+      "learning_rate": 4.062909567496723e-06,
+      "loss": 5.4812,
+      "step": 124
+    },
+    {
+      "epoch": 0.003902660103483439,
+      "grad_norm": 7.370818138122559,
+      "learning_rate": 5.078636959370905e-06,
+      "loss": 4.8332,
+      "step": 155
+    },
+    {
+      "epoch": 0.004683192124180126,
+      "grad_norm": 7.932437896728516,
+      "learning_rate": 6.094364351245085e-06,
+      "loss": 4.4411,
+      "step": 186
+    },
+    {
+      "epoch": 0.005463724144876814,
+      "grad_norm": 7.834314823150635,
+      "learning_rate": 7.110091743119267e-06,
+      "loss": 4.1978,
+      "step": 217
+    },
+    {
+      "epoch": 0.006244256165573502,
+      "grad_norm": 11.881230354309082,
+      "learning_rate": 8.125819134993446e-06,
+      "loss": 3.9897,
+      "step": 248
+    },
+    {
+      "epoch": 0.00702478818627019,
+      "grad_norm": 6.348697185516357,
+      "learning_rate": 9.141546526867629e-06,
+      "loss": 3.8375,
+      "step": 279
+    },
+    {
+      "epoch": 0.007805320206966878,
+      "grad_norm": 8.414978981018066,
+      "learning_rate": 1.015727391874181e-05,
+      "loss": 3.7681,
+      "step": 310
+    },
+    {
+      "epoch": 0.008585852227663565,
+      "grad_norm": 6.531826972961426,
+      "learning_rate": 1.117300131061599e-05,
+      "loss": 3.6599,
+      "step": 341
+    },
+    {
+      "epoch": 0.009366384248360253,
+      "grad_norm": 9.794255256652832,
+      "learning_rate": 1.218872870249017e-05,
+      "loss": 3.5324,
+      "step": 372
+    },
+    {
+      "epoch": 0.01014691626905694,
+      "grad_norm": 8.084766387939453,
+      "learning_rate": 1.3204456094364351e-05,
+      "loss": 3.4696,
+      "step": 403
+    },
+    {
+      "epoch": 0.010927448289753628,
+      "grad_norm": 7.659717559814453,
+      "learning_rate": 1.4220183486238533e-05,
+      "loss": 3.3832,
+      "step": 434
+    },
+    {
+      "epoch": 0.011707980310450316,
+      "grad_norm": 5.131711959838867,
+      "learning_rate": 1.5235910878112714e-05,
+      "loss": 3.3514,
+      "step": 465
+    },
+    {
+      "epoch": 0.012488512331147004,
+      "grad_norm": 6.3673601150512695,
+      "learning_rate": 1.6251638269986893e-05,
+      "loss": 3.2988,
+      "step": 496
+    },
+    {
+      "epoch": 0.013269044351843692,
+      "grad_norm": 4.5014142990112305,
+      "learning_rate": 1.7267365661861077e-05,
+      "loss": 3.239,
+      "step": 527
+    },
+    {
+      "epoch": 0.01404957637254038,
+      "grad_norm": 5.1420769691467285,
+      "learning_rate": 1.8283093053735257e-05,
+      "loss": 3.1892,
+      "step": 558
+    },
+    {
+      "epoch": 0.014830108393237068,
+      "grad_norm": 5.227200508117676,
+      "learning_rate": 1.9298820445609438e-05,
+      "loss": 3.1732,
+      "step": 589
+    },
+    {
+      "epoch": 0.015610640413933756,
+      "grad_norm": 4.4621734619140625,
+      "learning_rate": 2.031454783748362e-05,
+      "loss": 3.0898,
+      "step": 620
+    },
+    {
+      "epoch": 0.016391172434630442,
+      "grad_norm": 5.213263511657715,
+      "learning_rate": 2.13302752293578e-05,
+      "loss": 3.0832,
+      "step": 651
+    },
+    {
+      "epoch": 0.01717170445532713,
+      "grad_norm": 4.23059606552124,
+      "learning_rate": 2.234600262123198e-05,
+      "loss": 3.0341,
+      "step": 682
+    },
+    {
+      "epoch": 0.017952236476023817,
+      "grad_norm": 3.5276854038238525,
+      "learning_rate": 2.336173001310616e-05,
+      "loss": 3.0241,
+      "step": 713
+    },
+    {
+      "epoch": 0.018732768496720505,
+      "grad_norm": 3.199700355529785,
+      "learning_rate": 2.437745740498034e-05,
+      "loss": 2.9659,
+      "step": 744
+    },
+    {
+      "epoch": 0.019513300517417193,
+      "grad_norm": 9.667389869689941,
+      "learning_rate": 2.5393184796854525e-05,
+      "loss": 2.9292,
+      "step": 775
+    },
+    {
+      "epoch": 0.02029383253811388,
+      "grad_norm": 3.677541732788086,
+      "learning_rate": 2.6408912188728702e-05,
+      "loss": 2.919,
+      "step": 806
+    },
+    {
+      "epoch": 0.02107436455881057,
+      "grad_norm": 3.711683750152588,
+      "learning_rate": 2.7424639580602886e-05,
+      "loss": 2.9141,
+      "step": 837
+    },
+    {
+      "epoch": 0.021854896579507257,
+      "grad_norm": 3.1250174045562744,
+      "learning_rate": 2.8440366972477066e-05,
+      "loss": 2.8585,
+      "step": 868
+    },
+    {
+      "epoch": 0.022635428600203945,
+      "grad_norm": 3.4183220863342285,
+      "learning_rate": 2.9456094364351244e-05,
+      "loss": 2.8206,
+      "step": 899
+    },
+    {
+      "epoch": 0.023415960620900633,
+      "grad_norm": 2.8176679611206055,
+      "learning_rate": 3.0471821756225428e-05,
+      "loss": 2.787,
+      "step": 930
+    },
+    {
+      "epoch": 0.02419649264159732,
+      "grad_norm": 2.7993154525756836,
+      "learning_rate": 3.148754914809961e-05,
+      "loss": 2.7678,
+      "step": 961
+    },
+    {
+      "epoch": 0.02497702466229401,
+      "grad_norm": 2.8017027378082275,
+      "learning_rate": 3.2503276539973785e-05,
+      "loss": 2.7499,
+      "step": 992
+    },
+    {
+      "epoch": 0.025757556682990696,
+      "grad_norm": 2.958606004714966,
+      "learning_rate": 3.351900393184797e-05,
+      "loss": 2.7211,
+      "step": 1023
+    },
+    {
+      "epoch": 0.026538088703687384,
+      "grad_norm": 2.5942046642303467,
+      "learning_rate": 3.453473132372215e-05,
+      "loss": 2.6823,
+      "step": 1054
+    },
+    {
+      "epoch": 0.027318620724384072,
+      "grad_norm": 3.1978206634521484,
+      "learning_rate": 3.555045871559633e-05,
+      "loss": 2.6943,
+      "step": 1085
+    },
+    {
+      "epoch": 0.02809915274508076,
+      "grad_norm": 2.6260809898376465,
+      "learning_rate": 3.6566186107470514e-05,
+      "loss": 2.6574,
+      "step": 1116
+    },
+    {
+      "epoch": 0.028879684765777448,
+      "grad_norm": 2.6633715629577637,
+      "learning_rate": 3.7581913499344695e-05,
+      "loss": 2.6394,
+      "step": 1147
+    },
+    {
+      "epoch": 0.029660216786474135,
+      "grad_norm": 2.5701236724853516,
+      "learning_rate": 3.8597640891218876e-05,
+      "loss": 2.6336,
+      "step": 1178
+    },
+    {
+      "epoch": 0.030440748807170823,
+      "grad_norm": 2.4242734909057617,
+      "learning_rate": 3.9613368283093056e-05,
+      "loss": 2.6285,
+      "step": 1209
+    },
+    {
+      "epoch": 0.03122128082786751,
+      "grad_norm": 2.6410114765167236,
+      "learning_rate": 4.062909567496724e-05,
+      "loss": 2.5821,
+      "step": 1240
+    },
+    {
+      "epoch": 0.032001812848564196,
+      "grad_norm": 2.419649839401245,
+      "learning_rate": 4.164482306684142e-05,
+      "loss": 2.5576,
+      "step": 1271
+    },
+    {
+      "epoch": 0.032782344869260883,
+      "grad_norm": 2.314750909805298,
+      "learning_rate": 4.26605504587156e-05,
+      "loss": 2.5438,
+      "step": 1302
+    },
+    {
+      "epoch": 0.03356287688995757,
+      "grad_norm": 2.288361072540283,
+      "learning_rate": 4.367627785058978e-05,
+      "loss": 2.5197,
+      "step": 1333
+    },
+    {
+      "epoch": 0.03434340891065426,
+      "grad_norm": 2.328840494155884,
+      "learning_rate": 4.469200524246396e-05,
+      "loss": 2.5193,
+      "step": 1364
+    },
+    {
+      "epoch": 0.03512394093135095,
+      "grad_norm": 2.2555599212646484,
+      "learning_rate": 4.570773263433814e-05,
+      "loss": 2.4907,
+      "step": 1395
+    },
+    {
+      "epoch": 0.035904472952047635,
+      "grad_norm": 2.1358766555786133,
+      "learning_rate": 4.672346002621232e-05,
+      "loss": 2.4737,
+      "step": 1426
+    },
+    {
+      "epoch": 0.03668500497274432,
+      "grad_norm": 2.1471140384674072,
+      "learning_rate": 4.77391874180865e-05,
+      "loss": 2.4733,
+      "step": 1457
+    },
+    {
+      "epoch": 0.03746553699344101,
+      "grad_norm": 2.1371941566467285,
+      "learning_rate": 4.875491480996068e-05,
+      "loss": 2.432,
+      "step": 1488
+    },
+    {
+      "epoch": 0.0382460690141377,
+      "grad_norm": 1.9789690971374512,
+      "learning_rate": 4.977064220183487e-05,
+      "loss": 2.4407,
+      "step": 1519
+    },
+    {
+      "epoch": 0.039026601034834386,
+      "grad_norm": 2.0055742263793945,
+      "learning_rate": 4.9999915451558777e-05,
+      "loss": 2.4178,
+      "step": 1550
+    },
+    {
+      "epoch": 0.039807133055531074,
+      "grad_norm": 2.095475196838379,
+      "learning_rate": 4.999955597496219e-05,
+      "loss": 2.4198,
+      "step": 1581
+    },
+    {
+      "epoch": 0.04058766507622776,
+      "grad_norm": 2.046337842941284,
+      "learning_rate": 4.9998914381774255e-05,
+      "loss": 2.3936,
+      "step": 1612
+    },
+    {
+      "epoch": 0.04136819709692445,
+      "grad_norm": 1.8528848886489868,
+      "learning_rate": 4.999799067923527e-05,
+      "loss": 2.3893,
+      "step": 1643
+    },
+    {
+      "epoch": 0.04214872911762114,
+      "grad_norm": 1.883175253868103,
+      "learning_rate": 4.999678487776908e-05,
+      "loss": 2.3668,
+      "step": 1674
+    },
+    {
+      "epoch": 0.042929261138317826,
+      "grad_norm": 1.8084770441055298,
+      "learning_rate": 4.9995296990983006e-05,
+      "loss": 2.3702,
+      "step": 1705
+    },
+    {
+      "epoch": 0.043709793159014514,
+      "grad_norm": 1.8336963653564453,
+      "learning_rate": 4.999352703566763e-05,
+      "loss": 2.357,
+      "step": 1736
+    },
+    {
+      "epoch": 0.0444903251797112,
+      "grad_norm": 1.8369375467300415,
+      "learning_rate": 4.999147503179668e-05,
+      "loss": 2.3393,
+      "step": 1767
+    },
+    {
+      "epoch": 0.04527085720040789,
+      "grad_norm": 1.8411383628845215,
+      "learning_rate": 4.998914100252672e-05,
+      "loss": 2.319,
+      "step": 1798
+    },
+    {
+      "epoch": 0.04605138922110458,
+      "grad_norm": 1.785543441772461,
+      "learning_rate": 4.998652497419696e-05,
+      "loss": 2.3259,
+      "step": 1829
+    },
+    {
+      "epoch": 0.046831921241801265,
+      "grad_norm": 1.7194079160690308,
+      "learning_rate": 4.9983626976328927e-05,
+      "loss": 2.3046,
+      "step": 1860
+    },
+    {
+      "epoch": 0.04761245326249795,
+      "grad_norm": 1.7909469604492188,
+      "learning_rate": 4.998044704162613e-05,
+      "loss": 2.307,
+      "step": 1891
+    },
+    {
+      "epoch": 0.04839298528319464,
+      "grad_norm": 1.725806474685669,
+      "learning_rate": 4.9976985205973705e-05,
+      "loss": 2.2992,
+      "step": 1922
+    },
+    {
+      "epoch": 0.04917351730389133,
+      "grad_norm": 1.67300546169281,
+      "learning_rate": 4.997324150843799e-05,
+      "loss": 2.2763,
+      "step": 1953
+    },
+    {
+      "epoch": 0.04995404932458802,
+      "grad_norm": 1.7416061162948608,
+      "learning_rate": 4.99692159912661e-05,
+      "loss": 2.2596,
+      "step": 1984
+    },
+    {
+      "epoch": 0.050734581345284704,
+      "grad_norm": 1.843024492263794,
+      "learning_rate": 4.996490869988546e-05,
+      "loss": 2.2644,
+      "step": 2015
+    },
+    {
+      "epoch": 0.05151511336598139,
+      "grad_norm": 1.6172534227371216,
