Upload folder using huggingface_hub

.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 +1,26 @@
+{
+  "</EF>": 151666,
+  "</tool_call>": 151658,
+  "<EF>": 151665,
+  "<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
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 9.514760021422899e+17,
+    "train_loss": 0.5942036323547363,
+    "train_runtime": 26089.1141,
+    "train_samples_per_second": 14.701,
+    "train_steps_per_second": 0.029
+}

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "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": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.52.4"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf249bfd395c88e83b8578246febfcfa2a5f9d18d75df38a621dcd50243ffad0
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fba2ccd660959431f87efd1135caebef13ce5c94c057f0b8f38b351ba158716
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8eac81bf5ab0e043118c30741a2f6813c5aa1620f2a5562d74c5e3dadca9978
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67bcb68e799155fdd32d2804ee858a56a1585f0713b99989969335c2988365fe
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<EF>",
+    "</EF>"
+  ],
+  "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 sha256:158bd03214732a3ce3e88b0486d80231c97fb06126840cfe44846c62c8c97c58
+size 11422259

tokenizer_config.json

@@ -0,0 +1,213 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<EF>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151666": {
+      "content": "</EF>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<EF>",
+    "</EF>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 9.514760021422899e+17,
+    "train_loss": 0.5942036323547363,
+    "train_runtime": 26089.1141,
+    "train_samples_per_second": 14.701,
+    "train_steps_per_second": 0.029
+}

trainer_log.jsonl

@@ -0,0 +1,76 @@
+{"current_steps": 10, "total_steps": 750, "loss": 0.6301, "lr": 6.000000000000001e-07, "epoch": 0.013349463935588836, "percentage": 1.33, "elapsed_time": "0:06:40", "remaining_time": "8:13:49"}
+{"current_steps": 20, "total_steps": 750, "loss": 0.6325, "lr": 1.2666666666666669e-06, "epoch": 0.026698927871177672, "percentage": 2.67, "elapsed_time": "0:12:24", "remaining_time": "7:32:53"}
+{"current_steps": 30, "total_steps": 750, "loss": 0.6061, "lr": 1.9333333333333336e-06, "epoch": 0.04004839180676651, "percentage": 4.0, "elapsed_time": "0:18:19", "remaining_time": "7:19:38"}
+{"current_steps": 40, "total_steps": 750, "loss": 0.6039, "lr": 2.6e-06, "epoch": 0.053397855742355345, "percentage": 5.33, "elapsed_time": "0:24:05", "remaining_time": "7:07:32"}
+{"current_steps": 50, "total_steps": 750, "loss": 0.6035, "lr": 3.266666666666667e-06, "epoch": 0.06674731967794419, "percentage": 6.67, "elapsed_time": "0:29:51", "remaining_time": "6:57:57"}
+{"current_steps": 60, "total_steps": 750, "loss": 0.6177, "lr": 3.9333333333333335e-06, "epoch": 0.08009678361353302, "percentage": 8.0, "elapsed_time": "0:35:37", "remaining_time": "6:49:39"}
+{"current_steps": 70, "total_steps": 750, "loss": 0.603, "lr": 4.600000000000001e-06, "epoch": 0.09344624754912186, "percentage": 9.33, "elapsed_time": "0:41:24", "remaining_time": "6:42:15"}
+{"current_steps": 80, "total_steps": 750, "loss": 0.6118, "lr": 4.99956677884892e-06, "epoch": 0.10679571148471069, "percentage": 10.67, "elapsed_time": "0:47:13", "remaining_time": "6:35:31"}
