Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "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_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

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": "4.48.3"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cb6e174122180ebc86da06d95449168db4b6bddd49696135a0c285176337361
+size 4976687216

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce6c3bf20fe73d7dd30fd0c46de5b6f23d4e3b3137543489e274ee77bbca8e28
+size 4778622352

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:464b9d80079db56d50e1fa71768160cf6cfbddfb38203c7b66b00a52c9c3f7d6
+size 4932743960

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef4542665562b3a5fa3f4ec59acca2df2af8b0a8fcf4f2a41f7cbd36ec53e584
+size 4932743992

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18c82d2ccb2512e9277a45570ed3fdca669bd15ae27e3a7f99bd12f88deb2039
+size 4998852296

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ade4fac7191c45a75a03158fdc28030e4122f40b1b18d3b18b896ad18fdffe4
+size 3662865184

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:897f954c5532b4a099afa8811c1b6f8dc3af36ec0e9f4a95009cf01a50026842
+size 2179989632

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 30462466048
+  },
+  "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-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-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-00001-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-00002-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"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,2513 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.928,
+  "eval_steps": 500,
+  "global_step": 310,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016,
+      "grad_norm": 13.215581893920898,
+      "learning_rate": 6.25e-07,
+      "loss": 1.6218,
+      "mean_token_accuracy": 0.6110803186893463,
+      "step": 1
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 13.990567207336426,
+      "learning_rate": 1.25e-06,
+      "loss": 1.7041,
+      "mean_token_accuracy": 0.6301040947437286,
+      "step": 2
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 13.211037635803223,
+      "learning_rate": 1.8750000000000003e-06,
+      "loss": 1.7223,
+      "mean_token_accuracy": 0.5843513906002045,
+      "step": 3
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 14.67287826538086,
+      "learning_rate": 2.5e-06,
+      "loss": 1.7409,
+      "mean_token_accuracy": 0.5931073725223541,
+      "step": 4
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 11.63578987121582,
+      "learning_rate": 3.125e-06,
+      "loss": 1.6771,
+      "mean_token_accuracy": 0.59913170337677,
+      "step": 5
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 10.64076042175293,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 1.594,
+      "mean_token_accuracy": 0.604899674654007,
+      "step": 6
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 6.09752893447876,
+      "learning_rate": 4.3750000000000005e-06,
+      "loss": 1.458,
+      "mean_token_accuracy": 0.6177553832530975,
+      "step": 7
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 6.3267412185668945,
+      "learning_rate": 5e-06,
+      "loss": 1.4365,
+      "mean_token_accuracy": 0.625266432762146,
+      "step": 8
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 7.116683006286621,
+      "learning_rate": 5.625e-06,
+      "loss": 1.4384,
+      "mean_token_accuracy": 0.6151327192783356,
+      "step": 9
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 5.78098726272583,
+      "learning_rate": 6.25e-06,
+      "loss": 1.5083,
+      "mean_token_accuracy": 0.5956140756607056,
+      "step": 10
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 6.24675989151001,
+      "learning_rate": 6.875e-06,
+      "loss": 1.4437,
+      "mean_token_accuracy": 0.6152209639549255,
+      "step": 11
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 5.379809856414795,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.3736,
+      "mean_token_accuracy": 0.6294114291667938,
+      "step": 12
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 6.314828872680664,
+      "learning_rate": 8.125000000000001e-06,
+      "loss": 1.2994,
+      "mean_token_accuracy": 0.6413589417934418,
+      "step": 13
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 5.699032783508301,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 1.4117,
+      "mean_token_accuracy": 0.6173716485500336,
+      "step": 14
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 5.353813171386719,
+      "learning_rate": 9.375000000000001e-06,
+      "loss": 1.3486,
+      "mean_token_accuracy": 0.6315614581108093,
+      "step": 15
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 4.132171630859375,
+      "learning_rate": 1e-05,
+      "loss": 1.2788,
+      "mean_token_accuracy": 0.6412823796272278,
+      "step": 16
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 3.82682204246521,
+      "learning_rate": 9.999714542826806e-06,
+      "loss": 1.299,
+      "mean_token_accuracy": 0.6437126398086548,
+      "step": 17
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 3.6106579303741455,
+      "learning_rate": 9.99885820390154e-06,
+      "loss": 1.2665,
+      "mean_token_accuracy": 0.6511238217353821,
+      "step": 18
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 3.483157157897949,
+      "learning_rate": 9.99743108100344e-06,
+      "loss": 1.182,
+      "mean_token_accuracy": 0.6675288081169128,
+      "step": 19
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.896629571914673,
+      "learning_rate": 9.995433337085492e-06,
+      "loss": 1.2832,
+      "mean_token_accuracy": 0.6452755331993103,
+      "step": 20
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 3.7331128120422363,
+      "learning_rate": 9.992865200255829e-06,
+      "loss": 1.2423,
+      "mean_token_accuracy": 0.6492677927017212,
+      "step": 21
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 2.90647292137146,
+      "learning_rate": 9.989726963751683e-06,
+      "loss": 1.1555,
+      "mean_token_accuracy": 0.6576137840747833,
+      "step": 22
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 3.1129422187805176,
+      "learning_rate": 9.986018985905901e-06,
+      "loss": 1.1522,
+      "mean_token_accuracy": 0.6654780805110931,
+      "step": 23
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 2.943026304244995,
+      "learning_rate": 9.981741690106035e-06,
+      "loss": 1.2178,
+      "mean_token_accuracy": 0.6560894250869751,
+      "step": 24
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.891770362854004,
+      "learning_rate": 9.976895564745993e-06,
+      "loss": 1.1376,
+      "mean_token_accuracy": 0.6699535846710205,
+      "step": 25
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 3.3815524578094482,
+      "learning_rate": 9.97148116317027e-06,
+      "loss": 1.0781,
+      "mean_token_accuracy": 0.6821956038475037,
+      "step": 26
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 2.6959567070007324,
+      "learning_rate": 9.965499103610775e-06,
+      "loss": 1.186,
+      "mean_token_accuracy": 0.6514892578125,
+      "step": 27
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 2.619265079498291,
+      "learning_rate": 9.95895006911623e-06,
+      "loss": 1.1389,
+      "mean_token_accuracy": 0.6814388632774353,
+      "step": 28
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 2.3042593002319336,
+      "learning_rate": 9.951834807474191e-06,
+      "loss": 1.2518,
+      "mean_token_accuracy": 0.6459318101406097,
+      "step": 29
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.0451290607452393,
+      "learning_rate": 9.944154131125643e-06,
+      "loss": 1.2551,
+      "mean_token_accuracy": 0.6489538252353668,
+      "step": 30
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 2.3282535076141357,
+      "learning_rate": 9.935908917072253e-06,
+      "loss": 1.1706,
+      "mean_token_accuracy": 0.6664490401744843,
+      "step": 31
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 2.491532802581787,
+      "learning_rate": 9.927100106776213e-06,
+      "loss": 1.1587,
+      "mean_token_accuracy": 0.6678481698036194,
+      "step": 32
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 2.270688533782959,
+      "learning_rate": 9.917728706052765e-06,
+      "loss": 1.2636,
+      "mean_token_accuracy": 0.6454881429672241,
+      "step": 33
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 2.3011410236358643,