+      "learning_rate": 4.996031968290326e-05,
+      "loss": 2.271,
+      "step": 2046
+    },
+    {
+      "epoch": 0.05229564538667808,
+      "grad_norm": 1.6510816812515259,
+      "learning_rate": 4.995544899210594e-05,
+      "loss": 2.2445,
+      "step": 2077
+    },
+    {
+      "epoch": 0.05307617740737477,
+      "grad_norm": 1.625775933265686,
+      "learning_rate": 4.9950296682458583e-05,
+      "loss": 2.2432,
+      "step": 2108
+    },
+    {
+      "epoch": 0.053856709428071456,
+      "grad_norm": 1.602299690246582,
+      "learning_rate": 4.994486281210429e-05,
+      "loss": 2.2266,
+      "step": 2139
+    },
+    {
+      "epoch": 0.054637241448768144,
+      "grad_norm": 1.7036757469177246,
+      "learning_rate": 4.9939147442363566e-05,
+      "loss": 2.2292,
+      "step": 2170
+    },
+    {
+      "epoch": 0.05541777346946483,
+      "grad_norm": 1.5851162672042847,
+      "learning_rate": 4.9933150637733574e-05,
+      "loss": 2.2286,
+      "step": 2201
+    },
+    {
+      "epoch": 0.05619830549016152,
+      "grad_norm": 1.6328140497207642,
+      "learning_rate": 4.992687246588743e-05,
+      "loss": 2.2342,
+      "step": 2232
+    },
+    {
+      "epoch": 0.05697883751085821,
+      "grad_norm": 1.4901413917541504,
+      "learning_rate": 4.992031299767347e-05,
+      "loss": 2.2094,
+      "step": 2263
+    },
+    {
+      "epoch": 0.057759369531554895,
+      "grad_norm": 1.5897445678710938,
+      "learning_rate": 4.9913472307114386e-05,
+      "loss": 2.2126,
+      "step": 2294
+    },
+    {
+      "epoch": 0.05853990155225158,
+      "grad_norm": 1.5534899234771729,
+      "learning_rate": 4.9906350471406446e-05,
+      "loss": 2.2125,
+      "step": 2325
+    },
+    {
+      "epoch": 0.05932043357294827,
+      "grad_norm": 1.5713675022125244,
+      "learning_rate": 4.989894757091861e-05,
+      "loss": 2.2007,
+      "step": 2356
+    },
+    {
+      "epoch": 0.06010096559364496,
+      "grad_norm": 1.473955750465393,
+      "learning_rate": 4.989126368919158e-05,
+      "loss": 2.1819,
+      "step": 2387
+    },
+    {
+      "epoch": 0.06088149761434165,
+      "grad_norm": 1.5200265645980835,
+      "learning_rate": 4.988329891293693e-05,
+      "loss": 2.1944,
+      "step": 2418
+    },
+    {
+      "epoch": 0.061662029635038335,
+      "grad_norm": 1.5236589908599854,
+      "learning_rate": 4.987505333203608e-05,
+      "loss": 2.1816,
+      "step": 2449
+    },
+    {
+      "epoch": 0.06244256165573502,
+      "grad_norm": 1.5306485891342163,
+      "learning_rate": 4.9866527039539276e-05,
+      "loss": 2.187,
+      "step": 2480
+    },
+    {
+      "epoch": 0.06322309367643171,
+      "grad_norm": 1.5017462968826294,
+      "learning_rate": 4.9857720131664594e-05,
+      "loss": 2.1706,
+      "step": 2511
+    },
+    {
+      "epoch": 0.06400362569712839,
+      "grad_norm": 4.610604763031006,
+      "learning_rate": 4.9848632707796773e-05,
+      "loss": 2.1528,
+      "step": 2542
+    },
+    {
+      "epoch": 0.06478415771782509,
+      "grad_norm": 1.4580930471420288,
+      "learning_rate": 4.9839264870486155e-05,
+      "loss": 2.1849,
+      "step": 2573
+    },
+    {
+      "epoch": 0.06556468973852177,
+      "grad_norm": 1.5506151914596558,
+      "learning_rate": 4.9829616725447526e-05,
+      "loss": 2.1504,
+      "step": 2604
+    },
+    {
+      "epoch": 0.06634522175921846,
+      "grad_norm": 1.4275034666061401,
+      "learning_rate": 4.981968838155888e-05,
+      "loss": 2.1492,
+      "step": 2635
+    },
+    {
+      "epoch": 0.06712575377991514,
+      "grad_norm": 1.4749577045440674,
+      "learning_rate": 4.980947995086024e-05,
+      "loss": 2.1579,
+      "step": 2666
+    },
+    {
+      "epoch": 0.06790628580061184,
+      "grad_norm": 1.4220107793807983,
+      "learning_rate": 4.979899154855234e-05,
+      "loss": 2.1522,
+      "step": 2697
+    },
+    {
+      "epoch": 0.06868681782130852,
+      "grad_norm": 1.4243831634521484,
+      "learning_rate": 4.9788223292995386e-05,
+      "loss": 2.1258,
+      "step": 2728
+    },
+    {
+      "epoch": 0.06946734984200521,
+      "grad_norm": 1.4925100803375244,
+      "learning_rate": 4.977717530570768e-05,
+      "loss": 2.1379,
+      "step": 2759
+    },
+    {
+      "epoch": 0.0702478818627019,
+      "grad_norm": 1.4839624166488647,
+      "learning_rate": 4.976584771136425e-05,
+      "loss": 2.1588,
+      "step": 2790
+    },
+    {
+      "epoch": 0.07102841388339859,
+      "grad_norm": 1.4130090475082397,
+      "learning_rate": 4.975424063779547e-05,
+      "loss": 2.1461,
+      "step": 2821
+    },
+    {
+      "epoch": 0.07180894590409527,
+      "grad_norm": 1.3940472602844238,
+      "learning_rate": 4.974235421598557e-05,
+      "loss": 2.1416,
+      "step": 2852
+    },
+    {
+      "epoch": 0.07258947792479196,
+      "grad_norm": 1.4502291679382324,
+      "learning_rate": 4.973018858007122e-05,
+      "loss": 2.1315,
+      "step": 2883
+    },
+    {
+      "epoch": 0.07337000994548865,
+      "grad_norm": 1.4334006309509277,
+      "learning_rate": 4.9717743867339963e-05,
+      "loss": 2.122,
+      "step": 2914
+    },
+    {
+      "epoch": 0.07415054196618534,
+      "grad_norm": 1.4366185665130615,
+      "learning_rate": 4.9705020218228695e-05,
+      "loss": 2.1179,
+      "step": 2945
+    },
+    {
+      "epoch": 0.07493107398688202,
+      "grad_norm": 1.437264084815979,
+      "learning_rate": 4.969201777632205e-05,
+      "loss": 2.1171,
+      "step": 2976
+    },
+    {
+      "epoch": 0.07571160600757872,
+      "grad_norm": 1.3713815212249756,
+      "learning_rate": 4.9678736688350846e-05,
+      "loss": 2.1215,
+      "step": 3007
+    },
+    {
+      "epoch": 0.0764921380282754,
+      "grad_norm": 1.5930180549621582,
+      "learning_rate": 4.966517710419033e-05,
+      "loss": 2.0961,
+      "step": 3038
+    },
+    {
+      "epoch": 0.07727267004897209,
+      "grad_norm": 1.4208778142929077,
+      "learning_rate": 4.965133917685858e-05,
+      "loss": 2.1193,
+      "step": 3069
+    },
+    {
+      "epoch": 0.07805320206966877,
+      "grad_norm": 1.3563286066055298,
+      "learning_rate": 4.9637223062514714e-05,
+      "loss": 2.0957,
+      "step": 3100
+    },
+    {
+      "epoch": 0.07883373409036547,
+      "grad_norm": 1.382861852645874,
+      "learning_rate": 4.962282892045718e-05,
+      "loss": 2.117,
+      "step": 3131
+    },
+    {
+      "epoch": 0.07961426611106215,
+      "grad_norm": 1.326231837272644,
+      "learning_rate": 4.9608156913121904e-05,
+      "loss": 2.0906,
+      "step": 3162
+    },
+    {
+      "epoch": 0.08039479813175884,
+      "grad_norm": 1.3465954065322876,
+      "learning_rate": 4.959320720608049e-05,
+      "loss": 2.09,
+      "step": 3193
+    },
+    {
+      "epoch": 0.08117533015245552,
+      "grad_norm": 1.3832777738571167,
+      "learning_rate": 4.9577979968038354e-05,
+      "loss": 2.089,
+      "step": 3224
+    },
+    {
+      "epoch": 0.08195586217315222,
+      "grad_norm": 1.4453243017196655,
+      "learning_rate": 4.956247537083282e-05,
+      "loss": 2.0867,
+      "step": 3255
+    },
+    {
+      "epoch": 0.0827363941938489,
+      "grad_norm": 1.310168743133545,
+      "learning_rate": 4.9546693589431145e-05,
+      "loss": 2.0915,
+      "step": 3286
+    },
+    {
+      "epoch": 0.0835169262145456,
+      "grad_norm": 1.354078769683838,
+      "learning_rate": 4.9530634801928595e-05,
+      "loss": 2.0888,
+      "step": 3317
+    },
+    {
+      "epoch": 0.08429745823524228,
+      "grad_norm": 1.3768595457077026,
+      "learning_rate": 4.9514299189546395e-05,
+      "loss": 2.0821,
+      "step": 3348
+    },
+    {
+      "epoch": 0.08507799025593897,
+      "grad_norm": 1.3402544260025024,
+      "learning_rate": 4.949768693662973e-05,
+      "loss": 2.0776,
+      "step": 3379
+    },
+    {
+      "epoch": 0.08585852227663565,
+      "grad_norm": 1.3178027868270874,
+      "learning_rate": 4.948079823064559e-05,
+      "loss": 2.0699,
+      "step": 3410
+    },
+    {
+      "epoch": 0.08663905429733235,
+      "grad_norm": 1.7057585716247559,
+      "learning_rate": 4.946363326218074e-05,
+      "loss": 2.0615,
+      "step": 3441
+    },
+    {
+      "epoch": 0.08741958631802903,
+      "grad_norm": 1.3453648090362549,
+      "learning_rate": 4.9446192224939525e-05,
+      "loss": 2.0788,
+      "step": 3472
+    },
+    {
+      "epoch": 0.08820011833872572,
+      "grad_norm": 1.3319638967514038,
+      "learning_rate": 4.942847531574167e-05,
+      "loss": 2.0619,
+      "step": 3503
+    },
+    {
+      "epoch": 0.0889806503594224,
+      "grad_norm": 1.2845163345336914,
+      "learning_rate": 4.941048273452008e-05,
+      "loss": 2.0728,
+      "step": 3534
+    },
+    {
+      "epoch": 0.0897611823801191,
+      "grad_norm": 1.3615431785583496,
+      "learning_rate": 4.9392214684318605e-05,
+      "loss": 2.0538,
+      "step": 3565
+    },
+    {
+      "epoch": 0.09054171440081578,
+      "grad_norm": 1.2946122884750366,
+      "learning_rate": 4.93736713712897e-05,
+      "loss": 2.0689,
+      "step": 3596
+    },
+    {
+      "epoch": 0.09132224642151247,
+      "grad_norm": 1.294846534729004,
+      "learning_rate": 4.9354853004692124e-05,
+      "loss": 2.0706,
+      "step": 3627
+    },
+    {
+      "epoch": 0.09210277844220915,
+      "grad_norm": 1.298010230064392,
+      "learning_rate": 4.93357597968886e-05,
+      "loss": 2.0406,
+      "step": 3658
+    },
+    {
+      "epoch": 0.09288331046290585,
+      "grad_norm": 1.7569706439971924,
+      "learning_rate": 4.931639196334338e-05,
+      "loss": 2.0736,
+      "step": 3689
+    },
+    {
+      "epoch": 0.09366384248360253,
+      "grad_norm": 1.2595418691635132,
+      "learning_rate": 4.9296749722619826e-05,
+      "loss": 2.0654,
+      "step": 3720
+    },
+    {
+      "epoch": 0.09444437450429922,
+      "grad_norm": 1.3139164447784424,
+      "learning_rate": 4.9276833296377966e-05,
+      "loss": 2.0467,
+      "step": 3751
+    },
+    {
+      "epoch": 0.0952249065249959,
+      "grad_norm": 1.290247917175293,
+      "learning_rate": 4.925664290937196e-05,
+      "loss": 2.0418,
+      "step": 3782
+    },
+    {
+      "epoch": 0.0960054385456926,
+      "grad_norm": 1.2755826711654663,
+      "learning_rate": 4.9236178789447576e-05,
+      "loss": 2.0244,
+      "step": 3813
+    },
+    {
+      "epoch": 0.09678597056638928,
+      "grad_norm": 1.2596077919006348,
+      "learning_rate": 4.921544116753962e-05,
+      "loss": 2.0609,
+      "step": 3844
+    },
+    {
+      "epoch": 0.09756650258708598,
+      "grad_norm": 1.249387264251709,
+      "learning_rate": 4.919443027766935e-05,
+      "loss": 2.0455,
+      "step": 3875
+    },
+    {
+      "epoch": 0.09834703460778266,
+      "grad_norm": 1.255379319190979,
+      "learning_rate": 4.91731463569418e-05,
+      "loss": 2.024,
+      "step": 3906
+    },
+    {
+      "epoch": 0.09912756662847935,
+      "grad_norm": 1.2620748281478882,
+      "learning_rate": 4.915158964554312e-05,
+      "loss": 2.0355,
+      "step": 3937
+    },
+    {
+      "epoch": 0.09990809864917603,
+      "grad_norm": 1.2736345529556274,