+{"current_steps": 90, "total_steps": 750, "loss": 0.6116, "lr": 4.994694765050121e-06, "epoch": 0.12014517542029952, "percentage": 12.0, "elapsed_time": "0:53:05", "remaining_time": "6:29:16"}
+{"current_steps": 100, "total_steps": 750, "loss": 0.6046, "lr": 4.984419797901491e-06, "epoch": 0.13349463935588837, "percentage": 13.33, "elapsed_time": "0:58:55", "remaining_time": "6:22:58"}
+{"current_steps": 110, "total_steps": 750, "loss": 0.5961, "lr": 4.9687641306938766e-06, "epoch": 0.1468441032914772, "percentage": 14.67, "elapsed_time": "1:04:36", "remaining_time": "6:15:52"}
+{"current_steps": 120, "total_steps": 750, "loss": 0.5891, "lr": 4.94776167011629e-06, "epoch": 0.16019356722706604, "percentage": 16.0, "elapsed_time": "1:10:19", "remaining_time": "6:09:14"}
+{"current_steps": 130, "total_steps": 750, "loss": 0.5965, "lr": 4.921457902821578e-06, "epoch": 0.17354303116265488, "percentage": 17.33, "elapsed_time": "1:16:11", "remaining_time": "6:03:22"}
+{"current_steps": 140, "total_steps": 750, "loss": 0.5876, "lr": 4.889909796912454e-06, "epoch": 0.1868924950982437, "percentage": 18.67, "elapsed_time": "1:21:55", "remaining_time": "5:56:56"}
+{"current_steps": 150, "total_steps": 750, "loss": 0.5866, "lr": 4.85318567856128e-06, "epoch": 0.20024195903383255, "percentage": 20.0, "elapsed_time": "1:27:39", "remaining_time": "5:50:37"}
+{"current_steps": 160, "total_steps": 750, "loss": 0.5917, "lr": 4.811365084030784e-06, "epoch": 0.21359142296942138, "percentage": 21.33, "elapsed_time": "1:33:24", "remaining_time": "5:44:25"}
+{"current_steps": 170, "total_steps": 750, "loss": 0.5972, "lr": 4.764538587416233e-06, "epoch": 0.22694088690501021, "percentage": 22.67, "elapsed_time": "1:39:11", "remaining_time": "5:38:26"}
+{"current_steps": 180, "total_steps": 750, "loss": 0.5692, "lr": 4.712807604482108e-06, "epoch": 0.24029035084059905, "percentage": 24.0, "elapsed_time": "1:44:54", "remaining_time": "5:32:12"}
+{"current_steps": 190, "total_steps": 750, "loss": 0.5878, "lr": 4.656284173018144e-06, "epoch": 0.2536398147761879, "percentage": 25.33, "elapsed_time": "1:50:35", "remaining_time": "5:25:58"}
+{"current_steps": 200, "total_steps": 750, "loss": 0.606, "lr": 4.595090710190419e-06, "epoch": 0.26698927871177675, "percentage": 26.67, "elapsed_time": "1:56:17", "remaining_time": "5:19:48"}
+{"current_steps": 210, "total_steps": 750, "loss": 0.5921, "lr": 4.529359747413038e-06, "epoch": 0.2803387426473656, "percentage": 28.0, "elapsed_time": "2:01:57", "remaining_time": "5:13:37"}
+{"current_steps": 220, "total_steps": 750, "loss": 0.5954, "lr": 4.4592336433146e-06, "epoch": 0.2936882065829544, "percentage": 29.33, "elapsed_time": "2:07:48", "remaining_time": "5:07:53"}
+{"current_steps": 230, "total_steps": 750, "loss": 0.6013, "lr": 4.384864275421109e-06, "epoch": 0.30703767051854325, "percentage": 30.67, "elapsed_time": "2:13:31", "remaining_time": "5:01:52"}
+{"current_steps": 240, "total_steps": 750, "loss": 0.6083, "lr": 4.30641271122307e-06, "epoch": 0.3203871344541321, "percentage": 32.0, "elapsed_time": "2:19:21", "remaining_time": "4:56:08"}
+{"current_steps": 250, "total_steps": 750, "loss": 0.6216, "lr": 4.224048859339175e-06, "epoch": 0.3337365983897209, "percentage": 33.33, "elapsed_time": "2:25:10", "remaining_time": "4:50:20"}