+      "learning_rate": 9.907795784955327e-06,
+      "loss": 1.1625,
+      "mean_token_accuracy": 0.6705195307731628,
+      "step": 34
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 2.0805764198303223,
+      "learning_rate": 9.897302477653334e-06,
+      "loss": 1.1351,
+      "mean_token_accuracy": 0.6750719845294952,
+      "step": 35
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 2.144771099090576,
+      "learning_rate": 9.88624998230272e-06,
+      "loss": 1.1632,
+      "mean_token_accuracy": 0.6594493687152863,
+      "step": 36
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 2.3651621341705322,
+      "learning_rate": 9.874639560909118e-06,
+      "loss": 1.1155,
+      "mean_token_accuracy": 0.6659645736217499,
+      "step": 37
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 2.438082695007324,
+      "learning_rate": 9.862472539183757e-06,
+      "loss": 1.049,
+      "mean_token_accuracy": 0.6966923773288727,
+      "step": 38
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 2.3827691078186035,
+      "learning_rate": 9.849750306392085e-06,
+      "loss": 1.1359,
+      "mean_token_accuracy": 0.6755817234516144,
+      "step": 39
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.284531831741333,
+      "learning_rate": 9.836474315195148e-06,
+      "loss": 1.2714,
+      "mean_token_accuracy": 0.6394982039928436,
+      "step": 40
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 2.040752410888672,
+      "learning_rate": 9.822646081483713e-06,
+      "loss": 1.1401,
+      "mean_token_accuracy": 0.6642443835735321,
+      "step": 41
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 2.416327476501465,
+      "learning_rate": 9.808267184205182e-06,
+      "loss": 1.1629,
+      "mean_token_accuracy": 0.6591512560844421,
+      "step": 42
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 2.5612552165985107,
+      "learning_rate": 9.793339265183303e-06,
+      "loss": 1.0806,
+      "mean_token_accuracy": 0.6875375807285309,
+      "step": 43
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 2.396414041519165,
+      "learning_rate": 9.777864028930705e-06,
+      "loss": 1.143,
+      "mean_token_accuracy": 0.6633529961109161,
+      "step": 44
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.2041707038879395,
+      "learning_rate": 9.761843242454261e-06,
+      "loss": 1.1267,
+      "mean_token_accuracy": 0.6633928120136261,
+      "step": 45
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 2.2253987789154053,
+      "learning_rate": 9.745278735053345e-06,
+      "loss": 1.052,
+      "mean_token_accuracy": 0.6914463341236115,
+      "step": 46
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 2.0851356983184814,
+      "learning_rate": 9.728172398110935e-06,
+      "loss": 1.2451,
+      "mean_token_accuracy": 0.6509403884410858,
+      "step": 47
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 2.110045909881592,
+      "learning_rate": 9.710526184877667e-06,
+      "loss": 1.1558,
+      "mean_token_accuracy": 0.6611768901348114,
+      "step": 48
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 2.5329489707946777,
+      "learning_rate": 9.692342110248802e-06,
+      "loss": 1.0322,
+      "mean_token_accuracy": 0.6901764273643494,
+      "step": 49
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.5721609592437744,
+      "learning_rate": 9.673622250534155e-06,
+      "loss": 1.1132,
+      "mean_token_accuracy": 0.6760377287864685,
+      "step": 50
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 2.4259121417999268,
+      "learning_rate": 9.654368743221022e-06,
+      "loss": 1.1227,
+      "mean_token_accuracy": 0.6690613925457001,
+      "step": 51
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 2.1539769172668457,
+      "learning_rate": 9.63458378673011e-06,
+      "loss": 1.1727,
+      "mean_token_accuracy": 0.6630356311798096,
+      "step": 52
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 2.281749963760376,
+      "learning_rate": 9.61426964016452e-06,
+      "loss": 1.1745,
+      "mean_token_accuracy": 0.6740401685237885,
+      "step": 53
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 2.3648617267608643,
+      "learning_rate": 9.593428623051793e-06,
+      "loss": 1.1393,
+      "mean_token_accuracy": 0.6692823767662048,
+      "step": 54
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.0223169326782227,
+      "learning_rate": 9.572063115079063e-06,
+      "loss": 1.1872,
+      "mean_token_accuracy": 0.6564280390739441,
+      "step": 55
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 2.4743919372558594,
+      "learning_rate": 9.550175555821333e-06,
+      "loss": 1.0744,
+      "mean_token_accuracy": 0.6807240545749664,
+      "step": 56
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 2.407332181930542,
+      "learning_rate": 9.527768444462922e-06,
+      "loss": 1.0236,
+      "mean_token_accuracy": 0.6924389898777008,
+      "step": 57
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 2.3066141605377197,
+      "learning_rate": 9.504844339512096e-06,
+      "loss": 1.08,
+      "mean_token_accuracy": 0.6853623390197754,
+      "step": 58
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 2.3197851181030273,
+      "learning_rate": 9.481405858508935e-06,
+      "loss": 1.1733,
+      "mean_token_accuracy": 0.6676386296749115,
+      "step": 59
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.277989625930786,
+      "learning_rate": 9.457455677726447e-06,
+      "loss": 1.112,
+      "mean_token_accuracy": 0.6790435910224915,
+      "step": 60
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 2.2761218547821045,
+      "learning_rate": 9.432996531865001e-06,
+      "loss": 1.1124,
+      "mean_token_accuracy": 0.6608242690563202,
+      "step": 61
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 2.4564669132232666,
+      "learning_rate": 9.408031213740045e-06,
+      "loss": 1.0301,
+      "mean_token_accuracy": 0.6902466714382172,
+      "step": 62
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.897603988647461,
+      "learning_rate": 9.382562573963238e-06,
+      "loss": 1.1236,
+      "mean_token_accuracy": 0.6699228882789612,
+      "step": 63
+    },
+    {
+      "epoch": 1.016,
+      "grad_norm": 2.5035905838012695,
+      "learning_rate": 9.356593520616948e-06,
+      "loss": 0.9954,
+      "mean_token_accuracy": 0.6969379484653473,
+      "step": 64
+    },
+    {
+      "epoch": 1.032,
+      "grad_norm": 2.1372523307800293,
+      "learning_rate": 9.330127018922195e-06,
+      "loss": 0.8832,
+      "mean_token_accuracy": 0.7084084153175354,
+      "step": 65
+    },
+    {
+      "epoch": 1.048,
+      "grad_norm": 2.1107141971588135,
+      "learning_rate": 9.303166090900082e-06,
+      "loss": 0.997,
+      "mean_token_accuracy": 0.6974039673805237,
+      "step": 66
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 2.203361988067627,
+      "learning_rate": 9.275713815026732e-06,
+      "loss": 0.8926,
+      "mean_token_accuracy": 0.7100537419319153,
+      "step": 67
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 2.280200481414795,
+      "learning_rate": 9.24777332588177e-06,
+      "loss": 0.7885,
+      "mean_token_accuracy": 0.7500935792922974,
+      "step": 68
+    },
+    {
+      "epoch": 1.096,
+      "grad_norm": 1.9387831687927246,
+      "learning_rate": 9.219347813790416e-06,
+      "loss": 0.7684,
+      "mean_token_accuracy": 0.7537571489810944,
+      "step": 69
+    },
+    {
+      "epoch": 1.112,
+      "grad_norm": 1.8483513593673706,
+      "learning_rate": 9.190440524459203e-06,
+      "loss": 0.9308,
+      "mean_token_accuracy": 0.7234339416027069,
+      "step": 70
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 2.085538148880005,
+      "learning_rate": 9.16105475860537e-06,
+      "loss": 0.892,
+      "mean_token_accuracy": 0.7284388244152069,
+      "step": 71
+    },
+    {
+      "epoch": 1.144,
+      "grad_norm": 2.351925849914551,
+      "learning_rate": 9.131193871579975e-06,
+      "loss": 0.9014,
+      "mean_token_accuracy": 0.709541916847229,
+      "step": 72
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 2.246936798095703,
+      "learning_rate": 9.10086127298478e-06,
+      "loss": 0.797,
+      "mean_token_accuracy": 0.7530255913734436,
+      "step": 73
+    },
+    {
+      "epoch": 1.176,
+      "grad_norm": 2.2428550720214844,
+      "learning_rate": 9.070060426282924e-06,
+      "loss": 0.891,
+      "mean_token_accuracy": 0.7251231074333191,