+      "learning_rate": 4.912976038673786e-05,
+      "loss": 2.0351,
+      "step": 3968
+    },
+    {
+      "epoch": 0.10068863066987273,
+      "grad_norm": 1.18524169921875,
+      "learning_rate": 4.9107658826866254e-05,
+      "loss": 2.029,
+      "step": 3999
+    },
+    {
+      "epoch": 0.10146916269056941,
+      "grad_norm": 10.429583549499512,
+      "learning_rate": 4.908528521534139e-05,
+      "loss": 2.0226,
+      "step": 4030
+    },
+    {
+      "epoch": 0.1022496947112661,
+      "grad_norm": 1.240295648574829,
+      "learning_rate": 4.906263980464644e-05,
+      "loss": 2.0401,
+      "step": 4061
+    },
+    {
+      "epoch": 0.10303022673196278,
+      "grad_norm": 1.2191627025604248,
+      "learning_rate": 4.903972285033178e-05,
+      "loss": 2.0079,
+      "step": 4092
+    },
+    {
+      "epoch": 0.10381075875265948,
+      "grad_norm": 1.2340337038040161,
+      "learning_rate": 4.901653461101213e-05,
+      "loss": 2.0305,
+      "step": 4123
+    },
+    {
+      "epoch": 0.10459129077335616,
+      "grad_norm": 1.284839153289795,
+      "learning_rate": 4.8993075348363626e-05,
+      "loss": 2.0212,
+      "step": 4154
+    },
+    {
+      "epoch": 0.10537182279405286,
+      "grad_norm": 1.2955284118652344,
+      "learning_rate": 4.896934532712084e-05,
+      "loss": 2.0328,
+      "step": 4185
+    },
+    {
+      "epoch": 0.10615235481474954,
+      "grad_norm": 1.165124535560608,
+      "learning_rate": 4.8945344815073846e-05,
+      "loss": 2.0248,
+      "step": 4216
+    },
+    {
+      "epoch": 0.10693288683544623,
+      "grad_norm": 1.1925835609436035,
+      "learning_rate": 4.892107408306516e-05,
+      "loss": 2.0086,
+      "step": 4247
+    },
+    {
+      "epoch": 0.10771341885614291,
+      "grad_norm": 1.1841633319854736,
+      "learning_rate": 4.889653340498669e-05,
+      "loss": 2.0166,
+      "step": 4278
+    },
+    {
+      "epoch": 0.1084939508768396,
+      "grad_norm": 1.2198415994644165,
+      "learning_rate": 4.8871723057776664e-05,
+      "loss": 2.0164,
+      "step": 4309
+    },
+    {
+      "epoch": 0.10927448289753629,
+      "grad_norm": 1.2284913063049316,
+      "learning_rate": 4.8846643321416476e-05,
+      "loss": 2.015,
+      "step": 4340
+    },
+    {
+      "epoch": 0.11005501491823298,
+      "grad_norm": 1.2090349197387695,
+      "learning_rate": 4.882129447892753e-05,
+      "loss": 2.0094,
+      "step": 4371
+    },
+    {
+      "epoch": 0.11083554693892966,
+      "grad_norm": 1.215232491493225,
+      "learning_rate": 4.8795676816368076e-05,
+      "loss": 2.0045,
+      "step": 4402
+    },
+    {
+      "epoch": 0.11161607895962636,
+      "grad_norm": 1.2804045677185059,
+      "learning_rate": 4.876979062282995e-05,
+      "loss": 1.9899,
+      "step": 4433
+    },
+    {
+      "epoch": 0.11239661098032304,
+      "grad_norm": 1.2405016422271729,
+      "learning_rate": 4.8743636190435325e-05,
+      "loss": 2.0093,
+      "step": 4464
+    },
+    {
+      "epoch": 0.11317714300101973,
+      "grad_norm": 1.1784151792526245,
+      "learning_rate": 4.871721381433344e-05,
+      "loss": 2.0036,
+      "step": 4495
+    },
+    {
+      "epoch": 0.11395767502171641,
+      "grad_norm": 1.185738205909729,
+      "learning_rate": 4.869052379269719e-05,
+      "loss": 2.0033,
+      "step": 4526
+    },
+    {
+      "epoch": 0.11473820704241311,
+      "grad_norm": 1.1984614133834839,
+      "learning_rate": 4.866356642671985e-05,
+      "loss": 2.025,
+      "step": 4557
+    },
+    {
+      "epoch": 0.11551873906310979,
+      "grad_norm": 1.1734029054641724,
+      "learning_rate": 4.8636342020611634e-05,
+      "loss": 2.0023,
+      "step": 4588
+    },
+    {
+      "epoch": 0.11629927108380649,
+      "grad_norm": 1.198611855506897,
+      "learning_rate": 4.860885088159626e-05,
+      "loss": 2.0031,
+      "step": 4619
+    },
+    {
+      "epoch": 0.11707980310450317,
+      "grad_norm": 1.1793649196624756,
+      "learning_rate": 4.858109331990751e-05,
+      "loss": 1.9806,
+      "step": 4650
+    },
+    {
+      "epoch": 0.11786033512519985,
+      "grad_norm": 1.1945818662643433,
+      "learning_rate": 4.855306964878567e-05,
+      "loss": 1.9855,
+      "step": 4681
+    },
+    {
+      "epoch": 0.11864086714589654,
+      "grad_norm": 1.1875253915786743,
+      "learning_rate": 4.8524780184474084e-05,
+      "loss": 1.9883,
+      "step": 4712
+    },
+    {
+      "epoch": 0.11942139916659322,
+      "grad_norm": 1.1512328386306763,
+      "learning_rate": 4.8496225246215496e-05,
+      "loss": 1.9807,
+      "step": 4743
+    },
+    {
+      "epoch": 0.12020193118728992,
+      "grad_norm": 1.2059484720230103,
+      "learning_rate": 4.8467405156248505e-05,
+      "loss": 2.0103,
+      "step": 4774
+    },
+    {
+      "epoch": 0.1209824632079866,
+      "grad_norm": 1.1759779453277588,
+      "learning_rate": 4.843832023980392e-05,
+      "loss": 1.9754,
+      "step": 4805
+    },
+    {
+      "epoch": 0.1217629952286833,
+      "grad_norm": 1.2004414796829224,
+      "learning_rate": 4.840897082510106e-05,
+      "loss": 1.9893,
+      "step": 4836
+    },
+    {
+      "epoch": 0.12254352724937997,
+      "grad_norm": 1.1744251251220703,
+      "learning_rate": 4.8379357243344084e-05,
+      "loss": 1.9848,
+      "step": 4867
+    },
+    {
+      "epoch": 0.12332405927007667,
+      "grad_norm": 1.1731071472167969,
+      "learning_rate": 4.8349479828718236e-05,
+      "loss": 1.9945,
+      "step": 4898
+    },
+    {
+      "epoch": 0.12410459129077335,
+      "grad_norm": 1.2002074718475342,
+      "learning_rate": 4.8319338918386075e-05,
+      "loss": 1.9869,
+      "step": 4929
+    },
+    {
+      "epoch": 0.12488512331147004,
+      "grad_norm": 1.147085189819336,
+      "learning_rate": 4.828893485248369e-05,
+      "loss": 1.9876,
+      "step": 4960
+    },
+    {
+      "epoch": 0.12566565533216673,
+      "grad_norm": 1.1605637073516846,
+      "learning_rate": 4.825826797411682e-05,
+      "loss": 1.9858,
+      "step": 4991
+    },
+    {
+      "epoch": 0.12644618735286342,
+      "grad_norm": 1.1823869943618774,
+      "learning_rate": 4.822733862935702e-05,
+      "loss": 1.9617,
+      "step": 5022
+    },
+    {
+      "epoch": 0.12722671937356012,
+      "grad_norm": 1.1143817901611328,
+      "learning_rate": 4.819614716723775e-05,
+      "loss": 1.9756,
+      "step": 5053
+    },
+    {
+      "epoch": 0.12800725139425678,
+      "grad_norm": 1.1646877527236938,
+      "learning_rate": 4.8164693939750425e-05,
+      "loss": 2.0005,
+      "step": 5084
+    },
+    {
+      "epoch": 0.12878778341495348,
+      "grad_norm": 1.1390529870986938,
+      "learning_rate": 4.813297930184042e-05,
+      "loss": 1.9943,
+      "step": 5115
+    },
+    {
+      "epoch": 0.12956831543565017,
+      "grad_norm": 1.1759583950042725,
+      "learning_rate": 4.810100361140314e-05,
+      "loss": 1.9772,
+      "step": 5146
+    },
+    {
+      "epoch": 0.13034884745634687,
+      "grad_norm": 1.1465727090835571,
+      "learning_rate": 4.8068767229279885e-05,
+      "loss": 1.9563,
+      "step": 5177
+    },
+    {
+      "epoch": 0.13112937947704353,
+      "grad_norm": 1.2573471069335938,
+      "learning_rate": 4.8036270519253854e-05,
+      "loss": 1.9735,
+      "step": 5208
+    },
+    {
+      "epoch": 0.13190991149774023,
+      "grad_norm": 1.1301871538162231,
+      "learning_rate": 4.8003513848046e-05,
+      "loss": 1.987,
+      "step": 5239
+    },
+    {
+      "epoch": 0.13269044351843692,
+      "grad_norm": 1.1424096822738647,
+      "learning_rate": 4.79704975853109e-05,
+      "loss": 1.9661,
+      "step": 5270
+    },
+    {
+      "epoch": 0.13347097553913362,
+      "grad_norm": 1.131800889968872,
+      "learning_rate": 4.793722210363262e-05,
+      "loss": 1.9828,
+      "step": 5301
+    },
+    {
+      "epoch": 0.13425150755983029,
+      "grad_norm": 1.1227242946624756,
+      "learning_rate": 4.7903687778520414e-05,
+      "loss": 1.975,
+      "step": 5332
+    },
+    {
+      "epoch": 0.13503203958052698,
+      "grad_norm": 1.143832802772522,
+      "learning_rate": 4.7869894988404593e-05,
+      "loss": 1.9619,
+      "step": 5363
+    },
+    {
+      "epoch": 0.13581257160122367,
+      "grad_norm": 1.1281683444976807,
+      "learning_rate": 4.783584411463221e-05,
+      "loss": 1.9603,
+      "step": 5394
+    },
+    {
+      "epoch": 0.13659310362192037,
+      "grad_norm": 1.134901762008667,
+      "learning_rate": 4.780153554146274e-05,
+      "loss": 1.9888,
+      "step": 5425
+    },
+    {
+      "epoch": 0.13737363564261704,
+      "grad_norm": 1.1317532062530518,
+      "learning_rate": 4.7766969656063766e-05,
+      "loss": 1.9793,
+      "step": 5456
+    },
+    {
+      "epoch": 0.13815416766331373,
+      "grad_norm": 1.2516345977783203,
+      "learning_rate": 4.773214684850662e-05,
+      "loss": 1.9839,
+      "step": 5487
+    },
+    {
+      "epoch": 0.13893469968401043,
+      "grad_norm": 1.107391119003296,
+      "learning_rate": 4.769706751176193e-05,
+      "loss": 1.9606,
+      "step": 5518
+    },
+    {
+      "epoch": 0.13971523170470712,
+      "grad_norm": 1.1041492223739624,
+      "learning_rate": 4.7661732041695264e-05,
+      "loss": 1.9688,
+      "step": 5549
+    },
+    {
+      "epoch": 0.1404957637254038,
+      "grad_norm": 1.1099929809570312,
+      "learning_rate": 4.762614083706258e-05,
+      "loss": 1.9821,
+      "step": 5580
+    },
+    {
+      "epoch": 0.14127629574610048,
+      "grad_norm": 1.167151927947998,
+      "learning_rate": 4.759029429950581e-05,
+      "loss": 1.9669,
+      "step": 5611
+    },
+    {
+      "epoch": 0.14205682776679718,
+      "grad_norm": 1.0942577123641968,
+      "learning_rate": 4.7554192833548235e-05,
+      "loss": 1.9565,
+      "step": 5642
+    },
+    {
+      "epoch": 0.14283735978749387,
+      "grad_norm": 1.0859640836715698,
+      "learning_rate": 4.751783684659e-05,
+      "loss": 1.9634,
+      "step": 5673
+    },
+    {
+      "epoch": 0.14361789180819054,
+      "grad_norm": 2.420607089996338,
+      "learning_rate": 4.748122674890348e-05,
+      "loss": 1.9365,
+      "step": 5704
+    },
+    {
+      "epoch": 0.14439842382888723,
+      "grad_norm": 1.0996880531311035,
+      "learning_rate": 4.7444362953628654e-05,
+      "loss": 1.9718,
+      "step": 5735
+    },
+    {
+      "epoch": 0.14517895584958393,
+      "grad_norm": 1.1183338165283203,
+      "learning_rate": 4.7407245876768424e-05,
+      "loss": 1.9564,
+      "step": 5766
+    },
+    {
+      "epoch": 0.14595948787028062,
+      "grad_norm": 1.1093947887420654,
+      "learning_rate": 4.736987593718397e-05,
+      "loss": 1.9516,
+      "step": 5797
+    },
+    {
+      "epoch": 0.1467400198909773,
+      "grad_norm": 1.141797423362732,
+      "learning_rate": 4.733225355658999e-05,
+      "loss": 1.929,
+      "step": 5828
+    },
+    {
+      "epoch": 0.14752055191167399,
+      "grad_norm": 1.1214358806610107,
+      "learning_rate": 4.7294379159549926e-05,
+      "loss": 1.9297,
+      "step": 5859
+    },
+    {
+      "epoch": 0.14830108393237068,
+      "grad_norm": 1.1025431156158447,