+{"current_steps": 260, "total_steps": 750, "loss": 0.6042, "lr": 4.1379511015320625e-06, "epoch": 0.34708606232530975, "percentage": 34.67, "elapsed_time": "2:31:22", "remaining_time": "4:45:17"}
+{"current_steps": 270, "total_steps": 750, "loss": 0.6163, "lr": 4.048305906373151e-06, "epoch": 0.3604355262608986, "percentage": 36.0, "elapsed_time": "2:37:11", "remaining_time": "4:39:27"}
+{"current_steps": 280, "total_steps": 750, "loss": 0.576, "lr": 3.955307425393224e-06, "epoch": 0.3737849901964874, "percentage": 37.33, "elapsed_time": "2:42:58", "remaining_time": "4:33:34"}
+{"current_steps": 290, "total_steps": 750, "loss": 0.5905, "lr": 3.859157072593459e-06, "epoch": 0.38713445413207626, "percentage": 38.67, "elapsed_time": "2:48:42", "remaining_time": "4:27:37"}
+{"current_steps": 300, "total_steps": 750, "loss": 0.6046, "lr": 3.760063088227542e-06, "epoch": 0.4004839180676651, "percentage": 40.0, "elapsed_time": "2:54:33", "remaining_time": "4:21:50"}
+{"current_steps": 310, "total_steps": 750, "loss": 0.5795, "lr": 3.658240087799655e-06, "epoch": 0.4138333820032539, "percentage": 41.33, "elapsed_time": "3:00:16", "remaining_time": "4:15:53"}
+{"current_steps": 320, "total_steps": 750, "loss": 0.6001, "lr": 3.5539085972550786e-06, "epoch": 0.42718284593884276, "percentage": 42.67, "elapsed_time": "3:06:04", "remaining_time": "4:10:02"}
+{"current_steps": 330, "total_steps": 750, "loss": 0.5969, "lr": 3.4472945753701038e-06, "epoch": 0.4405323098744316, "percentage": 44.0, "elapsed_time": "3:11:49", "remaining_time": "4:04:08"}
+{"current_steps": 340, "total_steps": 750, "loss": 0.5809, "lr": 3.338628924375638e-06, "epoch": 0.45388177381002043, "percentage": 45.33, "elapsed_time": "3:17:36", "remaining_time": "3:58:17"}
+{"current_steps": 350, "total_steps": 750, "loss": 0.5884, "lr": 3.228146989874389e-06, "epoch": 0.46723123774560926, "percentage": 46.67, "elapsed_time": "3:23:22", "remaining_time": "3:52:25"}
+{"current_steps": 360, "total_steps": 750, "loss": 0.5854, "lr": 3.116088051134695e-06, "epoch": 0.4805807016811981, "percentage": 48.0, "elapsed_time": "3:29:05", "remaining_time": "3:46:31"}
+{"current_steps": 370, "total_steps": 750, "loss": 0.6115, "lr": 3.002694802864912e-06, "epoch": 0.49393016561678693, "percentage": 49.33, "elapsed_time": "3:34:48", "remaining_time": "3:40:37"}
+{"current_steps": 380, "total_steps": 750, "loss": 0.6079, "lr": 2.888212829590719e-06, "epoch": 0.5072796295523758, "percentage": 50.67, "elapsed_time": "3:40:38", "remaining_time": "3:34:50"}
+{"current_steps": 390, "total_steps": 750, "loss": 0.5787, "lr": 2.77289007377372e-06, "epoch": 0.5206290934879646, "percentage": 52.0, "elapsed_time": "3:46:23", "remaining_time": "3:28:58"}
+{"current_steps": 400, "total_steps": 750, "loss": 0.6069, "lr": 2.6569762988232838e-06, "epoch": 0.5339785574235535, "percentage": 53.33, "elapsed_time": "3:52:07", "remaining_time": "3:23:06"}
+{"current_steps": 410, "total_steps": 750, "loss": 0.575, "lr": 2.5407225481646146e-06, "epoch": 0.5473280213591423, "percentage": 54.67, "elapsed_time": "3:57:52", "remaining_time": "3:17:15"}
+{"current_steps": 420, "total_steps": 750, "loss": 0.5858, "lr": 2.4243806015345988e-06, "epoch": 0.5606774852947312, "percentage": 56.0, "elapsed_time": "4:03:38", "remaining_time": "3:11:25"}