+      "step": 74
+    },
+    {
+      "epoch": 1.192,
+      "grad_norm": 2.2173142433166504,
+      "learning_rate": 9.038794848403463e-06,
+      "loss": 0.8948,
+      "mean_token_accuracy": 0.7141964137554169,
+      "step": 75
+    },
+    {
+      "epoch": 1.208,
+      "grad_norm": 2.357853889465332,
+      "learning_rate": 9.007068109339783e-06,
+      "loss": 0.8253,
+      "mean_token_accuracy": 0.737085372209549,
+      "step": 76
+    },
+    {
+      "epoch": 1.224,
+      "grad_norm": 2.5355238914489746,
+      "learning_rate": 8.97488383174199e-06,
+      "loss": 0.9135,
+      "mean_token_accuracy": 0.7259043753147125,
+      "step": 77
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 2.1808676719665527,
+      "learning_rate": 8.94224569050324e-06,
+      "loss": 0.9373,
+      "mean_token_accuracy": 0.718153566122055,
+      "step": 78
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 2.065774917602539,
+      "learning_rate": 8.90915741234015e-06,
+      "loss": 0.9066,
+      "mean_token_accuracy": 0.7267594933509827,
+      "step": 79
+    },
+    {
+      "epoch": 1.272,
+      "grad_norm": 2.277780055999756,
+      "learning_rate": 8.87562277536726e-06,
+      "loss": 0.84,
+      "mean_token_accuracy": 0.7230830788612366,
+      "step": 80
+    },
+    {
+      "epoch": 1.288,
+      "grad_norm": 2.232370615005493,
+      "learning_rate": 8.84164560866564e-06,
+      "loss": 0.8702,
+      "mean_token_accuracy": 0.7305114567279816,
+      "step": 81
+    },
+    {
+      "epoch": 1.304,
+      "grad_norm": 2.038029193878174,
+      "learning_rate": 8.807229791845673e-06,
+      "loss": 0.9693,
+      "mean_token_accuracy": 0.71137934923172,
+      "step": 82
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 2.3167836666107178,
+      "learning_rate": 8.772379254604074e-06,
+      "loss": 0.9381,
+      "mean_token_accuracy": 0.7007491886615753,
+      "step": 83
+    },
+    {
+      "epoch": 1.336,
+      "grad_norm": 2.048931121826172,
+      "learning_rate": 8.737097976275177e-06,
+      "loss": 0.9307,
+      "mean_token_accuracy": 0.7027971148490906,
+      "step": 84
+    },
+    {
+      "epoch": 1.3519999999999999,
+      "grad_norm": 1.9068111181259155,
+      "learning_rate": 8.701389985376578e-06,
+      "loss": 0.8459,
+      "mean_token_accuracy": 0.7333859205245972,
+      "step": 85
+    },
+    {
+      "epoch": 1.3679999999999999,
+      "grad_norm": 2.2652273178100586,
+      "learning_rate": 8.665259359149132e-06,
+      "loss": 0.8011,
+      "mean_token_accuracy": 0.7324046790599823,
+      "step": 86
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 2.2550220489501953,
+      "learning_rate": 8.62871022309141e-06,
+      "loss": 0.894,
+      "mean_token_accuracy": 0.7118227481842041,
+      "step": 87
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 2.1859939098358154,
+      "learning_rate": 8.591746750488639e-06,
+      "loss": 0.9182,
+      "mean_token_accuracy": 0.7196886539459229,
+      "step": 88
+    },
+    {
+      "epoch": 1.416,
+      "grad_norm": 2.1244003772735596,
+      "learning_rate": 8.554373161936176e-06,
+      "loss": 0.8451,
+      "mean_token_accuracy": 0.7242709100246429,
+      "step": 89
+    },
+    {
+      "epoch": 1.432,
+      "grad_norm": 2.1248416900634766,
+      "learning_rate": 8.516593724857598e-06,
+      "loss": 0.7697,
+      "mean_token_accuracy": 0.7540797293186188,
+      "step": 90
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 2.0870182514190674,
+      "learning_rate": 8.478412753017433e-06,
+      "loss": 0.8992,
+      "mean_token_accuracy": 0.7169869244098663,
+      "step": 91
+    },
+    {
+      "epoch": 1.464,
+      "grad_norm": 2.2304399013519287,
+      "learning_rate": 8.439834606028594e-06,
+      "loss": 0.9942,
+      "mean_token_accuracy": 0.7090178430080414,
+      "step": 92
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 2.376088857650757,
+      "learning_rate": 8.400863688854598e-06,
+      "loss": 0.82,
+      "mean_token_accuracy": 0.7365303039550781,
+      "step": 93
+    },
+    {
+      "epoch": 1.496,
+      "grad_norm": 2.288710594177246,
+      "learning_rate": 8.361504451306585e-06,
+      "loss": 0.8563,
+      "mean_token_accuracy": 0.730265200138092,
+      "step": 94
+    },
+    {
+      "epoch": 1.512,
+      "grad_norm": 2.1162161827087402,
+      "learning_rate": 8.321761387535231e-06,
+      "loss": 0.8894,
+      "mean_token_accuracy": 0.7278172373771667,
+      "step": 95
+    },
+    {
+      "epoch": 1.528,
+      "grad_norm": 2.040531635284424,
+      "learning_rate": 8.281639035517591e-06,
+      "loss": 0.8451,
+      "mean_token_accuracy": 0.7346065938472748,
+      "step": 96
+    },
+    {
+      "epoch": 1.544,
+      "grad_norm": 2.139214277267456,
+      "learning_rate": 8.241141976538944e-06,
+      "loss": 0.9186,
+      "mean_token_accuracy": 0.7127924859523773,
+      "step": 97
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 2.0378589630126953,
+      "learning_rate": 8.200274834669675e-06,
+      "loss": 0.8343,
+      "mean_token_accuracy": 0.7423592507839203,
+      "step": 98
+    },
+    {
+      "epoch": 1.576,
+      "grad_norm": 2.0469090938568115,
+      "learning_rate": 8.159042276237308e-06,
+      "loss": 0.9495,
+      "mean_token_accuracy": 0.7150463759899139,
+      "step": 99
+    },
+    {
+      "epoch": 1.592,
+      "grad_norm": 1.8930435180664062,
+      "learning_rate": 8.117449009293668e-06,
+      "loss": 0.7888,
+      "mean_token_accuracy": 0.7434406578540802,
+      "step": 100
+    },
+    {
+      "epoch": 1.608,
+      "grad_norm": 2.1599249839782715,
+      "learning_rate": 8.075499783077321e-06,
+      "loss": 0.8726,
+      "mean_token_accuracy": 0.7206392288208008,
+      "step": 101
+    },
+    {
+      "epoch": 1.624,
+      "grad_norm": 2.1455466747283936,
+      "learning_rate": 8.033199387471278e-06,
+      "loss": 0.9613,
+      "mean_token_accuracy": 0.7104770839214325,
+      "step": 102
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 2.0764999389648438,
+      "learning_rate": 7.99055265245608e-06,
+      "loss": 0.9353,
+      "mean_token_accuracy": 0.7238904535770416,
+      "step": 103
+    },
+    {
+      "epoch": 1.6560000000000001,
+      "grad_norm": 1.9134161472320557,
+      "learning_rate": 7.9475644475583e-06,
+      "loss": 0.8277,
+      "mean_token_accuracy": 0.7398611009120941,
+      "step": 104
+    },
+    {
+      "epoch": 1.6720000000000002,
+      "grad_norm": 2.059666872024536,
+      "learning_rate": 7.904239681294515e-06,
+      "loss": 0.809,
+      "mean_token_accuracy": 0.7348803877830505,
+      "step": 105
+    },
+    {
+      "epoch": 1.688,
+      "grad_norm": 1.903882622718811,
+      "learning_rate": 7.860583300610849e-06,
+      "loss": 0.779,
+      "mean_token_accuracy": 0.7487615942955017,
+      "step": 106
+    },
+    {
+      "epoch": 1.704,
+      "grad_norm": 1.921822428703308,
+      "learning_rate": 7.81660029031811e-06,
+      "loss": 0.8543,
+      "mean_token_accuracy": 0.7314419448375702,
+      "step": 107
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 1.9682213068008423,
+      "learning_rate": 7.772295672522615e-06,
+      "loss": 0.8275,
+      "mean_token_accuracy": 0.7274343073368073,
+      "step": 108
+    },
+    {
+      "epoch": 1.736,
+      "grad_norm": 2.098949909210205,
+      "learning_rate": 7.727674506052744e-06,
+      "loss": 0.862,
+      "mean_token_accuracy": 0.7319101393222809,
+      "step": 109
+    },
+    {
+      "epoch": 1.752,
+      "grad_norm": 1.8602185249328613,
+      "learning_rate": 7.682741885881314e-06,
+      "loss": 0.8919,
+      "mean_token_accuracy": 0.7283230125904083,
+      "step": 110
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 1.8391119241714478,
+      "learning_rate": 7.637502942543825e-06,
+      "loss": 0.9563,
+      "mean_token_accuracy": 0.716068685054779,
+      "step": 111
+    },
+    {
+      "epoch": 1.784,
+      "grad_norm": 1.818740725517273,
+      "learning_rate": 7.591962841552627e-06,
+      "loss": 0.8362,
+      "mean_token_accuracy": 0.7313212752342224,
+      "step": 112
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 1.9765996932983398,
+      "learning_rate": 7.546126782807117e-06,
+      "loss": 0.9427,
+      "mean_token_accuracy": 0.7000788450241089,
+      "step": 113
+    },
+    {
+      "epoch": 1.8159999999999998,
+      "grad_norm": 1.8508985042572021,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.8859,