+      "learning_rate": 4.725625317347119e-05,
+      "loss": 1.9226,
+      "step": 5890
+    },
+    {
+      "epoch": 0.14908161595306738,
+      "grad_norm": 1.1094226837158203,
+      "learning_rate": 4.7217876028600374e-05,
+      "loss": 1.946,
+      "step": 5921
+    },
+    {
+      "epoch": 0.14986214797376404,
+      "grad_norm": 1.0909287929534912,
+      "learning_rate": 4.717924815801832e-05,
+      "loss": 1.9511,
+      "step": 5952
+    },
+    {
+      "epoch": 0.15064267999446074,
+      "grad_norm": 1.0755189657211304,
+      "learning_rate": 4.714036999763532e-05,
+      "loss": 1.939,
+      "step": 5983
+    },
+    {
+      "epoch": 0.15142321201515743,
+      "grad_norm": 1.1426901817321777,
+      "learning_rate": 4.7101241986186116e-05,
+      "loss": 1.93,
+      "step": 6014
+    },
+    {
+      "epoch": 0.15220374403585413,
+      "grad_norm": 1.1208311319351196,
+      "learning_rate": 4.7061864565225e-05,
+      "loss": 1.9516,
+      "step": 6045
+    },
+    {
+      "epoch": 0.1529842760565508,
+      "grad_norm": 1.0931717157363892,
+      "learning_rate": 4.702223817912081e-05,
+      "loss": 1.9314,
+      "step": 6076
+    },
+    {
+      "epoch": 0.1537648080772475,
+      "grad_norm": 1.075864553451538,
+      "learning_rate": 4.698236327505195e-05,
+      "loss": 1.935,
+      "step": 6107
+    },
+    {
+      "epoch": 0.15454534009794418,
+      "grad_norm": 1.090559720993042,
+      "learning_rate": 4.694224030300127e-05,
+      "loss": 1.9431,
+      "step": 6138
+    },
+    {
+      "epoch": 0.15532587211864088,
+      "grad_norm": 1.0956670045852661,
+      "learning_rate": 4.690186971575107e-05,
+      "loss": 1.9678,
+      "step": 6169
+    },
+    {
+      "epoch": 0.15610640413933755,
+      "grad_norm": 1.125927448272705,
+      "learning_rate": 4.6861251968877916e-05,
+      "loss": 1.9292,
+      "step": 6200
+    },
+    {
+      "epoch": 0.15688693616003424,
+      "grad_norm": 1.0844208002090454,
+      "learning_rate": 4.68203875207476e-05,
+      "loss": 1.9189,
+      "step": 6231
+    },
+    {
+      "epoch": 0.15766746818073094,
+      "grad_norm": 1.064327597618103,
+      "learning_rate": 4.677927683250983e-05,
+      "loss": 1.928,
+      "step": 6262
+    },
+    {
+      "epoch": 0.15844800020142763,
+      "grad_norm": 1.1281861066818237,
+      "learning_rate": 4.6737920368093156e-05,
+      "loss": 1.9437,
+      "step": 6293
+    },
+    {
+      "epoch": 0.1592285322221243,
+      "grad_norm": 1.0674384832382202,
+      "learning_rate": 4.669631859419965e-05,
+      "loss": 1.9347,
+      "step": 6324
+    },
+    {
+      "epoch": 0.160009064242821,
+      "grad_norm": 1.105566382408142,
+      "learning_rate": 4.6654471980299676e-05,
+      "loss": 1.9229,
+      "step": 6355
+    },
+    {
+      "epoch": 0.1607895962635177,
+      "grad_norm": 1.0582126379013062,
+      "learning_rate": 4.661238099862658e-05,
+      "loss": 1.9321,
+      "step": 6386
+    },
+    {
+      "epoch": 0.16157012828421438,
+      "grad_norm": 1.1147974729537964,
+      "learning_rate": 4.657004612417138e-05,
+      "loss": 1.9289,
+      "step": 6417
+    },
+    {
+      "epoch": 0.16235066030491105,
+      "grad_norm": 1.0804343223571777,
+      "learning_rate": 4.6527467834677374e-05,
+      "loss": 1.9307,
+      "step": 6448
+    },
+    {
+      "epoch": 0.16313119232560774,
+      "grad_norm": 1.0830508470535278,
+      "learning_rate": 4.648464661063478e-05,
+      "loss": 1.9408,
+      "step": 6479
+    },
+    {
+      "epoch": 0.16391172434630444,
+      "grad_norm": 1.0533562898635864,
+      "learning_rate": 4.6441582935275264e-05,
+      "loss": 1.9347,
+      "step": 6510
+    },
+    {
+      "epoch": 0.16469225636700113,
+      "grad_norm": 1.044925332069397,
+      "learning_rate": 4.6398277294566586e-05,
+      "loss": 1.9112,
+      "step": 6541
+    },
+    {
+      "epoch": 0.1654727883876978,
+      "grad_norm": 1.087296962738037,
+      "learning_rate": 4.6354730177207e-05,
+      "loss": 1.9381,
+      "step": 6572
+    },
+    {
+      "epoch": 0.1662533204083945,
+      "grad_norm": 1.0853668451309204,
+      "learning_rate": 4.6310942074619787e-05,
+      "loss": 1.9224,
+      "step": 6603
+    },
+    {
+      "epoch": 0.1670338524290912,
+      "grad_norm": 1.0661752223968506,
+      "learning_rate": 4.626691348094777e-05,
+      "loss": 1.9386,
+      "step": 6634
+    },
+    {
+      "epoch": 0.16781438444978788,
+      "grad_norm": 1.0393208265304565,
+      "learning_rate": 4.622264489304762e-05,
+      "loss": 1.9266,
+      "step": 6665
+    },
+    {
+      "epoch": 0.16859491647048455,
+      "grad_norm": 1.0324763059616089,
+      "learning_rate": 4.617813681048434e-05,
+      "loss": 1.919,
+      "step": 6696
+    },
+    {
+      "epoch": 0.16937544849118125,
+      "grad_norm": 1.0684878826141357,
+      "learning_rate": 4.61333897355256e-05,
+      "loss": 1.9321,
+      "step": 6727
+    },
+    {
+      "epoch": 0.17015598051187794,
+      "grad_norm": 1.0477505922317505,
+      "learning_rate": 4.608840417313604e-05,
+      "loss": 1.9449,
+      "step": 6758
+    },
+    {
+      "epoch": 0.17093651253257464,
+      "grad_norm": 1.0684869289398193,
+      "learning_rate": 4.6043180630971646e-05,
+      "loss": 1.9252,
+      "step": 6789
+    },
+    {
+      "epoch": 0.1717170445532713,
+      "grad_norm": 1.0869554281234741,
+      "learning_rate": 4.599771961937391e-05,
+      "loss": 1.9183,
+      "step": 6820
+    },
+    {
+      "epoch": 0.172497576573968,
+      "grad_norm": 1.0297125577926636,
+      "learning_rate": 4.5952021651364204e-05,
+      "loss": 1.9123,
+      "step": 6851
+    },
+    {
+      "epoch": 0.1732781085946647,
+      "grad_norm": 1.0670006275177002,
+      "learning_rate": 4.590608724263786e-05,
+      "loss": 1.9353,
+      "step": 6882
+    },
+    {
+      "epoch": 0.1740586406153614,
+      "grad_norm": 1.0744417905807495,
+      "learning_rate": 4.585991691155845e-05,
+      "loss": 1.8979,
+      "step": 6913
+    },
+    {
+      "epoch": 0.17483917263605805,
+      "grad_norm": 1.0910695791244507,
+      "learning_rate": 4.581351117915188e-05,
+      "loss": 1.9153,
+      "step": 6944
+    },
+    {
+      "epoch": 0.17561970465675475,
+      "grad_norm": 1.083776593208313,
+      "learning_rate": 4.5766870569100534e-05,
+      "loss": 1.9026,
+      "step": 6975
+    },
+    {
+      "epoch": 0.17640023667745144,
+      "grad_norm": 1.0857270956039429,
+      "learning_rate": 4.571999560773736e-05,
+      "loss": 1.9279,
+      "step": 7006
+    },
+    {
+      "epoch": 0.1771807686981481,
+      "grad_norm": 1.0350106954574585,
+      "learning_rate": 4.5672886824039915e-05,
+      "loss": 1.9236,
+      "step": 7037
+    },
+    {
+      "epoch": 0.1779613007188448,
+      "grad_norm": 1.0498634576797485,
+      "learning_rate": 4.5625544749624435e-05,
+      "loss": 1.8934,
+      "step": 7068
+    },
+    {
+      "epoch": 0.1787418327395415,
+      "grad_norm": 1.0836471319198608,
+      "learning_rate": 4.5577969918739794e-05,
+      "loss": 1.9131,
+      "step": 7099
+    },
+    {
+      "epoch": 0.1795223647602382,
+      "grad_norm": 1.0414760112762451,
+      "learning_rate": 4.5530162868261486e-05,
+      "loss": 1.8792,
+      "step": 7130
+    },
+    {
+      "epoch": 0.18030289678093486,
+      "grad_norm": 1.0747581720352173,
+      "learning_rate": 4.548212413768558e-05,
+      "loss": 1.8973,
+      "step": 7161
+    },
+    {
+      "epoch": 0.18108342880163156,
+      "grad_norm": 1.0464451313018799,
+      "learning_rate": 4.543385426912261e-05,
+      "loss": 1.907,
+      "step": 7192
+    },
+    {
+      "epoch": 0.18186396082232825,
+      "grad_norm": 1.0159403085708618,
+      "learning_rate": 4.53853538072915e-05,
+      "loss": 1.9111,
+      "step": 7223
+    },
+    {
+      "epoch": 0.18264449284302495,
+      "grad_norm": 1.093883991241455,
+      "learning_rate": 4.533662329951336e-05,
+      "loss": 1.8927,
+      "step": 7254
+    },
+    {
+      "epoch": 0.18342502486372161,
+      "grad_norm": 1.0358048677444458,
+      "learning_rate": 4.528766329570536e-05,
+      "loss": 1.9164,
+      "step": 7285
+    },
+    {
+      "epoch": 0.1842055568844183,
+      "grad_norm": 1.051798939704895,
+      "learning_rate": 4.523847434837447e-05,
+      "loss": 1.9084,
+      "step": 7316
+    },
+    {
+      "epoch": 0.184986088905115,
+      "grad_norm": 1.0729514360427856,
+      "learning_rate": 4.518905701261128e-05,
+      "loss": 1.9089,
+      "step": 7347
+    },
+    {
+      "epoch": 0.1857666209258117,
+      "grad_norm": 1.0399775505065918,
+      "learning_rate": 4.5139411846083715e-05,
+      "loss": 1.922,
+      "step": 7378
+    },
+    {
+      "epoch": 0.18654715294650837,
+      "grad_norm": 1.0500715970993042,
+      "learning_rate": 4.508953940903073e-05,
+      "loss": 1.9118,
+      "step": 7409
+    },
+    {
+      "epoch": 0.18732768496720506,
+      "grad_norm": 1.0770058631896973,
+      "learning_rate": 4.5039440264255994e-05,
+      "loss": 1.9059,
+      "step": 7440
+    },
+    {
+      "epoch": 0.18810821698790176,
+      "grad_norm": 1.0471183061599731,
+      "learning_rate": 4.498911497712155e-05,
+      "loss": 1.9119,
+      "step": 7471
+    },
+    {
+      "epoch": 0.18888874900859845,
+      "grad_norm": 1.038761019706726,
+      "learning_rate": 4.493856411554142e-05,
+      "loss": 1.8798,
+      "step": 7502
+    },
+    {
+      "epoch": 0.18966928102929512,
+      "grad_norm": 1.0365252494812012,
+      "learning_rate": 4.4887788249975206e-05,
+      "loss": 1.8983,
+      "step": 7533
+    },
+    {
+      "epoch": 0.1904498130499918,
+      "grad_norm": 1.1033800840377808,
+      "learning_rate": 4.4836787953421656e-05,
+      "loss": 1.8911,
+      "step": 7564
+    },
+    {
+      "epoch": 0.1912303450706885,
+      "grad_norm": 1.064213514328003,
+      "learning_rate": 4.478556380141218e-05,
+      "loss": 1.8995,
+      "step": 7595
+    },
+    {
+      "epoch": 0.1920108770913852,
+      "grad_norm": 0.997905969619751,
+      "learning_rate": 4.4734116372004375e-05,
+      "loss": 1.8705,
+      "step": 7626
+    },
+    {
+      "epoch": 0.19279140911208187,
+      "grad_norm": 1.0392402410507202,
+      "learning_rate": 4.4682446245775477e-05,
+      "loss": 1.9105,
+      "step": 7657
+    },
+    {
+      "epoch": 0.19357194113277856,
+      "grad_norm": 1.0340332984924316,
+      "learning_rate": 4.463055400581586e-05,
+      "loss": 1.9074,
+      "step": 7688
+    },
+    {
+      "epoch": 0.19435247315347526,
+      "grad_norm": 1.0196648836135864,
+      "learning_rate": 4.4578440237722374e-05,
+      "loss": 1.9059,
+      "step": 7719
+    },
+    {
+      "epoch": 0.19513300517417195,
+      "grad_norm": 0.99578458070755,
+      "learning_rate": 4.452610552959183e-05,
+      "loss": 1.8974,
+      "step": 7750
+    },
+    {
+      "epoch": 0.19591353719486862,
+      "grad_norm": 1.026090145111084,
+      "learning_rate": 4.447355047201428e-05,
+      "loss": 1.8886,
+      "step": 7781
+    },
+    {
+      "epoch": 0.19669406921556531,
+      "grad_norm": 0.9945096969604492,