+      "mean_token_accuracy": 0.7213517427444458,
+      "step": 114
+    },
+    {
+      "epoch": 1.8319999999999999,
+      "grad_norm": 1.936930537223816,
+      "learning_rate": 7.453587760019691e-06,
+      "loss": 0.8006,
+      "mean_token_accuracy": 0.7494409084320068,
+      "step": 115
+    },
+    {
+      "epoch": 1.8479999999999999,
+      "grad_norm": 1.8357962369918823,
+      "learning_rate": 7.406895362348916e-06,
+      "loss": 0.9697,
+      "mean_token_accuracy": 0.7061353325843811,
+      "step": 116
+    },
+    {
+      "epoch": 1.8639999999999999,
+      "grad_norm": 1.9790865182876587,
+      "learning_rate": 7.359928138459615e-06,
+      "loss": 0.9303,
+      "mean_token_accuracy": 0.7191019952297211,
+      "step": 117
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 1.857360601425171,
+      "learning_rate": 7.312691451204178e-06,
+      "loss": 0.8748,
+      "mean_token_accuracy": 0.7341600954532623,
+      "step": 118
+    },
+    {
+      "epoch": 1.896,
+      "grad_norm": 1.8874846696853638,
+      "learning_rate": 7.265190694203086e-06,
+      "loss": 0.9276,
+      "mean_token_accuracy": 0.7085016965866089,
+      "step": 119
+    },
+    {
+      "epoch": 1.912,
+      "grad_norm": 1.8215382099151611,
+      "learning_rate": 7.217431291229068e-06,
+      "loss": 0.8696,
+      "mean_token_accuracy": 0.712285041809082,
+      "step": 120
+    },
+    {
+      "epoch": 1.928,
+      "grad_norm": 2.019747257232666,
+      "learning_rate": 7.169418695587791e-06,
+      "loss": 0.8699,
+      "mean_token_accuracy": 0.7117200493812561,
+      "step": 121
+    },
+    {
+      "epoch": 1.944,
+      "grad_norm": 2.0499608516693115,
+      "learning_rate": 7.121158389495187e-06,
+      "loss": 0.8163,
+      "mean_token_accuracy": 0.7351702451705933,
+      "step": 122
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 1.9624381065368652,
+      "learning_rate": 7.072655883451478e-06,
+      "loss": 0.8318,
+      "mean_token_accuracy": 0.7394059598445892,
+      "step": 123
+    },
+    {
+      "epoch": 1.976,
+      "grad_norm": 2.178957223892212,
+      "learning_rate": 7.023916715611969e-06,
+      "loss": 0.8883,
+      "mean_token_accuracy": 0.7379129827022552,
+      "step": 124
+    },
+    {
+      "epoch": 1.992,
+      "grad_norm": 2.058216094970703,
+      "learning_rate": 6.974946451154694e-06,
+      "loss": 0.8657,
+      "mean_token_accuracy": 0.7464525401592255,
+      "step": 125
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.7633073329925537,
+      "learning_rate": 6.925750681644954e-06,
+      "loss": 0.8745,
+      "mean_token_accuracy": 0.6934740543365479,
+      "step": 126
+    },
+    {
+      "epoch": 2.016,
+      "grad_norm": 2.234250783920288,
+      "learning_rate": 6.876335024396872e-06,
+      "loss": 0.7128,
+      "mean_token_accuracy": 0.7859170734882355,
+      "step": 127
+    },
+    {
+      "epoch": 2.032,
+      "grad_norm": 1.9746248722076416,
+      "learning_rate": 6.8267051218319766e-06,
+      "loss": 0.7826,
+      "mean_token_accuracy": 0.7330600023269653,
+      "step": 128
+    },
+    {
+      "epoch": 2.048,
+      "grad_norm": 1.6777163743972778,
+      "learning_rate": 6.7768666408349445e-06,
+      "loss": 0.7145,
+      "mean_token_accuracy": 0.7724449634552002,
+      "step": 129
+    },
+    {
+      "epoch": 2.064,
+      "grad_norm": 1.8287721872329712,
+      "learning_rate": 6.726825272106539e-06,
+      "loss": 0.7962,
+      "mean_token_accuracy": 0.7566362023353577,
+      "step": 130
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 1.8211966753005981,
+      "learning_rate": 6.676586729513823e-06,
+      "loss": 0.603,
+      "mean_token_accuracy": 0.7968634068965912,
+      "step": 131
+    },
+    {
+      "epoch": 2.096,
+      "grad_norm": 2.150343894958496,
+      "learning_rate": 6.626156749437736e-06,
+      "loss": 0.5516,
+      "mean_token_accuracy": 0.8278916776180267,
+      "step": 132
+    },
+    {
+      "epoch": 2.112,
+      "grad_norm": 2.1101906299591064,
+      "learning_rate": 6.575541090118105e-06,
+      "loss": 0.7889,
+      "mean_token_accuracy": 0.7510809600353241,
+      "step": 133
+    },
+    {
+      "epoch": 2.128,
+      "grad_norm": 1.85099196434021,
+      "learning_rate": 6.524745530996137e-06,
+      "loss": 0.6569,
+      "mean_token_accuracy": 0.7761998474597931,
+      "step": 134
+    },
+    {
+      "epoch": 2.144,
+      "grad_norm": 1.9975664615631104,
+      "learning_rate": 6.473775872054522e-06,
+      "loss": 0.6174,
+      "mean_token_accuracy": 0.7907389402389526,
+      "step": 135
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 1.923912763595581,
+      "learning_rate": 6.4226379331551625e-06,
+      "loss": 0.6157,
+      "mean_token_accuracy": 0.7957707643508911,
+      "step": 136
+    },
+    {
+      "epoch": 2.176,
+      "grad_norm": 2.096576452255249,
+      "learning_rate": 6.3713375533746525e-06,
+      "loss": 0.5704,
+      "mean_token_accuracy": 0.8159550130367279,
+      "step": 137
+    },
+    {
+      "epoch": 2.192,
+      "grad_norm": 2.174253463745117,
+      "learning_rate": 6.319880590337549e-06,
+      "loss": 0.5904,
+      "mean_token_accuracy": 0.7935393750667572,
+      "step": 138
+    },
+    {
+      "epoch": 2.208,
+      "grad_norm": 1.8152769804000854,
+      "learning_rate": 6.268272919547537e-06,
+      "loss": 0.6239,
+      "mean_token_accuracy": 0.7914057075977325,
+      "step": 139
+    },
+    {
+      "epoch": 2.224,
+      "grad_norm": 1.8336701393127441,
+      "learning_rate": 6.216520433716544e-06,
+      "loss": 0.7358,
+      "mean_token_accuracy": 0.7601068317890167,
+      "step": 140
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 1.7724854946136475,
+      "learning_rate": 6.164629042091894e-06,
+      "loss": 0.5178,
+      "mean_token_accuracy": 0.8328815996646881,
+      "step": 141
+    },
+    {
+      "epoch": 2.2560000000000002,
+      "grad_norm": 2.001527786254883,
+      "learning_rate": 6.112604669781572e-06,
+      "loss": 0.7341,
+      "mean_token_accuracy": 0.7661413848400116,
+      "step": 142
+    },
+    {
+      "epoch": 2.2720000000000002,
+      "grad_norm": 1.973062515258789,
+      "learning_rate": 6.060453257077686e-06,
+      "loss": 0.6315,
+      "mean_token_accuracy": 0.7816351056098938,
+      "step": 143
+    },
+    {
+      "epoch": 2.288,
+      "grad_norm": 1.9068118333816528,
+      "learning_rate": 6.008180758778167e-06,
+      "loss": 0.6673,
+      "mean_token_accuracy": 0.7819712162017822,
+      "step": 144
+    },
+    {
+      "epoch": 2.304,
+      "grad_norm": 1.9064576625823975,
+      "learning_rate": 5.955793143506863e-06,
+      "loss": 0.5872,
+      "mean_token_accuracy": 0.8068342804908752,
+      "step": 145
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 1.783179759979248,
+      "learning_rate": 5.903296393031996e-06,
+      "loss": 0.6182,
+      "mean_token_accuracy": 0.7834264039993286,
+      "step": 146
+    },
+    {
+      "epoch": 2.336,
+      "grad_norm": 1.8228886127471924,
+      "learning_rate": 5.850696501583164e-06,
+      "loss": 0.6316,
+      "mean_token_accuracy": 0.7983745634555817,
+      "step": 147
+    },
+    {
+      "epoch": 2.352,
+      "grad_norm": 1.7698777914047241,
+      "learning_rate": 5.797999475166897e-06,
+      "loss": 0.7002,
+      "mean_token_accuracy": 0.7744604349136353,
+      "step": 148
+    },
+    {
+      "epoch": 2.368,
+      "grad_norm": 2.0236709117889404,
+      "learning_rate": 5.745211330880872e-06,
+      "loss": 0.6289,
+      "mean_token_accuracy": 0.7845793068408966,
+      "step": 149
+    },
+    {
+      "epoch": 2.384,
+      "grad_norm": 2.0701353549957275,
+      "learning_rate": 5.69233809622687e-06,
+      "loss": 0.4853,
+      "mean_token_accuracy": 0.8342052102088928,
+      "step": 150
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.841230034828186,
+      "learning_rate": 5.6393858084225305e-06,
+      "loss": 0.6612,
+      "mean_token_accuracy": 0.7836865186691284,
+      "step": 151
+    },
+    {
+      "epoch": 2.416,
+      "grad_norm": 1.8939555883407593,
+      "learning_rate": 5.586360513712011e-06,
+      "loss": 0.645,
+      "mean_token_accuracy": 0.779130607843399,
+      "step": 152
+    },
+    {
+      "epoch": 2.432,
+      "grad_norm": 1.9395414590835571,
+      "learning_rate": 5.533268266675601e-06,
+      "loss": 0.6672,
+      "mean_token_accuracy": 0.767756462097168,
+      "step": 153
+    },
+    {
+      "epoch": 2.448,
+      "grad_norm": 1.8063210248947144,
+      "learning_rate": 5.480115129538409e-06,
+      "loss": 0.6267,
+      "mean_token_accuracy": 0.7938161492347717,
+      "step": 154
+    },
+    {
+      "epoch": 2.464,
+      "grad_norm": 1.9447354078292847,
+      "learning_rate": 5.426907171478143e-06,
+      "loss": 0.458,
+      "mean_token_accuracy": 0.8398927450180054,
+      "step": 155
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 1.9445098638534546,
+      "learning_rate": 5.373650467932122e-06,
+      "loss": 0.5893,
+      "mean_token_accuracy": 0.8068392276763916,
+      "step": 156
+    },
+    {
+      "epoch": 2.496,
+      "grad_norm": 1.9469696283340454,
+      "learning_rate": 5.320351099903565e-06,
+      "loss": 0.7112,
+      "mean_token_accuracy": 0.7803526222705841,
+      "step": 157
+    },
+    {
+      "epoch": 2.512,
+      "grad_norm": 1.8126373291015625,
+      "learning_rate": 5.267015153267246e-06,
+      "loss": 0.5232,
+      "mean_token_accuracy": 0.8252148330211639,
+      "step": 158
+    },
+    {
+      "epoch": 2.528,
+      "grad_norm": 1.9050959348678589,
+      "learning_rate": 5.213648718074584e-06,
+      "loss": 0.5775,
+      "mean_token_accuracy": 0.7865356504917145,
+      "step": 159
+    },
+    {
+      "epoch": 2.544,
+      "grad_norm": 1.998955488204956,
+      "learning_rate": 5.160257887858278e-06,
+      "loss": 0.703,
+      "mean_token_accuracy": 0.7390948235988617,
+      "step": 160
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 1.973913311958313,
+      "learning_rate": 5.106848758936508e-06,
+      "loss": 0.6627,
+      "mean_token_accuracy": 0.7834351360797882,
+      "step": 161
+    },
+    {
+      "epoch": 2.576,
+      "grad_norm": 1.9610992670059204,
+      "learning_rate": 5.053427429716867e-06,
+      "loss": 0.676,
+      "mean_token_accuracy": 0.7891885936260223,
+      "step": 162
+    },
+    {
+      "epoch": 2.592,
+      "grad_norm": 1.9601593017578125,
+      "learning_rate": 5e-06,
+      "loss": 0.6207,
+      "mean_token_accuracy": 0.7994289994239807,
+      "step": 163
+    },
+    {
+      "epoch": 2.608,
+      "grad_norm": 1.98080575466156,
+      "learning_rate": 4.946572570283135e-06,
+      "loss": 0.5899,
+      "mean_token_accuracy": 0.7986661791801453,
+      "step": 164
+    },
+    {
+      "epoch": 2.624,
+      "grad_norm": 1.8518565893173218,
+      "learning_rate": 4.893151241063493e-06,
+      "loss": 0.6278,
+      "mean_token_accuracy": 0.7949875593185425,
+      "step": 165
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 1.865482211112976,
+      "learning_rate": 4.839742112141725e-06,
+      "loss": 0.6787,
+      "mean_token_accuracy": 0.7608937621116638,
+      "step": 166
+    },
+    {
+      "epoch": 2.656,
+      "grad_norm": 2.0454063415527344,
+      "learning_rate": 4.786351281925417e-06,
+      "loss": 0.7028,
+      "mean_token_accuracy": 0.7533181011676788,
+      "step": 167
+    },
+    {
+      "epoch": 2.672,
+      "grad_norm": 1.9324195384979248,
+      "learning_rate": 4.732984846732755e-06,
+      "loss": 0.5646,
+      "mean_token_accuracy": 0.8008407652378082,
+      "step": 168
+    },
+    {
+      "epoch": 2.6879999999999997,
+      "grad_norm": 1.8085490465164185,
+      "learning_rate": 4.679648900096436e-06,
+      "loss": 0.6662,
+      "mean_token_accuracy": 0.7686671316623688,
+      "step": 169
+    },
+    {
+      "epoch": 2.7039999999999997,
+      "grad_norm": 1.8703786134719849,
+      "learning_rate": 4.626349532067879e-06,
+      "loss": 0.7152,
+      "mean_token_accuracy": 0.7892328798770905,
+      "step": 170
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 2.0019490718841553,
+      "learning_rate": 4.573092828521857e-06,
+      "loss": 0.569,
+      "mean_token_accuracy": 0.8060936331748962,
+      "step": 171
+    },
+    {
+      "epoch": 2.7359999999999998,
+      "grad_norm": 1.706632137298584,
+      "learning_rate": 4.5198848704615915e-06,
+      "loss": 0.6882,
+      "mean_token_accuracy": 0.7672425508499146,
+      "step": 172
+    },
+    {
+      "epoch": 2.752,
+      "grad_norm": 1.881160855293274,
+      "learning_rate": 4.466731733324399e-06,
+      "loss": 0.6283,
+      "mean_token_accuracy": 0.8031312525272369,
+      "step": 173
+    },
+    {
+      "epoch": 2.768,
+      "grad_norm": 1.8949018716812134,
+      "learning_rate": 4.413639486287992e-06,
+      "loss": 0.5711,
+      "mean_token_accuracy": 0.8097128570079803,
+      "step": 174
+    },
+    {
+      "epoch": 2.784,
+      "grad_norm": 1.7667330503463745,
+      "learning_rate": 4.3606141915774695e-06,
+      "loss": 0.8263,
+      "mean_token_accuracy": 0.7537855207920074,
+      "step": 175
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 1.8455729484558105,
+      "learning_rate": 4.307661903773129e-06,
+      "loss": 0.5854,
+      "mean_token_accuracy": 0.8064002692699432,
+      "step": 176
+    },
+    {
+      "epoch": 2.816,
+      "grad_norm": 1.8596807718276978,
+      "learning_rate": 4.254788669119127e-06,
+      "loss": 0.6915,
+      "mean_token_accuracy": 0.7887419760227203,
+      "step": 177
+    },
+    {
+      "epoch": 2.832,
+      "grad_norm": 1.7176703214645386,
+      "learning_rate": 4.2020005248331056e-06,
+      "loss": 0.6683,
+      "mean_token_accuracy": 0.7633313834667206,
+      "step": 178
+    },
+    {
+      "epoch": 2.848,
+      "grad_norm": 1.7099390029907227,
+      "learning_rate": 4.149303498416838e-06,
+      "loss": 0.5278,
+      "mean_token_accuracy": 0.7912513315677643,
+      "step": 179
+    },
+    {
+      "epoch": 2.864,
+      "grad_norm": 1.9386448860168457,
+      "learning_rate": 4.096703606968007e-06,
+      "loss": 0.6205,
+      "mean_token_accuracy": 0.787754625082016,
+      "step": 180
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 1.731827974319458,
+      "learning_rate": 4.04420685649314e-06,
+      "loss": 0.6155,
+      "mean_token_accuracy": 0.8019371926784515,
+      "step": 181
+    },
+    {
+      "epoch": 2.896,
+      "grad_norm": 1.9536575078964233,
+      "learning_rate": 3.991819241221836e-06,
+      "loss": 0.6656,
+      "mean_token_accuracy": 0.7672460973262787,
+      "step": 182
+    },
+    {
+      "epoch": 2.912,
+      "grad_norm": 1.7277284860610962,
+      "learning_rate": 3.939546742922318e-06,
+      "loss": 0.6124,
+      "mean_token_accuracy": 0.7833640873432159,
+      "step": 183
+    },
+    {
+      "epoch": 2.928,
+      "grad_norm": 1.7660479545593262,
+      "learning_rate": 3.887395330218429e-06,
+      "loss": 0.5523,
+      "mean_token_accuracy": 0.8151686191558838,
+      "step": 184
+    },
+    {
+      "epoch": 2.944,
+      "grad_norm": 1.7463651895523071,
+      "learning_rate": 3.835370957908108e-06,
+      "loss": 0.5803,
+      "mean_token_accuracy": 0.8114446699619293,
+      "step": 185
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 1.9581048488616943,
+      "learning_rate": 3.783479566283457e-06,
+      "loss": 0.7512,
+      "mean_token_accuracy": 0.7575298547744751,
+      "step": 186
+    },
+    {
+      "epoch": 2.976,
+      "grad_norm": 2.0337820053100586,
+      "learning_rate": 3.731727080452464e-06,
+      "loss": 0.4586,
+      "mean_token_accuracy": 0.8477471768856049,
+      "step": 187
+    },
+    {
+      "epoch": 2.992,
+      "grad_norm": 2.0532712936401367,
+      "learning_rate": 3.6801194096624515e-06,
+      "loss": 0.7017,
+      "mean_token_accuracy": 0.7881054580211639,
+      "step": 188
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.616175651550293,
+      "learning_rate": 3.6286624466253496e-06,
+      "loss": 0.4702,
+      "mean_token_accuracy": 0.8436923027038574,
+      "step": 189
+    },
+    {
+      "epoch": 3.016,
+      "grad_norm": 1.8989686965942383,
+      "learning_rate": 3.5773620668448384e-06,
+      "loss": 0.4499,
+      "mean_token_accuracy": 0.8539375066757202,
+      "step": 190
+    },
+    {
+      "epoch": 3.032,
+      "grad_norm": 1.7433695793151855,
+      "learning_rate": 3.526224127945479e-06,
+      "loss": 0.44,
+      "mean_token_accuracy": 0.834608644247055,
+      "step": 191
+    },
+    {
+      "epoch": 3.048,
+      "grad_norm": 1.5851784944534302,
+      "learning_rate": 3.475254469003865e-06,
+      "loss": 0.526,
+      "mean_token_accuracy": 0.8261672258377075,
+      "step": 192
+    },
+    {
+      "epoch": 3.064,
+      "grad_norm": 1.618119239807129,
+      "learning_rate": 3.424458909881897e-06,
+      "loss": 0.4833,
+      "mean_token_accuracy": 0.8181418478488922,