+      "learning_rate": 4.4420775658066414e-05,
+      "loss": 1.8879,
+      "step": 7812
+    },
+    {
+      "epoch": 0.197474601236262,
+      "grad_norm": 1.0226850509643555,
+      "learning_rate": 4.436778168330484e-05,
+      "loss": 1.8936,
+      "step": 7843
+    },
+    {
+      "epoch": 0.1982551332569587,
+      "grad_norm": 1.0433967113494873,
+      "learning_rate": 4.4314569145759353e-05,
+      "loss": 1.882,
+      "step": 7874
+    },
+    {
+      "epoch": 0.19903566527765537,
+      "grad_norm": 1.0612221956253052,
+      "learning_rate": 4.42611386459262e-05,
+      "loss": 1.8879,
+      "step": 7905
+    },
+    {
+      "epoch": 0.19981619729835207,
+      "grad_norm": 1.0252665281295776,
+      "learning_rate": 4.420749078676133e-05,
+      "loss": 1.9005,
+      "step": 7936
+    },
+    {
+      "epoch": 0.20059672931904876,
+      "grad_norm": 1.015100359916687,
+      "learning_rate": 4.4153626173673516e-05,
+      "loss": 1.8944,
+      "step": 7967
+    },
+    {
+      "epoch": 0.20137726133974546,
+      "grad_norm": 1.0417771339416504,
+      "learning_rate": 4.409954541451762e-05,
+      "loss": 1.8837,
+      "step": 7998
+    },
+    {
+      "epoch": 0.20215779336044212,
+      "grad_norm": 1.026708960533142,
+      "learning_rate": 4.404524911958764e-05,
+      "loss": 1.92,
+      "step": 8029
+    },
+    {
+      "epoch": 0.20293832538113882,
+      "grad_norm": 1.0414159297943115,
+      "learning_rate": 4.399073790160989e-05,
+      "loss": 1.8709,
+      "step": 8060
+    },
+    {
+      "epoch": 0.2037188574018355,
+      "grad_norm": 1.014039397239685,
+      "learning_rate": 4.393601237573607e-05,
+      "loss": 1.8842,
+      "step": 8091
+    },
+    {
+      "epoch": 0.2044993894225322,
+      "grad_norm": 1.0103037357330322,
+      "learning_rate": 4.388107315953628e-05,
+      "loss": 1.8889,
+      "step": 8122
+    },
+    {
+      "epoch": 0.20527992144322887,
+      "grad_norm": 1.0166395902633667,
+      "learning_rate": 4.382592087299212e-05,
+      "loss": 1.8808,
+      "step": 8153
+    },
+    {
+      "epoch": 0.20606045346392557,
+      "grad_norm": 1.023850679397583,
+      "learning_rate": 4.377055613848964e-05,
+      "loss": 1.8918,
+      "step": 8184
+    },
+    {
+      "epoch": 0.20684098548462226,
+      "grad_norm": 1.0251572132110596,
+      "learning_rate": 4.3714979580812355e-05,
+      "loss": 1.882,
+      "step": 8215
+    },
+    {
+      "epoch": 0.20762151750531896,
+      "grad_norm": 1.0183281898498535,
+      "learning_rate": 4.365919182713416e-05,
+      "loss": 1.8844,
+      "step": 8246
+    },
+    {
+      "epoch": 0.20840204952601563,
+      "grad_norm": 1.0135486125946045,
+      "learning_rate": 4.360319350701226e-05,
+      "loss": 1.8814,
+      "step": 8277
+    },
+    {
+      "epoch": 0.20918258154671232,
+      "grad_norm": 1.0247812271118164,
+      "learning_rate": 4.3546985252380115e-05,
+      "loss": 1.8818,
+      "step": 8308
+    },
+    {
+      "epoch": 0.20996311356740902,
+      "grad_norm": 1.0123242139816284,
+      "learning_rate": 4.349056769754021e-05,
+      "loss": 1.8723,
+      "step": 8339
+    },
+    {
+      "epoch": 0.2107436455881057,
+      "grad_norm": 1.0139250755310059,
+      "learning_rate": 4.3433941479156994e-05,
+      "loss": 1.8858,
+      "step": 8370
+    },
+    {
+      "epoch": 0.21152417760880238,
+      "grad_norm": 4.008477687835693,
+      "learning_rate": 4.3377107236249647e-05,
+      "loss": 1.8735,
+      "step": 8401
+    },
+    {
+      "epoch": 0.21230470962949907,
+      "grad_norm": 1.0454871654510498,
+      "learning_rate": 4.332006561018488e-05,
+      "loss": 1.8824,
+      "step": 8432
+    },
+    {
+      "epoch": 0.21308524165019577,
+      "grad_norm": 1.0586799383163452,
+      "learning_rate": 4.3262817244669683e-05,
+      "loss": 1.8992,
+      "step": 8463
+    },
+    {
+      "epoch": 0.21386577367089246,
+      "grad_norm": 1.0073469877243042,
+      "learning_rate": 4.3205362785744083e-05,
+      "loss": 1.8766,
+      "step": 8494
+    },
+    {
+      "epoch": 0.21464630569158913,
+      "grad_norm": 0.9976999759674072,
+      "learning_rate": 4.314770288177384e-05,
+      "loss": 1.8864,
+      "step": 8525
+    },
+    {
+      "epoch": 0.21542683771228582,
+      "grad_norm": 0.9928112030029297,
+      "learning_rate": 4.308983818344313e-05,
+      "loss": 1.8874,
+      "step": 8556
+    },
+    {
+      "epoch": 0.21620736973298252,
+      "grad_norm": 1.038405418395996,
+      "learning_rate": 4.3031769343747206e-05,
+      "loss": 1.8725,
+      "step": 8587
+    },
+    {
+      "epoch": 0.2169879017536792,
+      "grad_norm": 1.0328835248947144,
+      "learning_rate": 4.297349701798505e-05,
+      "loss": 1.8884,
+      "step": 8618
+    },
+    {
+      "epoch": 0.21776843377437588,
+      "grad_norm": 1.0254933834075928,
+      "learning_rate": 4.2915021863751916e-05,
+      "loss": 1.8611,
+      "step": 8649
+    },
+    {
+      "epoch": 0.21854896579507258,
+      "grad_norm": 0.99531090259552,
+      "learning_rate": 4.285634454093198e-05,
+      "loss": 1.8889,
+      "step": 8680
+    },
+    {
+      "epoch": 0.21932949781576927,
+      "grad_norm": 1.0536468029022217,
+      "learning_rate": 4.279746571169086e-05,
+      "loss": 1.8875,
+      "step": 8711
+    },
+    {
+      "epoch": 0.22011002983646596,
+      "grad_norm": 0.9915075898170471,
+      "learning_rate": 4.2738386040468136e-05,
+      "loss": 1.8901,
+      "step": 8742
+    },
+    {
+      "epoch": 0.22089056185716263,
+      "grad_norm": 0.9883093237876892,
+      "learning_rate": 4.2679106193969866e-05,
+      "loss": 1.8704,
+      "step": 8773
+    },
+    {
+      "epoch": 0.22167109387785933,
+      "grad_norm": 1.0425434112548828,
+      "learning_rate": 4.261962684116106e-05,
+      "loss": 1.8643,
+      "step": 8804
+    },
+    {
+      "epoch": 0.22245162589855602,
+      "grad_norm": 1.0154091119766235,
+      "learning_rate": 4.2559948653258145e-05,
+      "loss": 1.8806,
+      "step": 8835
+    },
+    {
+      "epoch": 0.22323215791925272,
+      "grad_norm": 1.0432935953140259,
+      "learning_rate": 4.250007230372134e-05,
+      "loss": 1.8928,
+      "step": 8866
+    },
+    {
+      "epoch": 0.22401268993994938,
+      "grad_norm": 0.9709262251853943,
+      "learning_rate": 4.2439998468247126e-05,
+      "loss": 1.8591,
+      "step": 8897
+    },
+    {
+      "epoch": 0.22479322196064608,
+      "grad_norm": 0.9708088636398315,
+      "learning_rate": 4.2379727824760566e-05,
+      "loss": 1.8797,
+      "step": 8928
+    },
+    {
+      "epoch": 0.22557375398134277,
+      "grad_norm": 0.9911683201789856,
+      "learning_rate": 4.231926105340768e-05,
+      "loss": 1.8456,
+      "step": 8959
+    },
+    {
+      "epoch": 0.22635428600203947,
+      "grad_norm": 0.99161297082901,
+      "learning_rate": 4.225859883654776e-05,
+      "loss": 1.8712,
+      "step": 8990
+    },
+    {
+      "epoch": 0.22713481802273613,
+      "grad_norm": 1.0025807619094849,
+      "learning_rate": 4.219774185874569e-05,
+      "loss": 1.8814,
+      "step": 9021
+    },
+    {
+      "epoch": 0.22791535004343283,
+      "grad_norm": 0.9597026109695435,
+      "learning_rate": 4.213669080676418e-05,
+      "loss": 1.8799,
+      "step": 9052
+    },
+    {
+      "epoch": 0.22869588206412952,
+      "grad_norm": 1.0001273155212402,
+      "learning_rate": 4.2075446369556056e-05,
+      "loss": 1.8469,
+      "step": 9083
+    },
+    {
+      "epoch": 0.22947641408482622,
+      "grad_norm": 0.9670659303665161,
+      "learning_rate": 4.201400923825648e-05,
+      "loss": 1.8612,
+      "step": 9114
+    },
+    {
+      "epoch": 0.23025694610552289,
+      "grad_norm": 1.018050193786621,
+      "learning_rate": 4.195238010617511e-05,
+      "loss": 1.8656,
+      "step": 9145
+    },
+    {
+      "epoch": 0.23103747812621958,
+      "grad_norm": 0.9838584661483765,
+      "learning_rate": 4.1890559668788344e-05,
+      "loss": 1.8527,
+      "step": 9176
+    },
+    {
+      "epoch": 0.23181801014691628,
+      "grad_norm": 0.9968937635421753,
+      "learning_rate": 4.1828548623731405e-05,
+      "loss": 1.8753,
+      "step": 9207
+    },
+    {
+      "epoch": 0.23259854216761297,
+      "grad_norm": 0.9698464870452881,
+      "learning_rate": 4.1766347670790506e-05,
+      "loss": 1.8716,
+      "step": 9238
+    },
+    {
+      "epoch": 0.23337907418830964,
+      "grad_norm": 0.9592704772949219,
+      "learning_rate": 4.170395751189495e-05,
+      "loss": 1.8698,
+      "step": 9269
+    },
+    {
+      "epoch": 0.23415960620900633,
+      "grad_norm": 0.9904705286026001,
+      "learning_rate": 4.164137885110921e-05,
+      "loss": 1.8661,
+      "step": 9300
+    },
+    {
+      "epoch": 0.23494013822970303,
+      "grad_norm": 1.0243868827819824,
+      "learning_rate": 4.157861239462495e-05,
+      "loss": 1.8658,
+      "step": 9331
+    },
+    {
+      "epoch": 0.2357206702503997,
+      "grad_norm": 0.9936602711677551,
+      "learning_rate": 4.1515658850753114e-05,
+      "loss": 1.8475,
+      "step": 9362
+    },
+    {
+      "epoch": 0.2365012022710964,
+      "grad_norm": 0.9626069068908691,
+      "learning_rate": 4.145251892991588e-05,
+      "loss": 1.8507,
+      "step": 9393
+    },
+    {
+      "epoch": 0.23728173429179308,
+      "grad_norm": 0.9688258767127991,
+      "learning_rate": 4.138919334463868e-05,
+      "loss": 1.8628,
+      "step": 9424
+    },
+    {
+      "epoch": 0.23806226631248978,
+      "grad_norm": 0.9996054172515869,
+      "learning_rate": 4.1325682809542124e-05,
+      "loss": 1.8734,
+      "step": 9455
+    },
+    {
+      "epoch": 0.23884279833318645,
+      "grad_norm": 1.0037505626678467,
+      "learning_rate": 4.126198804133398e-05,
+      "loss": 1.8778,
+      "step": 9486
+    },
+    {
+      "epoch": 0.23962333035388314,
+      "grad_norm": 0.9751474857330322,
+      "learning_rate": 4.1198109758801055e-05,
+      "loss": 1.8615,
+      "step": 9517
+    },
+    {
+      "epoch": 0.24040386237457984,
+      "grad_norm": 0.9760595560073853,
+      "learning_rate": 4.113404868280107e-05,
+      "loss": 1.8614,
+      "step": 9548
+    },
+    {
+      "epoch": 0.24118439439527653,
+      "grad_norm": 1.0009572505950928,
+      "learning_rate": 4.106980553625457e-05,
+      "loss": 1.8762,
+      "step": 9579
+    },
+    {
+      "epoch": 0.2419649264159732,
+      "grad_norm": 0.983182966709137,
+      "learning_rate": 4.100538104413674e-05,
+      "loss": 1.857,
+      "step": 9610
+    },
+    {
+      "epoch": 0.2427454584366699,
+      "grad_norm": 1.0748534202575684,
+      "learning_rate": 4.09407759334692e-05,
+      "loss": 1.8658,
+      "step": 9641
+    },
+    {
+      "epoch": 0.2435259904573666,
+      "grad_norm": 0.9747381806373596,
+      "learning_rate": 4.087599093331186e-05,
+      "loss": 1.8484,
+      "step": 9672
+    },
+    {
+      "epoch": 0.24430652247806328,
+      "grad_norm": 0.9784808158874512,
+      "learning_rate": 4.081102677475462e-05,
+      "loss": 1.8492,
+      "step": 9703
+    },
+    {
+      "epoch": 0.24508705449875995,
+      "grad_norm": 0.9820215106010437,
+      "learning_rate": 4.0745884190909194e-05,
+      "loss": 1.8516,
+      "step": 9734
+    },
+    {
+      "epoch": 0.24586758651945664,
+      "grad_norm": 0.9536774158477783,
+      "learning_rate": 4.0680563916900796e-05,
+      "loss": 1.8444,
+      "step": 9765
+    },
+    {
+      "epoch": 0.24664811854015334,
+      "grad_norm": 0.9706370234489441,
+      "learning_rate": 4.0615066689859815e-05,
+      "loss": 1.8477,
+      "step": 9796
+    },
+    {
+      "epoch": 0.24742865056085003,
+      "grad_norm": 0.9700275659561157,
+      "learning_rate": 4.0549393248913584e-05,
+      "loss": 1.8515,
+      "step": 9827
+    },
+    {
+      "epoch": 0.2482091825815467,
+      "grad_norm": 0.9522431492805481,
+      "learning_rate": 4.048354433517794e-05,
+      "loss": 1.8287,
+      "step": 9858
+    },
+    {
+      "epoch": 0.2489897146022434,
+      "grad_norm": 0.9691547155380249,
+      "learning_rate": 4.0417520691748916e-05,
+      "loss": 1.8594,
+      "step": 9889
+    },
+    {
+      "epoch": 0.2497702466229401,
+      "grad_norm": 0.9588534235954285,
+      "learning_rate": 4.035132306369438e-05,
+      "loss": 1.8459,
+      "step": 9920
+    },
+    {
+      "epoch": 0.2505507786436368,
+      "grad_norm": 0.9900926351547241,
+      "learning_rate": 4.028495219804555e-05,
+      "loss": 1.8608,
+      "step": 9951
+    },
+    {
+      "epoch": 0.25133131066433345,
+      "grad_norm": 0.9539284110069275,
+      "learning_rate": 4.021840884378864e-05,
+      "loss": 1.8522,
+      "step": 9982
+    },
+    {
+      "epoch": 0.2521118426850302,
+      "grad_norm": 0.9557245969772339,
+      "learning_rate": 4.015169375185633e-05,
+      "loss": 1.8743,
+      "step": 10013
+    },
+    {
+      "epoch": 0.25289237470572684,
+      "grad_norm": 0.9317564964294434,
+      "learning_rate": 4.0084807675119396e-05,
+      "loss": 1.8384,
+      "step": 10044
+    },
+    {
+      "epoch": 0.2536729067264235,
+      "grad_norm": 0.9944160580635071,
+      "learning_rate": 4.0017751368378106e-05,
+      "loss": 1.857,
+      "step": 10075
+    },
+    {
+      "epoch": 0.25445343874712023,
+      "grad_norm": 0.9859464168548584,
+      "learning_rate": 3.995052558835377e-05,
+      "loss": 1.8484,
+      "step": 10106
+    },
+    {
+      "epoch": 0.2552339707678169,
+      "grad_norm": 1.0093594789505005,
+      "learning_rate": 3.988313109368017e-05,
+      "loss": 1.8506,
+      "step": 10137
+    },
+    {
+      "epoch": 0.25601450278851356,
+      "grad_norm": 0.9451240301132202,
+      "learning_rate": 3.981556864489504e-05,
+      "loss": 1.8732,
+      "step": 10168
+    },
+    {
+      "epoch": 0.2567950348092103,
+      "grad_norm": 0.972819447517395,
+      "learning_rate": 3.974783900443142e-05,
+      "loss": 1.856,
+      "step": 10199
+    },
+    {
+      "epoch": 0.25757556682990695,
+      "grad_norm": 0.996379554271698,
+      "learning_rate": 3.9679942936609095e-05,
+      "loss": 1.8299,
+      "step": 10230
+    },
+    {
+      "epoch": 0.2583560988506037,
+      "grad_norm": 2.503967046737671,
+      "learning_rate": 3.961188120762596e-05,
+      "loss": 1.8484,
+      "step": 10261
+    },
+    {
+      "epoch": 0.25913663087130034,
+      "grad_norm": 0.9491912126541138,
+      "learning_rate": 3.954365458554938e-05,
+      "loss": 1.8528,
+      "step": 10292
+    },
+    {
+      "epoch": 0.259917162891997,
+      "grad_norm": 0.9642863273620605,
+      "learning_rate": 3.947526384030751e-05,
+      "loss": 1.863,
+      "step": 10323
+    },
+    {
+      "epoch": 0.26069769491269373,
+      "grad_norm": 0.9915285706520081,
+      "learning_rate": 3.9406709743680624e-05,
+      "loss": 1.8191,
+      "step": 10354
+    },
+    {
+      "epoch": 0.2614782269333904,
+      "grad_norm": 1.0176483392715454,
+      "learning_rate": 3.9337993069292366e-05,
+      "loss": 1.8396,
+      "step": 10385
+    },
+    {
+      "epoch": 0.26225875895408707,
+      "grad_norm": 0.9567158222198486,
+      "learning_rate": 3.926911459260109e-05,
+      "loss": 1.8617,
+      "step": 10416
+    },
+    {
+      "epoch": 0.2630392909747838,
+      "grad_norm": 0.9236714839935303,
+      "learning_rate": 3.920007509089102e-05,
+      "loss": 1.8362,
+      "step": 10447
+    },
+    {
+      "epoch": 0.26381982299548046,
+      "grad_norm": 0.9428004026412964,
+      "learning_rate": 3.913087534326357e-05,
+      "loss": 1.8447,
+      "step": 10478
+    },
+    {
+      "epoch": 0.2646003550161772,
+      "grad_norm": 0.941067099571228,
+      "learning_rate": 3.9061516130628475e-05,
+      "loss": 1.8329,
+      "step": 10509
+    },
+    {
+      "epoch": 0.26538088703687385,
+      "grad_norm": 0.9685031175613403,
+      "learning_rate": 3.8991998235695025e-05,
+      "loss": 1.8543,
+      "step": 10540
+    },
+    {
+      "epoch": 0.2661614190575705,
+      "grad_norm": 0.9629632234573364,
+      "learning_rate": 3.8922322442963224e-05,
+      "loss": 1.8118,
+      "step": 10571
+    },
+    {
+      "epoch": 0.26694195107826724,
+      "grad_norm": 0.9536260366439819,
+      "learning_rate": 3.885248953871491e-05,
+      "loss": 1.8379,
+      "step": 10602
+    },
+    {
+      "epoch": 0.2677224830989639,
+      "grad_norm": 0.9781749248504639,
+      "learning_rate": 3.8782500311004915e-05,
+      "loss": 1.8419,
+      "step": 10633
+    },
+    {
+      "epoch": 0.26850301511966057,
+      "grad_norm": 0.9313937425613403,
+      "learning_rate": 3.871235554965218e-05,
+      "loss": 1.8467,
+      "step": 10664
+    },
+    {
+      "epoch": 0.2692835471403573,
+      "grad_norm": 0.9775392413139343,
+      "learning_rate": 3.864205604623078e-05,
+      "loss": 1.8209,
+      "step": 10695
+    },
+    {
+      "epoch": 0.27006407916105396,
+      "grad_norm": 0.965977132320404,
+      "learning_rate": 3.857160259406107e-05,
+      "loss": 1.8558,
+      "step": 10726
+    },
+    {
+      "epoch": 0.2708446111817507,
+      "grad_norm": 0.9789881706237793,
+      "learning_rate": 3.8500995988200674e-05,
+      "loss": 1.8523,
+      "step": 10757
+    },
+    {
+      "epoch": 0.27162514320244735,
+      "grad_norm": 0.9083163738250732,
+      "learning_rate": 3.843023702543556e-05,
+      "loss": 1.8274,
+      "step": 10788
+    },
+    {
+      "epoch": 0.272405675223144,
+      "grad_norm": 0.9248176217079163,
+      "learning_rate": 3.8359326504270984e-05,
+      "loss": 1.8316,
+      "step": 10819
+    },
+    {
+      "epoch": 0.27318620724384074,
+      "grad_norm": 0.9702487587928772,
+      "learning_rate": 3.828826522492255e-05,
+      "loss": 1.8344,
+      "step": 10850
+    },
+    {
+      "epoch": 0.2739667392645374,
+      "grad_norm": 0.9324803948402405,
+      "learning_rate": 3.821705398930713e-05,
+      "loss": 1.8544,
+      "step": 10881
+    },
+    {
+      "epoch": 0.2747472712852341,
+      "grad_norm": 0.9495794773101807,
+      "learning_rate": 3.814569360103385e-05,
+      "loss": 1.8446,
+      "step": 10912
+    },
+    {
+      "epoch": 0.2755278033059308,
+      "grad_norm": 0.9734468460083008,
+      "learning_rate": 3.807418486539499e-05,
+      "loss": 1.8434,
+      "step": 10943
+    },
+    {
+      "epoch": 0.27630833532662746,
+      "grad_norm": 0.9376105666160583,
+      "learning_rate": 3.80025285893569e-05,
+      "loss": 1.8339,
+      "step": 10974
+    },
+    {
+      "epoch": 0.2770888673473242,
+      "grad_norm": 0.9637653827667236,
+      "learning_rate": 3.793072558155093e-05,
+      "loss": 1.8445,
+      "step": 11005
+    },
+    {
+      "epoch": 0.27786939936802085,
+      "grad_norm": 0.9537612199783325,
+      "learning_rate": 3.785877665226426e-05,
+      "loss": 1.8332,
+      "step": 11036
+    },
+    {
+      "epoch": 0.2786499313887175,
+      "grad_norm": 0.9774130582809448,
+      "learning_rate": 3.778668261343079e-05,
+      "loss": 1.8269,
+      "step": 11067
+    },
+    {
+      "epoch": 0.27943046340941424,
+      "grad_norm": 0.9648153781890869,
+      "learning_rate": 3.771444427862192e-05,
+      "loss": 1.8301,
+      "step": 11098
+    },
+    {
+      "epoch": 0.2802109954301109,
+      "grad_norm": 0.9317411184310913,
+      "learning_rate": 3.7642062463037465e-05,
+      "loss": 1.836,
+      "step": 11129
+    },
+    {
+      "epoch": 0.2809915274508076,
+      "grad_norm": 0.9821638464927673,
+      "learning_rate": 3.7569537983496373e-05,
+      "loss": 1.846,
+      "step": 11160
+    },
+    {
+      "epoch": 0.2817720594715043,
+      "grad_norm": 0.9444936513900757,
+      "learning_rate": 3.749687165842753e-05,
+      "loss": 1.8248,
+      "step": 11191
+    },
+    {
+      "epoch": 0.28255259149220097,
+      "grad_norm": 0.9421222805976868,
+      "learning_rate": 3.7424064307860536e-05,
+      "loss": 1.8521,
+      "step": 11222
+    },
+    {
+      "epoch": 0.2833331235128977,
+      "grad_norm": 0.9378920793533325,
+      "learning_rate": 3.735111675341645e-05,
+      "loss": 1.8361,
+      "step": 11253
+    },
+    {
+      "epoch": 0.28411365553359436,
+      "grad_norm": 0.9363348484039307,
+      "learning_rate": 3.7278029818298524e-05,
+      "loss": 1.8276,
+      "step": 11284
+    },
+    {
+      "epoch": 0.284894187554291,
+      "grad_norm": 0.9247562885284424,
+      "learning_rate": 3.720480432728287e-05,
+      "loss": 1.8354,
+      "step": 11315
+    },
+    {
+      "epoch": 0.28567471957498775,
+      "grad_norm": 0.9505523443222046,
+      "learning_rate": 3.71314411067092e-05,
+      "loss": 1.807,
+      "step": 11346
+    },
+    {
+      "epoch": 0.2864552515956844,
+      "grad_norm": 0.9292653799057007,
+      "learning_rate": 3.70579409844715e-05,
+      "loss": 1.8281,
+      "step": 11377
+    },
+    {
+      "epoch": 0.2872357836163811,
+      "grad_norm": 0.9625663161277771,
+      "learning_rate": 3.698430479000865e-05,
+      "loss": 1.8211,
+      "step": 11408
+    },
+    {
+      "epoch": 0.2880163156370778,
+      "grad_norm": 0.9280233979225159,
+      "learning_rate": 3.691053335429509e-05,
+      "loss": 1.8177,
+      "step": 11439
+    },
+    {
+      "epoch": 0.28879684765777447,
+      "grad_norm": 0.9617031216621399,
+      "learning_rate": 3.683662750983147e-05,
+      "loss": 1.831,
+      "step": 11470
+    },
+    {
+      "epoch": 0.2895773796784712,
+      "grad_norm": 0.9631845951080322,
+      "learning_rate": 3.676258809063518e-05,
+      "loss": 1.8154,
+      "step": 11501
+    },
+    {
+      "epoch": 0.29035791169916786,
+      "grad_norm": 0.9200331568717957,
+      "learning_rate": 3.6688415932231004e-05,
+      "loss": 1.8452,
+      "step": 11532
+    },
+    {
+      "epoch": 0.2911384437198645,
+      "grad_norm": 0.9431037902832031,
+      "learning_rate": 3.661411187164166e-05,
+      "loss": 1.8221,
+      "step": 11563
+    },
+    {
+      "epoch": 0.29191897574056125,
+      "grad_norm": 0.9307507276535034,
+      "learning_rate": 3.65396767473784e-05,
+      "loss": 1.8092,
+      "step": 11594
+    },
+    {
+      "epoch": 0.2926995077612579,
+      "grad_norm": 0.9896314144134521,
+      "learning_rate": 3.6465111399431465e-05,
+      "loss": 1.826,
+      "step": 11625
+    },
+    {
+      "epoch": 0.2934800397819546,
+      "grad_norm": 0.9361921548843384,