+      "step": 193
+    },
+    {
+      "epoch": 3.08,
+      "grad_norm": 1.6358258724212646,
+      "learning_rate": 3.3738432505622653e-06,
+      "loss": 0.3926,
+      "mean_token_accuracy": 0.8705029785633087,
+      "step": 194
+    },
+    {
+      "epoch": 3.096,
+      "grad_norm": 1.7759870290756226,
+      "learning_rate": 3.3234132704861786e-06,
+      "loss": 0.6084,
+      "mean_token_accuracy": 0.8052189946174622,
+      "step": 195
+    },
+    {
+      "epoch": 3.112,
+      "grad_norm": 1.9421766996383667,
+      "learning_rate": 3.273174727893463e-06,
+      "loss": 0.4258,
+      "mean_token_accuracy": 0.8420732915401459,
+      "step": 196
+    },
+    {
+      "epoch": 3.128,
+      "grad_norm": 2.129655361175537,
+      "learning_rate": 3.2231333591650567e-06,
+      "loss": 0.4995,
+      "mean_token_accuracy": 0.8285854160785675,
+      "step": 197
+    },
+    {
+      "epoch": 3.144,
+      "grad_norm": 1.9939950704574585,
+      "learning_rate": 3.173294878168025e-06,
+      "loss": 0.4836,
+      "mean_token_accuracy": 0.8304620087146759,
+      "step": 198
+    },
+    {
+      "epoch": 3.16,
+      "grad_norm": 2.111128330230713,
+      "learning_rate": 3.12366497560313e-06,
+      "loss": 0.4879,
+      "mean_token_accuracy": 0.8432117104530334,
+      "step": 199
+    },
+    {
+      "epoch": 3.176,
+      "grad_norm": 1.8537310361862183,
+      "learning_rate": 3.074249318355046e-06,
+      "loss": 0.4127,
+      "mean_token_accuracy": 0.850278377532959,
+      "step": 200
+    },
+    {
+      "epoch": 3.192,
+      "grad_norm": 1.8146088123321533,
+      "learning_rate": 3.0250535488453077e-06,
+      "loss": 0.4438,
+      "mean_token_accuracy": 0.830359548330307,
+      "step": 201
+    },
+    {
+      "epoch": 3.208,
+      "grad_norm": 1.8513424396514893,
+      "learning_rate": 2.976083284388031e-06,
+      "loss": 0.4974,
+      "mean_token_accuracy": 0.8160843849182129,
+      "step": 202
+    },
+    {
+      "epoch": 3.224,
+      "grad_norm": 1.7857319116592407,
+      "learning_rate": 2.9273441165485227e-06,
+      "loss": 0.4141,
+      "mean_token_accuracy": 0.8569373190402985,
+      "step": 203
+    },
+    {
+      "epoch": 3.24,
+      "grad_norm": 1.8783490657806396,
+      "learning_rate": 2.8788416105048124e-06,
+      "loss": 0.3886,
+      "mean_token_accuracy": 0.850079745054245,
+      "step": 204
+    },
+    {
+      "epoch": 3.2560000000000002,
+      "grad_norm": 1.798640489578247,
+      "learning_rate": 2.83058130441221e-06,
+      "loss": 0.434,
+      "mean_token_accuracy": 0.8334758579730988,
+      "step": 205
+    },
+    {
+      "epoch": 3.2720000000000002,
+      "grad_norm": 1.7705386877059937,
+      "learning_rate": 2.782568708770933e-06,
+      "loss": 0.4141,
+      "mean_token_accuracy": 0.8566360175609589,
+      "step": 206
+    },
+    {
+      "epoch": 3.288,
+      "grad_norm": 1.741195797920227,
+      "learning_rate": 2.734809305796915e-06,
+      "loss": 0.4204,
+      "mean_token_accuracy": 0.8755166530609131,
+      "step": 207
+    },
+    {
+      "epoch": 3.304,
+      "grad_norm": 1.6184072494506836,
+      "learning_rate": 2.687308548795825e-06,
+      "loss": 0.3762,
+      "mean_token_accuracy": 0.8658173084259033,
+      "step": 208
+    },
+    {
+      "epoch": 3.32,
+      "grad_norm": 1.733109712600708,
+      "learning_rate": 2.6400718615403852e-06,
+      "loss": 0.5744,
+      "mean_token_accuracy": 0.8061816394329071,
+      "step": 209
+    },
+    {
+      "epoch": 3.336,
+      "grad_norm": 1.9283976554870605,
+      "learning_rate": 2.5931046376510875e-06,
+      "loss": 0.4062,
+      "mean_token_accuracy": 0.8531254231929779,
+      "step": 210
+    },
+    {
+      "epoch": 3.352,
+      "grad_norm": 1.7725756168365479,
+      "learning_rate": 2.5464122399803126e-06,
+      "loss": 0.5576,
+      "mean_token_accuracy": 0.800176590681076,
+      "step": 211
+    },
+    {
+      "epoch": 3.368,
+      "grad_norm": 1.6289314031600952,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.4405,
+      "mean_token_accuracy": 0.8461686670780182,
+      "step": 212
+    },
+    {
+      "epoch": 3.384,
+      "grad_norm": 1.7887394428253174,
+      "learning_rate": 2.4538732171928847e-06,
+      "loss": 0.4359,
+      "mean_token_accuracy": 0.8430683016777039,
+      "step": 213
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 1.781262993812561,
+      "learning_rate": 2.408037158447375e-06,
+      "loss": 0.6237,
+      "mean_token_accuracy": 0.8007213473320007,
+      "step": 214
+    },
+    {
+      "epoch": 3.416,
+      "grad_norm": 1.6724776029586792,
+      "learning_rate": 2.3624970574561773e-06,
+      "loss": 0.4734,
+      "mean_token_accuracy": 0.8019916415214539,
+      "step": 215
+    },
+    {
+      "epoch": 3.432,
+      "grad_norm": 1.624058485031128,
+      "learning_rate": 2.317258114118686e-06,
+      "loss": 0.5263,
+      "mean_token_accuracy": 0.8112485110759735,
+      "step": 216
+    },
+    {
+      "epoch": 3.448,
+      "grad_norm": 1.5671225786209106,
+      "learning_rate": 2.272325493947257e-06,
+      "loss": 0.5377,
+      "mean_token_accuracy": 0.8191773295402527,
+      "step": 217
+    },
+    {
+      "epoch": 3.464,
+      "grad_norm": 1.6635698080062866,
+      "learning_rate": 2.2277043274773856e-06,
+      "loss": 0.4164,
+      "mean_token_accuracy": 0.8735319077968597,
+      "step": 218
+    },
+    {
+      "epoch": 3.48,
+      "grad_norm": 1.5347254276275635,
+      "learning_rate": 2.1833997096818897e-06,
+      "loss": 0.5414,
+      "mean_token_accuracy": 0.8047713041305542,
+      "step": 219
+    },
+    {
+      "epoch": 3.496,
+      "grad_norm": 1.5895464420318604,
+      "learning_rate": 2.139416699389153e-06,
+      "loss": 0.431,
+      "mean_token_accuracy": 0.8373080492019653,
+      "step": 220
+    },
+    {
+      "epoch": 3.512,
+      "grad_norm": 1.728340983390808,
+      "learning_rate": 2.095760318705487e-06,
+      "loss": 0.4073,
+      "mean_token_accuracy": 0.8578878045082092,
+      "step": 221
+    },
+    {
+      "epoch": 3.528,
+      "grad_norm": 1.8697818517684937,
+      "learning_rate": 2.0524355524417017e-06,
+      "loss": 0.4038,
+      "mean_token_accuracy": 0.8781362175941467,
+      "step": 222
+    },
+    {
+      "epoch": 3.544,
+      "grad_norm": 1.7442781925201416,
+      "learning_rate": 2.00944734754392e-06,
+      "loss": 0.3679,
+      "mean_token_accuracy": 0.8618011176586151,
+      "step": 223
+    },
+    {
+      "epoch": 3.56,
+      "grad_norm": 1.6816269159317017,
+      "learning_rate": 1.966800612528723e-06,
+      "loss": 0.5316,
+      "mean_token_accuracy": 0.7882444560527802,
+      "step": 224
+    },
+    {
+      "epoch": 3.576,
+      "grad_norm": 1.6920692920684814,
+      "learning_rate": 1.9245002169226814e-06,
+      "loss": 0.4844,
+      "mean_token_accuracy": 0.8364316821098328,
+      "step": 225
+    },
+    {
+      "epoch": 3.592,
+      "grad_norm": 1.9367053508758545,
+      "learning_rate": 1.8825509907063328e-06,
+      "loss": 0.3735,
+      "mean_token_accuracy": 0.86876380443573,
+      "step": 226
+    },
+    {
+      "epoch": 3.608,
+      "grad_norm": 1.8703553676605225,
+      "learning_rate": 1.8409577237626935e-06,
+      "loss": 0.4888,
+      "mean_token_accuracy": 0.8111458122730255,
+      "step": 227
+    },
+    {
+      "epoch": 3.624,
+      "grad_norm": 1.7826961278915405,
+      "learning_rate": 1.7997251653303249e-06,
+      "loss": 0.4856,
+      "mean_token_accuracy": 0.801908940076828,
+      "step": 228
+    },
+    {
+      "epoch": 3.64,
+      "grad_norm": 1.846787929534912,
+      "learning_rate": 1.7588580234610592e-06,
+      "loss": 0.5526,
+      "mean_token_accuracy": 0.8281767964363098,
+      "step": 229
+    },
+    {
+      "epoch": 3.656,
+      "grad_norm": 1.5192652940750122,
+      "learning_rate": 1.7183609644824096e-06,
+      "loss": 0.4609,
+      "mean_token_accuracy": 0.8234535455703735,
+      "step": 230
+    },
+    {
+      "epoch": 3.672,
+      "grad_norm": 1.6722280979156494,
+      "learning_rate": 1.67823861246477e-06,
+      "loss": 0.5246,
+      "mean_token_accuracy": 0.7935002446174622,
+      "step": 231
+    },
+    {
+      "epoch": 3.6879999999999997,
+      "grad_norm": 1.5522016286849976,
+      "learning_rate": 1.6384955486934157e-06,
+      "loss": 0.4526,
+      "mean_token_accuracy": 0.8310949802398682,
+      "step": 232
+    },
+    {
+      "epoch": 3.7039999999999997,