+      "learning_rate": 3.6390416669260674e-05,
+      "loss": 1.8207,
+      "step": 11656
+    },
+    {
+      "epoch": 0.2942605718026513,
+      "grad_norm": 0.9492716789245605,
+      "learning_rate": 3.63155933997859e-05,
+      "loss": 1.822,
+      "step": 11687
+    },
+    {
+      "epoch": 0.29504110382334797,
+      "grad_norm": 0.9642727375030518,
+      "learning_rate": 3.624064243537758e-05,
+      "loss": 1.8165,
+      "step": 11718
+    },
+    {
+      "epoch": 0.29582163584404464,
+      "grad_norm": 0.9700178503990173,
+      "learning_rate": 3.616556462184716e-05,
+      "loss": 1.8093,
+      "step": 11749
+    },
+    {
+      "epoch": 0.29660216786474136,
+      "grad_norm": 0.90894615650177,
+      "learning_rate": 3.609036080643755e-05,
+      "loss": 1.8312,
+      "step": 11780
+    },
+    {
+      "epoch": 0.29738269988543803,
+      "grad_norm": 0.9441593885421753,
+      "learning_rate": 3.60150318378136e-05,
+      "loss": 1.8324,
+      "step": 11811
+    },
+    {
+      "epoch": 0.29816323190613475,
+      "grad_norm": 0.9351882338523865,
+      "learning_rate": 3.5939578566052465e-05,
+      "loss": 1.8303,
+      "step": 11842
+    },
+    {
+      "epoch": 0.2989437639268314,
+      "grad_norm": 0.9438377618789673,
+      "learning_rate": 3.586400184263408e-05,
+      "loss": 1.8164,
+      "step": 11873
+    },
+    {
+      "epoch": 0.2997242959475281,
+      "grad_norm": 0.9775059819221497,
+      "learning_rate": 3.578830252043148e-05,
+      "loss": 1.8146,
+      "step": 11904
+    },
+    {
+      "epoch": 0.3005048279682248,
+      "grad_norm": 0.9342683553695679,
+      "learning_rate": 3.571248145370125e-05,
+      "loss": 1.8324,
+      "step": 11935
+    },
+    {
+      "epoch": 0.3012853599889215,
+      "grad_norm": 0.9539228081703186,
+      "learning_rate": 3.5636539498073794e-05,
+      "loss": 1.8112,
+      "step": 11966
+    },
+    {
+      "epoch": 0.30206589200961814,
+      "grad_norm": 1.0048060417175293,
+      "learning_rate": 3.556047751054378e-05,
+      "loss": 1.8261,
+      "step": 11997
+    },
+    {
+      "epoch": 0.30284642403031486,
+      "grad_norm": 0.9269846081733704,
+      "learning_rate": 3.548429634946039e-05,
+      "loss": 1.8256,
+      "step": 12028
+    },
+    {
+      "epoch": 0.30362695605101153,
+      "grad_norm": 0.937609076499939,
+      "learning_rate": 3.540799687451768e-05,
+      "loss": 1.8222,
+      "step": 12059
+    },
+    {
+      "epoch": 0.30440748807170825,
+      "grad_norm": 0.9538866281509399,
+      "learning_rate": 3.533157994674485e-05,
+      "loss": 1.8214,
+      "step": 12090
+    },
+    {
+      "epoch": 0.3051880200924049,
+      "grad_norm": 0.9644604325294495,
+      "learning_rate": 3.5255046428496546e-05,
+      "loss": 1.8117,
+      "step": 12121
+    },
+    {
+      "epoch": 0.3059685521131016,
+      "grad_norm": 1.0498855113983154,
+      "learning_rate": 3.517839718344311e-05,
+      "loss": 1.8249,
+      "step": 12152
+    },
+    {
+      "epoch": 0.3067490841337983,
+      "grad_norm": 0.952634334564209,
+      "learning_rate": 3.510163307656086e-05,
+      "loss": 1.8263,
+      "step": 12183
+    },
+    {
+      "epoch": 0.307529616154495,
+      "grad_norm": 0.9833852052688599,
+      "learning_rate": 3.5024754974122324e-05,
+      "loss": 1.8246,
+      "step": 12214
+    },
+    {
+      "epoch": 0.30831014817519165,
+      "grad_norm": 0.9421613812446594,
+      "learning_rate": 3.494776374368643e-05,
+      "loss": 1.8065,
+      "step": 12245
+    },
+    {
+      "epoch": 0.30909068019588837,
+      "grad_norm": 0.9119872450828552,
+      "learning_rate": 3.4870660254088724e-05,
+      "loss": 1.7958,
+      "step": 12276
+    },
+    {
+      "epoch": 0.30987121221658503,
+      "grad_norm": 0.9541532397270203,
+      "learning_rate": 3.479344537543164e-05,
+      "loss": 1.8156,
+      "step": 12307
+    },
+    {
+      "epoch": 0.31065174423728176,
+      "grad_norm": 0.9333822131156921,
+      "learning_rate": 3.4716119979074565e-05,
+      "loss": 1.8098,
+      "step": 12338
+    },
+    {
+      "epoch": 0.3114322762579784,
+      "grad_norm": 0.9501641392707825,
+      "learning_rate": 3.463868493762412e-05,
+      "loss": 1.815,
+      "step": 12369
+    },
+    {
+      "epoch": 0.3122128082786751,
+      "grad_norm": 0.9692359566688538,
+      "learning_rate": 3.456114112492418e-05,
+      "loss": 1.8192,
+      "step": 12400
+    },
+    {
+      "epoch": 0.3129933402993718,
+      "grad_norm": 0.9368917942047119,
+      "learning_rate": 3.4483489416046164e-05,
+      "loss": 1.8044,
+      "step": 12431
+    },
+    {
+      "epoch": 0.3137738723200685,
+      "grad_norm": 0.981076180934906,
+      "learning_rate": 3.440573068727905e-05,
+      "loss": 1.806,
+      "step": 12462
+    },
+    {
+      "epoch": 0.31455440434076515,
+      "grad_norm": 0.9535355567932129,
+      "learning_rate": 3.4327865816119495e-05,
+      "loss": 1.805,
+      "step": 12493
+    },
+    {
+      "epoch": 0.31533493636146187,
+      "grad_norm": 0.9825057983398438,
+      "learning_rate": 3.4249895681262025e-05,
+      "loss": 1.7878,
+      "step": 12524
+    },
+    {
+      "epoch": 0.31611546838215854,
+      "grad_norm": 0.9295104146003723,
+      "learning_rate": 3.417182116258899e-05,
+      "loss": 1.8091,
+      "step": 12555
+    },
+    {
+      "epoch": 0.31689600040285526,
+      "grad_norm": 0.9550284147262573,
+      "learning_rate": 3.409364314116074e-05,
+      "loss": 1.8053,
+      "step": 12586
+    },
+    {
+      "epoch": 0.3176765324235519,
+      "grad_norm": 0.9383823871612549,
+      "learning_rate": 3.401536249920559e-05,
+      "loss": 1.8034,
+      "step": 12617
+    },
+    {
+      "epoch": 0.3184570644442486,
+      "grad_norm": 0.9513770341873169,
+      "learning_rate": 3.393698012010998e-05,
+      "loss": 1.8097,
+      "step": 12648
+    },
+    {
+      "epoch": 0.3192375964649453,
+      "grad_norm": 0.9214389324188232,
+      "learning_rate": 3.385849688840839e-05,
+      "loss": 1.8089,
+      "step": 12679
+    },
+    {
+      "epoch": 0.320018128485642,
+      "grad_norm": 0.9370726346969604,
+      "learning_rate": 3.3779913689773414e-05,
+      "loss": 1.8022,
+      "step": 12710
+    },
+    {
+      "epoch": 0.32079866050633865,
+      "grad_norm": 0.9661527872085571,
+      "learning_rate": 3.370123141100578e-05,
+      "loss": 1.8151,
+      "step": 12741
+    },
+    {
+      "epoch": 0.3215791925270354,
+      "grad_norm": 0.9569831490516663,
+      "learning_rate": 3.3622450940024305e-05,
+      "loss": 1.8283,
+      "step": 12772
+    },
+    {
+      "epoch": 0.32235972454773204,
+      "grad_norm": 0.9162306785583496,
+      "learning_rate": 3.35435731658559e-05,
+      "loss": 1.8005,
+      "step": 12803
+    },
+    {
+      "epoch": 0.32314025656842876,
+      "grad_norm": 0.955159068107605,
+      "learning_rate": 3.346459897862552e-05,
+      "loss": 1.7929,
+      "step": 12834
+    },
+    {
+      "epoch": 0.32392078858912543,
+      "grad_norm": 0.9484529495239258,
+      "learning_rate": 3.338552926954613e-05,
+      "loss": 1.8355,
+      "step": 12865
+    },
+    {
+      "epoch": 0.3247013206098221,
+      "grad_norm": 0.9199361205101013,
+      "learning_rate": 3.330636493090868e-05,
+      "loss": 1.8096,
+      "step": 12896
+    },
+    {
+      "epoch": 0.3254818526305188,
+      "grad_norm": 0.928848147392273,
+      "learning_rate": 3.322710685607193e-05,
+      "loss": 1.7896,
+      "step": 12927
+    },
+    {
+      "epoch": 0.3262623846512155,
+      "grad_norm": 0.9141325354576111,
+      "learning_rate": 3.314775593945251e-05,
+      "loss": 1.8113,
+      "step": 12958
+    },
+    {
+      "epoch": 0.32704291667191215,
+      "grad_norm": 0.97685307264328,
+      "learning_rate": 3.3068313076514714e-05,
+      "loss": 1.8241,
+      "step": 12989
+    },
+    {
+      "epoch": 0.3278234486926089,
+      "grad_norm": 0.9171717166900635,
+      "learning_rate": 3.298877916376047e-05,
+      "loss": 1.7953,
+      "step": 13020
+    },
+    {
+      "epoch": 0.32860398071330554,
+      "grad_norm": 0.9607007503509521,
+      "learning_rate": 3.290915509871915e-05,
+      "loss": 1.819,
+      "step": 13051
+    },
+    {
+      "epoch": 0.32938451273400227,
+      "grad_norm": 0.9524408578872681,
+      "learning_rate": 3.282944177993753e-05,
+      "loss": 1.8133,
+      "step": 13082
+    },
+    {
+      "epoch": 0.33016504475469893,
+      "grad_norm": 0.9388900399208069,
+      "learning_rate": 3.274964010696957e-05,
+      "loss": 1.8103,
+      "step": 13113
+    },
+    {
+      "epoch": 0.3309455767753956,
+      "grad_norm": 0.8972403407096863,
+      "learning_rate": 3.266975098036629e-05,
+      "loss": 1.7997,
+      "step": 13144
+    },
+    {
+      "epoch": 0.3317261087960923,
+      "grad_norm": 0.9373508095741272,
+      "learning_rate": 3.258977530166562e-05,
+      "loss": 1.8038,
+      "step": 13175
+    },
+    {
+      "epoch": 0.332506640816789,
+      "grad_norm": 0.9278662204742432,
+      "learning_rate": 3.250971397338227e-05,
+      "loss": 1.803,
+      "step": 13206
+    },
+    {
+      "epoch": 0.33328717283748566,
+      "grad_norm": 0.9486290812492371,
+      "learning_rate": 3.2429567898997404e-05,
+      "loss": 1.8114,
+      "step": 13237
+    },
+    {
+      "epoch": 0.3340677048581824,
+      "grad_norm": 0.9786876440048218,
+      "learning_rate": 3.234933798294859e-05,
+      "loss": 1.7902,
+      "step": 13268
+    },
+    {
+      "epoch": 0.33484823687887905,
+      "grad_norm": 0.9001107215881348,
+      "learning_rate": 3.2269025130619535e-05,
+      "loss": 1.8108,
+      "step": 13299
+    },
+    {
+      "epoch": 0.33562876889957577,
+      "grad_norm": 0.9080937504768372,
+      "learning_rate": 3.218863024832985e-05,
+      "loss": 1.7951,
+      "step": 13330
+    },
+    {
+      "epoch": 0.33640930092027244,
+      "grad_norm": 0.93299800157547,
+      "learning_rate": 3.2108154243324864e-05,
+      "loss": 1.8129,
+      "step": 13361
+    },
+    {
+      "epoch": 0.3371898329409691,
+      "grad_norm": 0.9452754855155945,
+      "learning_rate": 3.2027598023765345e-05,
+      "loss": 1.8077,
+      "step": 13392
+    },
+    {
+      "epoch": 0.3379703649616658,
+      "grad_norm": 0.9515936970710754,
+      "learning_rate": 3.194696249871729e-05,
+      "loss": 1.7961,
+      "step": 13423
+    },
+    {
+      "epoch": 0.3387508969823625,
+      "grad_norm": 0.9395990371704102,
+      "learning_rate": 3.186624857814164e-05,
+      "loss": 1.7982,
+      "step": 13454
+    },
+    {
+      "epoch": 0.33953142900305916,
+      "grad_norm": 0.9647415280342102,
+      "learning_rate": 3.178545717288401e-05,
+      "loss": 1.7997,
+      "step": 13485
+    },
+    {
+      "epoch": 0.3403119610237559,
+      "grad_norm": 0.9437438249588013,
+      "learning_rate": 3.170458919466444e-05,
+      "loss": 1.8069,
+      "step": 13516
+    },
+    {
+      "epoch": 0.34109249304445255,
+      "grad_norm": 0.9350516200065613,
+      "learning_rate": 3.1623645556067063e-05,
+      "loss": 1.8024,
+      "step": 13547
+    },
+    {
+      "epoch": 0.34187302506514927,