+      "grad_norm": 1.7835192680358887,
+      "learning_rate": 1.5991363111454023e-06,
+      "loss": 0.4427,
+      "mean_token_accuracy": 0.8425520956516266,
+      "step": 233
+    },
+    {
+      "epoch": 3.7199999999999998,
+      "grad_norm": 1.6655128002166748,
+      "learning_rate": 1.5601653939714073e-06,
+      "loss": 0.5791,
+      "mean_token_accuracy": 0.8191401064395905,
+      "step": 234
+    },
+    {
+      "epoch": 3.7359999999999998,
+      "grad_norm": 1.6413390636444092,
+      "learning_rate": 1.5215872469825682e-06,
+      "loss": 0.4886,
+      "mean_token_accuracy": 0.8357130289077759,
+      "step": 235
+    },
+    {
+      "epoch": 3.752,
+      "grad_norm": 1.6971957683563232,
+      "learning_rate": 1.4834062751424018e-06,
+      "loss": 0.5311,
+      "mean_token_accuracy": 0.8187433481216431,
+      "step": 236
+    },
+    {
+      "epoch": 3.768,
+      "grad_norm": 1.489127516746521,
+      "learning_rate": 1.4456268380638262e-06,
+      "loss": 0.4431,
+      "mean_token_accuracy": 0.8484348654747009,
+      "step": 237
+    },
+    {
+      "epoch": 3.784,
+      "grad_norm": 1.6830918788909912,
+      "learning_rate": 1.4082532495113627e-06,
+      "loss": 0.4008,
+      "mean_token_accuracy": 0.8682940900325775,
+      "step": 238
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 1.8044171333312988,
+      "learning_rate": 1.3712897769085903e-06,
+      "loss": 0.3821,
+      "mean_token_accuracy": 0.8439038991928101,
+      "step": 239
+    },
+    {
+      "epoch": 3.816,
+      "grad_norm": 1.6815401315689087,
+      "learning_rate": 1.3347406408508695e-06,
+      "loss": 0.3555,
+      "mean_token_accuracy": 0.8827997744083405,
+      "step": 240
+    },
+    {
+      "epoch": 3.832,
+      "grad_norm": 1.5818198919296265,
+      "learning_rate": 1.298610014623423e-06,
+      "loss": 0.3805,
+      "mean_token_accuracy": 0.8539446592330933,
+      "step": 241
+    },
+    {
+      "epoch": 3.848,
+      "grad_norm": 1.6825566291809082,
+      "learning_rate": 1.2629020237248241e-06,
+      "loss": 0.4691,
+      "mean_token_accuracy": 0.8389621675014496,
+      "step": 242
+    },
+    {
+      "epoch": 3.864,
+      "grad_norm": 1.8937445878982544,
+      "learning_rate": 1.2276207453959283e-06,
+      "loss": 0.4858,
+      "mean_token_accuracy": 0.8229635059833527,
+      "step": 243
+    },
+    {
+      "epoch": 3.88,
+      "grad_norm": 1.7236624956130981,
+      "learning_rate": 1.1927702081543279e-06,
+      "loss": 0.5053,
+      "mean_token_accuracy": 0.8316462635993958,
+      "step": 244
+    },
+    {
+      "epoch": 3.896,
+      "grad_norm": 1.700505256652832,
+      "learning_rate": 1.158354391334362e-06,
+      "loss": 0.3465,
+      "mean_token_accuracy": 0.8770395815372467,
+      "step": 245
+    },
+    {
+      "epoch": 3.912,
+      "grad_norm": 1.7477822303771973,
+      "learning_rate": 1.1243772246327416e-06,
+      "loss": 0.4043,
+      "mean_token_accuracy": 0.8705323040485382,
+      "step": 246
+    },
+    {
+      "epoch": 3.928,
+      "grad_norm": 1.6631226539611816,
+      "learning_rate": 1.0908425876598512e-06,
+      "loss": 0.446,
+      "mean_token_accuracy": 0.8587776124477386,
+      "step": 247
+    },
+    {
+      "epoch": 3.944,
+      "grad_norm": 1.7363426685333252,
+      "learning_rate": 1.0577543094967613e-06,
+      "loss": 0.4081,
+      "mean_token_accuracy": 0.871842622756958,
+      "step": 248
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 1.7819398641586304,
+      "learning_rate": 1.0251161682580125e-06,
+      "loss": 0.3599,
+      "mean_token_accuracy": 0.8662829697132111,
+      "step": 249
+    },
+    {
+      "epoch": 3.976,
+      "grad_norm": 1.8177067041397095,
+      "learning_rate": 9.929318906602176e-07,
+      "loss": 0.4463,
+      "mean_token_accuracy": 0.8615152835845947,
+      "step": 250
+    },
+    {
+      "epoch": 3.992,
+      "grad_norm": 1.6980502605438232,
+      "learning_rate": 9.612051515965388e-07,
+      "loss": 0.5262,
+      "mean_token_accuracy": 0.7997405827045441,
+      "step": 251
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.324087619781494,
+      "learning_rate": 9.299395737170758e-07,
+      "loss": 0.3421,
+      "mean_token_accuracy": 0.8514267802238464,
+      "step": 252
+    },
+    {
+      "epoch": 4.016,
+      "grad_norm": 1.6846673488616943,
+      "learning_rate": 8.991387270152202e-07,
+      "loss": 0.4377,
+      "mean_token_accuracy": 0.8406525552272797,
+      "step": 253
+    },
+    {
+      "epoch": 4.032,
+      "grad_norm": 1.7401528358459473,
+      "learning_rate": 8.688061284200266e-07,
+      "loss": 0.3745,
+      "mean_token_accuracy": 0.862852543592453,
+      "step": 254
+    },
+    {
+      "epoch": 4.048,
+      "grad_norm": 1.5129587650299072,
+      "learning_rate": 8.389452413946314e-07,
+      "loss": 0.4453,
+      "mean_token_accuracy": 0.8313189148902893,
+      "step": 255
+    },
+    {
+      "epoch": 4.064,
+      "grad_norm": 1.4720897674560547,
+      "learning_rate": 8.095594755407971e-07,
+      "loss": 0.5333,
+      "mean_token_accuracy": 0.8177091777324677,
+      "step": 256
+    },
+    {
+      "epoch": 4.08,
+      "grad_norm": 1.5798670053482056,
+      "learning_rate": 7.806521862095834e-07,
+      "loss": 0.3594,
+      "mean_token_accuracy": 0.878955602645874,
+      "step": 257
+    },
+    {
+      "epoch": 4.096,
+      "grad_norm": 1.5988901853561401,
+      "learning_rate": 7.522266741182305e-07,
+      "loss": 0.3372,
+      "mean_token_accuracy": 0.8858175873756409,
+      "step": 258
+    },
+    {
+      "epoch": 4.112,
+      "grad_norm": 1.3429925441741943,
+      "learning_rate": 7.242861849732696e-07,
+      "loss": 0.3053,
+      "mean_token_accuracy": 0.8911112546920776,
+      "step": 259
+    },
+    {
+      "epoch": 4.128,
+      "grad_norm": 1.392916202545166,
+      "learning_rate": 6.968339090999188e-07,
+      "loss": 0.3566,
+      "mean_token_accuracy": 0.8763693869113922,
+      "step": 260
+    },
+    {
+      "epoch": 4.144,
+      "grad_norm": 1.3282548189163208,
+      "learning_rate": 6.698729810778065e-07,
+      "loss": 0.3934,
+      "mean_token_accuracy": 0.8518996834754944,
+      "step": 261
+    },
+    {
+      "epoch": 4.16,
+      "grad_norm": 1.3634921312332153,
+      "learning_rate": 6.43406479383053e-07,
+      "loss": 0.2876,
+      "mean_token_accuracy": 0.8888527750968933,
+      "step": 262
+    },
+    {
+      "epoch": 4.176,
+      "grad_norm": 1.5951544046401978,
+      "learning_rate": 6.174374260367611e-07,
+      "loss": 0.3306,
+      "mean_token_accuracy": 0.8580814898014069,
+      "step": 263
+    },
+    {
+      "epoch": 4.192,
+      "grad_norm": 1.8386245965957642,
+      "learning_rate": 5.919687862599549e-07,
+      "loss": 0.5825,
+      "mean_token_accuracy": 0.8090504109859467,
+      "step": 264
+    },
+    {
+      "epoch": 4.208,
+      "grad_norm": 1.6140440702438354,
+      "learning_rate": 5.670034681349995e-07,
+      "loss": 0.3189,
+      "mean_token_accuracy": 0.8884587585926056,
+      "step": 265
+    },
+    {
+      "epoch": 4.224,
+      "grad_norm": 1.5564498901367188,
+      "learning_rate": 5.425443222735527e-07,
+      "loss": 0.3539,
+      "mean_token_accuracy": 0.8893531560897827,
+      "step": 266
+    },
+    {
+      "epoch": 4.24,
+      "grad_norm": 1.6134988069534302,
+      "learning_rate": 5.185941414910673e-07,
+      "loss": 0.3285,
+      "mean_token_accuracy": 0.8698451220989227,
+      "step": 267
+    },
+    {
+      "epoch": 4.256,
+      "grad_norm": 1.657450556755066,
+      "learning_rate": 4.951556604879049e-07,
+      "loss": 0.3152,
+      "mean_token_accuracy": 0.8656443655490875,
+      "step": 268
+    },
+    {
+      "epoch": 4.272,
+      "grad_norm": 1.6017976999282837,
+      "learning_rate": 4.722315555370793e-07,
+      "loss": 0.3683,
+      "mean_token_accuracy": 0.8707852065563202,
+      "step": 269
+    },
+    {
+      "epoch": 4.288,
+      "grad_norm": 1.5347394943237305,
+      "learning_rate": 4.4982444417866753e-07,
+      "loss": 0.3373,
+      "mean_token_accuracy": 0.8773435652256012,
+      "step": 270
+    },
+    {
+      "epoch": 4.304,
+      "grad_norm": 1.658043384552002,
+      "learning_rate": 4.279368849209381e-07,
+      "loss": 0.4898,
+      "mean_token_accuracy": 0.8278676569461823,
+      "step": 271
+    },
+    {
+      "epoch": 4.32,
+      "grad_norm": 1.503208875656128,
+      "learning_rate": 4.0657137694820826e-07,
+      "loss": 0.2716,
+      "mean_token_accuracy": 0.9029871225357056,
+      "step": 272
+    },
+    {
+      "epoch": 4.336,
+      "grad_norm": 1.4751423597335815,
+      "learning_rate": 3.8573035983548167e-07,
+      "loss": 0.4335,
+      "mean_token_accuracy": 0.8453833758831024,
+      "step": 273
+    },
+    {
+      "epoch": 4.352,
+      "grad_norm": 1.5802851915359497,
+      "learning_rate": 3.6541621326989183e-07,
+      "loss": 0.372,
+      "mean_token_accuracy": 0.8641645312309265,
+      "step": 274
+    },
+    {
+      "epoch": 4.368,
+      "grad_norm": 1.4285887479782104,
+      "learning_rate": 3.4563125677897936e-07,
+      "loss": 0.2716,
+      "mean_token_accuracy": 0.8914371728897095,
+      "step": 275
+    },
+    {
+      "epoch": 4.384,
+      "grad_norm": 1.543737769126892,
+      "learning_rate": 3.263777494658449e-07,
+      "loss": 0.4701,
+      "mean_token_accuracy": 0.8330877125263214,
+      "step": 276
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 1.5941988229751587,
+      "learning_rate": 3.076578897511978e-07,
+      "loss": 0.4733,
+      "mean_token_accuracy": 0.8405623137950897,
+      "step": 277
+    },
+    {
+      "epoch": 4.416,
+      "grad_norm": 1.4298094511032104,
+      "learning_rate": 2.894738151223331e-07,
+      "loss": 0.3411,
+      "mean_token_accuracy": 0.8751503527164459,
+      "step": 278
+    },
+    {
+      "epoch": 4.432,
+      "grad_norm": 1.4553662538528442,
+      "learning_rate": 2.71827601889067e-07,
+      "loss": 0.4069,
+      "mean_token_accuracy": 0.8369295597076416,
+      "step": 279
+    },
+    {
+      "epoch": 4.448,
+      "grad_norm": 1.3951661586761475,
+      "learning_rate": 2.547212649466568e-07,
+      "loss": 0.3843,
+      "mean_token_accuracy": 0.846329540014267,
+      "step": 280
+    },
+    {
+      "epoch": 4.464,
+      "grad_norm": 1.5225402116775513,
+      "learning_rate": 2.3815675754573885e-07,
+      "loss": 0.3576,
+      "mean_token_accuracy": 0.8736283481121063,
+      "step": 281
+    },
+    {
+      "epoch": 4.48,
+      "grad_norm": 1.6082041263580322,
+      "learning_rate": 2.2213597106929608e-07,
+      "loss": 0.2575,
+      "mean_token_accuracy": 0.9190754592418671,
+      "step": 282
+    },
+    {
+      "epoch": 4.496,
+      "grad_norm": 1.5779746770858765,
+      "learning_rate": 2.0666073481669714e-07,
+      "loss": 0.3829,
+      "mean_token_accuracy": 0.8619149625301361,
+      "step": 283
+    },
+    {
+      "epoch": 4.5120000000000005,
+      "grad_norm": 1.5220720767974854,
+      "learning_rate": 1.9173281579481896e-07,
+      "loss": 0.2685,
+      "mean_token_accuracy": 0.9106524586677551,
+      "step": 284
+    },
+    {
+      "epoch": 4.5280000000000005,
+      "grad_norm": 1.500473976135254,
+      "learning_rate": 1.7735391851628814e-07,
+      "loss": 0.2973,
+      "mean_token_accuracy": 0.892973393201828,
+      "step": 285
+    },
+    {
+      "epoch": 4.5440000000000005,
+      "grad_norm": 1.5466065406799316,
+      "learning_rate": 1.6352568480485277e-07,
+      "loss": 0.3419,
+      "mean_token_accuracy": 0.8905702233314514,
+      "step": 286
+    },
+    {
+      "epoch": 4.5600000000000005,
+      "grad_norm": 1.4613832235336304,
+      "learning_rate": 1.5024969360791564e-07,
+      "loss": 0.3889,
+      "mean_token_accuracy": 0.8405336439609528,
+      "step": 287
+    },
+    {
+      "epoch": 4.576,
+      "grad_norm": 1.484372615814209,
+      "learning_rate": 1.375274608162447e-07,
+      "loss": 0.2586,
+      "mean_token_accuracy": 0.9031639397144318,
+      "step": 288
+    },
+    {
+      "epoch": 4.592,
+      "grad_norm": 1.6078850030899048,
+      "learning_rate": 1.253604390908819e-07,
+      "loss": 0.3391,
+      "mean_token_accuracy": 0.8819546401500702,
+      "step": 289
+    },
+    {
+      "epoch": 4.608,
+      "grad_norm": 1.6001267433166504,
+      "learning_rate": 1.1375001769728e-07,
+      "loss": 0.311,
+      "mean_token_accuracy": 0.8772971332073212,
+      "step": 290
+    },
+    {
+      "epoch": 4.624,
+      "grad_norm": 1.572523593902588,
+      "learning_rate": 1.0269752234666642e-07,
+      "loss": 0.5671,
+      "mean_token_accuracy": 0.8123734891414642,
+      "step": 291
+    },
+    {
+      "epoch": 4.64,
+      "grad_norm": 1.4202545881271362,
+      "learning_rate": 9.22042150446728e-08,
+      "loss": 0.3798,
+      "mean_token_accuracy": 0.8508090078830719,
+      "step": 292
+    },
+    {
+      "epoch": 4.656,
+      "grad_norm": 1.5495851039886475,
+      "learning_rate": 8.227129394723643e-08,
+      "loss": 0.3317,
+      "mean_token_accuracy": 0.8867059946060181,
+      "step": 293
+    },
+    {
+      "epoch": 4.672,
+      "grad_norm": 1.4975632429122925,
+      "learning_rate": 7.289989322378732e-08,
+      "loss": 0.3868,
+      "mean_token_accuracy": 0.8555810451507568,
+      "step": 294
+    },
+    {
+      "epoch": 4.688,
+      "grad_norm": 1.413699984550476,
+      "learning_rate": 6.409108292774912e-08,
+      "loss": 0.3873,
+      "mean_token_accuracy": 0.8520547449588776,
+      "step": 295
+    },
+    {
+      "epoch": 4.704,
+      "grad_norm": 1.5418516397476196,
+      "learning_rate": 5.584586887435739e-08,
+      "loss": 0.3496,
+      "mean_token_accuracy": 0.863271564245224,
+      "step": 296
+    },
+    {
+      "epoch": 4.72,
+      "grad_norm": 1.517801284790039,
+      "learning_rate": 4.8165192525809754e-08,
+      "loss": 0.402,
+      "mean_token_accuracy": 0.867528647184372,
+      "step": 297
+    },
+    {
+      "epoch": 4.736,
+      "grad_norm": 1.3901314735412598,
+      "learning_rate": 4.104993088376974e-08,
+      "loss": 0.4927,
+      "mean_token_accuracy": 0.8101126849651337,
+      "step": 298
+    },
+    {
+      "epoch": 4.752,
+      "grad_norm": 1.6048532724380493,
+      "learning_rate": 3.450089638922738e-08,
+      "loss": 0.4841,
+      "mean_token_accuracy": 0.836152046918869,
+      "step": 299
+    },
+    {
+      "epoch": 4.768,
+      "grad_norm": 1.39896821975708,
+      "learning_rate": 2.8518836829732332e-08,
+      "loss": 0.4559,
+      "mean_token_accuracy": 0.8460139036178589,
+      "step": 300
+    },
+    {
+      "epoch": 4.784,
+      "grad_norm": 1.40359365940094,
+      "learning_rate": 2.3104435254008852e-08,
+      "loss": 0.2905,
+      "mean_token_accuracy": 0.8796796500682831,
+      "step": 301
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 1.392991065979004,
+      "learning_rate": 1.8258309893965375e-08,
+      "loss": 0.3089,
+      "mean_token_accuracy": 0.8802558779716492,
+      "step": 302
+    },
+    {
+      "epoch": 4.816,
+      "grad_norm": 1.6868401765823364,
+      "learning_rate": 1.3981014094099354e-08,
+      "loss": 0.2923,
+      "mean_token_accuracy": 0.8579813539981842,
+      "step": 303
+    },
+    {
+      "epoch": 4.832,
+      "grad_norm": 1.4592156410217285,
+      "learning_rate": 1.0273036248318325e-08,
+      "loss": 0.3833,
+      "mean_token_accuracy": 0.8635309934616089,
+      "step": 304
+    },
+    {
+      "epoch": 4.848,
+      "grad_norm": 1.4995806217193604,
+      "learning_rate": 7.13479974417175e-09,
+      "loss": 0.4708,
+      "mean_token_accuracy": 0.8479401469230652,
+      "step": 305
+    },
+    {
+      "epoch": 4.864,
+      "grad_norm": 1.4440363645553589,
+      "learning_rate": 4.56666291450858e-09,
+      "loss": 0.2393,
+      "mean_token_accuracy": 0.9273587167263031,
+      "step": 306
+    },
+    {
+      "epoch": 4.88,
+      "grad_norm": 1.4790477752685547,
+      "learning_rate": 2.568918996560532e-09,
+      "loss": 0.3455,
+      "mean_token_accuracy": 0.8849050998687744,
+      "step": 307
+    },
+    {
+      "epoch": 4.896,
+      "grad_norm": 1.658073902130127,
+      "learning_rate": 1.1417960984605459e-09,
+      "loss": 0.2981,
+      "mean_token_accuracy": 0.8946259915828705,
+      "step": 308
+    },
+    {
+      "epoch": 4.912,
+      "grad_norm": 1.4868714809417725,
+      "learning_rate": 2.854571731947253e-10,
+      "loss": 0.3557,
+      "mean_token_accuracy": 0.8737443387508392,
+      "step": 309
+    },
+    {
+      "epoch": 4.928,
+      "grad_norm": 1.462461233139038,
+      "learning_rate": 0.0,
+      "loss": 0.3918,
+      "mean_token_accuracy": 0.8558708727359772,
+      "step": 310
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 310,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.75424678173737e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:365b22c47a23ae7c01e16a3d1d0dfd70b7253834c525374254deff018aea05c0
+size 5944