+      "grad_norm": 0.9213714599609375,
+      "learning_rate": 3.154262717052985e-05,
+      "loss": 1.7963,
+      "step": 13578
+    },
+    {
+      "epoch": 0.34265355708584594,
+      "grad_norm": 0.9247968792915344,
+      "learning_rate": 3.146153495233426e-05,
+      "loss": 1.8172,
+      "step": 13609
+    },
+    {
+      "epoch": 0.3434340891065426,
+      "grad_norm": 0.8953402638435364,
+      "learning_rate": 3.1380369816594944e-05,
+      "loss": 1.8004,
+      "step": 13640
+    },
+    {
+      "epoch": 0.34421462112723933,
+      "grad_norm": 0.9214624762535095,
+      "learning_rate": 3.129913267924946e-05,
+      "loss": 1.7862,
+      "step": 13671
+    },
+    {
+      "epoch": 0.344995153147936,
+      "grad_norm": 0.946559727191925,
+      "learning_rate": 3.121782445704782e-05,
+      "loss": 1.7973,
+      "step": 13702
+    },
+    {
+      "epoch": 0.34577568516863266,
+      "grad_norm": 0.9344651103019714,
+      "learning_rate": 3.11364460675423e-05,
+      "loss": 1.7992,
+      "step": 13733
+    },
+    {
+      "epoch": 0.3465562171893294,
+      "grad_norm": 0.9140195846557617,
+      "learning_rate": 3.1054998429076934e-05,
+      "loss": 1.7846,
+      "step": 13764
+    },
+    {
+      "epoch": 0.34733674921002605,
+      "grad_norm": 0.9403822422027588,
+      "learning_rate": 3.097348246077728e-05,
+      "loss": 1.7814,
+      "step": 13795
+    },
+    {
+      "epoch": 0.3481172812307228,
+      "grad_norm": 0.954587996006012,
+      "learning_rate": 3.0891899082539924e-05,
+      "loss": 1.7864,
+      "step": 13826
+    },
+    {
+      "epoch": 0.34889781325141944,
+      "grad_norm": 0.9238544702529907,
+      "learning_rate": 3.0810249215022233e-05,
+      "loss": 1.7929,
+      "step": 13857
+    },
+    {
+      "epoch": 0.3496783452721161,
+      "grad_norm": 0.8994883894920349,
+      "learning_rate": 3.0728533779631865e-05,
+      "loss": 1.805,
+      "step": 13888
+    },
+    {
+      "epoch": 0.35045887729281283,
+      "grad_norm": 0.934203028678894,
+      "learning_rate": 3.064675369851637e-05,
+      "loss": 1.8046,
+      "step": 13919
+    },
+    {
+      "epoch": 0.3512394093135095,
+      "grad_norm": 0.9044675230979919,
+      "learning_rate": 3.056490989455289e-05,
+      "loss": 1.7866,
+      "step": 13950
+    },
+    {
+      "epoch": 0.35201994133420617,
+      "grad_norm": 0.915847897529602,
+      "learning_rate": 3.0483003291337596e-05,
+      "loss": 1.7861,
+      "step": 13981
+    },
+    {
+      "epoch": 0.3528004733549029,
+      "grad_norm": 0.9346082210540771,
+      "learning_rate": 3.040103481317539e-05,
+      "loss": 1.7891,
+      "step": 14012
+    },
+    {
+      "epoch": 0.35358100537559956,
+      "grad_norm": 0.9164626598358154,
+      "learning_rate": 3.03190053850694e-05,
+      "loss": 1.8021,
+      "step": 14043
+    },
+    {
+      "epoch": 0.3543615373962962,
+      "grad_norm": 0.9445552229881287,
+      "learning_rate": 3.0236915932710573e-05,
+      "loss": 1.7877,
+      "step": 14074
+    },
+    {
+      "epoch": 0.35514206941699294,
+      "grad_norm": 0.9604120254516602,
+      "learning_rate": 3.0154767382467232e-05,
+      "loss": 1.8087,
+      "step": 14105
+    },
+    {
+      "epoch": 0.3559226014376896,
+      "grad_norm": 0.9186177849769592,
+      "learning_rate": 3.0072560661374582e-05,
+      "loss": 1.7802,
+      "step": 14136
+    },
+    {
+      "epoch": 0.35670313345838633,
+      "grad_norm": 0.9228742122650146,
+      "learning_rate": 2.999029669712431e-05,
+      "loss": 1.8091,
+      "step": 14167
+    },
+    {
+      "epoch": 0.357483665479083,
+      "grad_norm": 0.9045746922492981,
+      "learning_rate": 2.990797641805408e-05,
+      "loss": 1.8013,
+      "step": 14198
+    },
+    {
+      "epoch": 0.35826419749977967,
+      "grad_norm": 0.9483916759490967,
+      "learning_rate": 2.982560075313704e-05,
+      "loss": 1.8044,
+      "step": 14229
+    },
+    {
+      "epoch": 0.3590447295204764,
+      "grad_norm": 0.9580939412117004,
+      "learning_rate": 2.9743170631971368e-05,
+      "loss": 1.8037,
+      "step": 14260
+    },
+    {
+      "epoch": 0.35982526154117306,
+      "grad_norm": 0.950960099697113,
+      "learning_rate": 2.9660686984769792e-05,
+      "loss": 1.8082,
+      "step": 14291
+    },
+    {
+      "epoch": 0.3606057935618697,
+      "grad_norm": 0.9356971383094788,
+      "learning_rate": 2.9578150742349047e-05,
+      "loss": 1.8049,
+      "step": 14322
+    },
+    {
+      "epoch": 0.36138632558256645,
+      "grad_norm": 0.9099254012107849,
+      "learning_rate": 2.949556283611942e-05,
+      "loss": 1.7991,
+      "step": 14353
+    },
+    {
+      "epoch": 0.3621668576032631,
+      "grad_norm": 0.9190629720687866,
+      "learning_rate": 2.9412924198074206e-05,
+      "loss": 1.8018,
+      "step": 14384
+    },
+    {
+      "epoch": 0.36294738962395984,
+      "grad_norm": 0.90566486120224,
+      "learning_rate": 2.9330235760779208e-05,
+      "loss": 1.789,
+      "step": 14415
+    },
+    {
+      "epoch": 0.3637279216446565,
+      "grad_norm": 0.970696747303009,
+      "learning_rate": 2.9247498457362188e-05,
+      "loss": 1.7851,
+      "step": 14446
+    },
+    {
+      "epoch": 0.36450845366535317,
+      "grad_norm": 0.9313214421272278,
+      "learning_rate": 2.9164713221502373e-05,
+      "loss": 1.7893,
+      "step": 14477
+    },
+    {
+      "epoch": 0.3652889856860499,
+      "grad_norm": 1.2887455224990845,
+      "learning_rate": 2.9081880987419912e-05,
+      "loss": 1.7836,
+      "step": 14508
+    },
+    {
+      "epoch": 0.36606951770674656,
+      "grad_norm": 0.922982394695282,
+      "learning_rate": 2.8999002689865296e-05,
+      "loss": 1.7676,
+      "step": 14539
+    },
+    {
+      "epoch": 0.36685004972744323,
+      "grad_norm": 0.9466812014579773,
+      "learning_rate": 2.8916079264108852e-05,
+      "loss": 1.7831,
+      "step": 14570
+    },
+    {
+      "epoch": 0.36763058174813995,
+      "grad_norm": 0.9107967615127563,
+      "learning_rate": 2.883311164593017e-05,
+      "loss": 1.7887,
+      "step": 14601
+    },
+    {
+      "epoch": 0.3684111137688366,
+      "grad_norm": 0.8859044313430786,
+      "learning_rate": 2.875010077160754e-05,
+      "loss": 1.7823,
+      "step": 14632
+    },
+    {
+      "epoch": 0.36919164578953334,
+      "grad_norm": 0.9182350039482117,
+      "learning_rate": 2.866704757790741e-05,
+      "loss": 1.7816,
+      "step": 14663
+    },
+    {
+      "epoch": 0.36997217781023,
+      "grad_norm": 1.1406787633895874,
+      "learning_rate": 2.858395300207376e-05,
+      "loss": 1.7962,
+      "step": 14694
+    },
+    {
+      "epoch": 0.3707527098309267,
+      "grad_norm": 0.9399011135101318,
+      "learning_rate": 2.8500817981817607e-05,
+      "loss": 1.7874,
+      "step": 14725
+    },
+    {
+      "epoch": 0.3715332418516234,
+      "grad_norm": 0.9223036766052246,
+      "learning_rate": 2.8417643455306336e-05,
+      "loss": 1.7661,
+      "step": 14756
+    },
+    {
+      "epoch": 0.37231377387232006,
+      "grad_norm": 0.9224306344985962,
+      "learning_rate": 2.8334430361153185e-05,
+      "loss": 1.7799,
+      "step": 14787
+    },
+    {
+      "epoch": 0.37309430589301673,
+      "grad_norm": 0.9353799819946289,
+      "learning_rate": 2.8251179638406612e-05,
+      "loss": 1.795,
+      "step": 14818
+    },
+    {
+      "epoch": 0.37387483791371345,
+      "grad_norm": 0.9208987355232239,
+      "learning_rate": 2.8167892226539704e-05,
+      "loss": 1.7967,
+      "step": 14849
+    },
+    {
+      "epoch": 0.3746553699344101,
+      "grad_norm": 0.9143754243850708,
+      "learning_rate": 2.8084569065439588e-05,
+      "loss": 1.7871,
+      "step": 14880
+    },
+    {
+      "epoch": 0.37543590195510684,
+      "grad_norm": 0.9162681698799133,
+      "learning_rate": 2.8001211095396807e-05,
+      "loss": 1.7791,
+      "step": 14911
+    },
+    {
+      "epoch": 0.3762164339758035,
+      "grad_norm": 0.9125809073448181,
+      "learning_rate": 2.791781925709473e-05,
+      "loss": 1.7847,
+      "step": 14942
+    },
+    {
+      "epoch": 0.3769969659965002,
+      "grad_norm": 0.9262179732322693,
+      "learning_rate": 2.7834394491598908e-05,
+      "loss": 1.789,
+      "step": 14973
+    },
+    {
+      "epoch": 0.3777774980171969,
+      "grad_norm": 0.9118053317070007,
+      "learning_rate": 2.7750937740346485e-05,
+      "loss": 1.7906,
+      "step": 15004
+    },
+    {
+      "epoch": 0.37855803003789357,
+      "grad_norm": 0.9322589635848999,
+      "learning_rate": 2.7667449945135564e-05,
+      "loss": 1.7811,
+      "step": 15035
+    },
+    {
+      "epoch": 0.37933856205859023,
+      "grad_norm": 0.9277715682983398,
+      "learning_rate": 2.7583932048114557e-05,
+      "loss": 1.7887,
+      "step": 15066
+    },
+    {
+      "epoch": 0.38011909407928696,
+      "grad_norm": 0.9804796576499939,
+      "learning_rate": 2.7500384991771587e-05,
+      "loss": 1.7945,
+      "step": 15097
+    },
+    {
+      "epoch": 0.3808996260999836,
+      "grad_norm": 0.9327893853187561,
+      "learning_rate": 2.7416809718923825e-05,
+      "loss": 1.785,
+      "step": 15128
+    },
+    {
+      "epoch": 0.38168015812068035,
+      "grad_norm": 0.9126656651496887,
+      "learning_rate": 2.7333207172706864e-05,
+      "loss": 1.7782,
+      "step": 15159
+    },
+    {
+      "epoch": 0.382460690141377,
+      "grad_norm": 0.9476912617683411,
+      "learning_rate": 2.7249578296564088e-05,
+      "loss": 1.7906,
+      "step": 15190
+    },
+    {
+      "epoch": 0.3832412221620737,
+      "grad_norm": 0.9388076663017273,
+      "learning_rate": 2.7165924034235973e-05,
+      "loss": 1.7993,
+      "step": 15221
+    },
+    {
+      "epoch": 0.3840217541827704,
+      "grad_norm": 0.9265156984329224,
+      "learning_rate": 2.708224532974953e-05,
+      "loss": 1.7624,
+      "step": 15252
+    }
+  ],
+  "logging_steps": 31,
+  "max_steps": 30517,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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 sha256:4d814be76984e23fb3bd9dc1672f03b4559e9f604318f29ab3bebb0989cab850
+size 5304

checkpoint-18312/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/Qwen2.5-7B-Instruct-si-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 sha256:3f8d21c656a0dd1bba3b2624e8b7f2932163e7d7a08af569b31812bfffc686e7
+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 sha256:721508f12632837a73c6fac48797a9eae4c95252ab97c722aa95d3ce13f1202f
+size 3662865184

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30e68f53aae13919e4118c59564572b3c9b2432468ad6d62254495a866dadaa3
+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:f5a835430eb1d25fe3e606f9cf510401f97b1abd8b16a69bae3aa7264c5ffc77
+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 sha256:4d814be76984e23fb3bd9dc1672f03b4559e9f604318f29ab3bebb0989cab850
+size 5304

checkpoint-21364/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/Qwen2.5-7B-Instruct-si-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 sha256:11f4672b707af5a068fc85540f2e0194c2c75918eb66349c90ae63a29a6e541e
+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