+{"current_steps": 430, "total_steps": 750, "loss": 0.5699, "lr": 2.3082024296829538e-06, "epoch": 0.5740269492303199, "percentage": 57.33, "elapsed_time": "4:09:20", "remaining_time": "3:05:33"}
+{"current_steps": 440, "total_steps": 750, "loss": 0.5823, "lr": 2.192439648659699e-06, "epoch": 0.5873764131659088, "percentage": 58.67, "elapsed_time": "4:15:07", "remaining_time": "2:59:45"}
+{"current_steps": 450, "total_steps": 750, "loss": 0.5974, "lr": 2.0773429748708153e-06, "epoch": 0.6007258771014976, "percentage": 60.0, "elapsed_time": "4:20:57", "remaining_time": "2:53:58"}
+{"current_steps": 460, "total_steps": 750, "loss": 0.5905, "lr": 1.963161682082342e-06, "epoch": 0.6140753410370865, "percentage": 61.33, "elapsed_time": "4:26:45", "remaining_time": "2:48:10"}
+{"current_steps": 470, "total_steps": 750, "loss": 0.5841, "lr": 1.850143061548907e-06, "epoch": 0.6274248049726753, "percentage": 62.67, "elapsed_time": "4:32:32", "remaining_time": "2:42:22"}
+{"current_steps": 480, "total_steps": 750, "loss": 0.5883, "lr": 1.7385318864359304e-06, "epoch": 0.6407742689082642, "percentage": 64.0, "elapsed_time": "4:38:15", "remaining_time": "2:36:31"}
+{"current_steps": 490, "total_steps": 750, "loss": 0.5981, "lr": 1.6285698816954626e-06, "epoch": 0.654123732843853, "percentage": 65.33, "elapsed_time": "4:44:08", "remaining_time": "2:30:46"}
+{"current_steps": 500, "total_steps": 750, "loss": 0.594, "lr": 1.520495200543754e-06, "epoch": 0.6674731967794418, "percentage": 66.67, "elapsed_time": "4:49:55", "remaining_time": "2:24:57"}
+{"current_steps": 510, "total_steps": 750, "loss": 0.5978, "lr": 1.41454190867443e-06, "epoch": 0.6808226607150306, "percentage": 68.0, "elapsed_time": "4:56:11", "remaining_time": "2:19:22"}
+{"current_steps": 520, "total_steps": 750, "loss": 0.5867, "lr": 1.3109394773243117e-06, "epoch": 0.6941721246506195, "percentage": 69.33, "elapsed_time": "5:01:57", "remaining_time": "2:13:33"}
+{"current_steps": 530, "total_steps": 750, "loss": 0.6018, "lr": 1.2099122862898214e-06, "epoch": 0.7075215885862083, "percentage": 70.67, "elapsed_time": "5:07:43", "remaining_time": "2:07:44"}
+{"current_steps": 540, "total_steps": 750, "loss": 0.6013, "lr": 1.1116791379703032e-06, "epoch": 0.7208710525217972, "percentage": 72.0, "elapsed_time": "5:13:29", "remaining_time": "2:01:54"}
+{"current_steps": 550, "total_steps": 750, "loss": 0.591, "lr": 1.0164527834907468e-06, "epoch": 0.7342205164573861, "percentage": 73.33, "elapsed_time": "5:19:14", "remaining_time": "1:56:05"}
+{"current_steps": 560, "total_steps": 750, "loss": 0.5691, "lr": 9.244394619302338e-07, "epoch": 0.7475699803929748, "percentage": 74.67, "elapsed_time": "5:24:59", "remaining_time": "1:50:15"}
+{"current_steps": 570, "total_steps": 750, "loss": 0.6041, "lr": 8.35838453654009e-07, "epoch": 0.7609194443285637, "percentage": 76.0, "elapsed_time": "5:30:50", "remaining_time": "1:44:28"}
+{"current_steps": 580, "total_steps": 750, "loss": 0.5886, "lr": 7.508416487165862e-07, "epoch": 0.7742689082641525, "percentage": 77.33, "elapsed_time": "5:36:35", "remaining_time": "1:38:39"}
+{"current_steps": 590, "total_steps": 750, "loss": 0.5754, "lr": 6.696331312706245e-07, "epoch": 0.7876183721997414, "percentage": 78.67, "elapsed_time": "5:42:21", "remaining_time": "1:32:50"}
+{"current_steps": 600, "total_steps": 750, "loss": 0.5896, "lr": 5.923887808816373e-07, "epoch": 0.8009678361353302, "percentage": 80.0, "elapsed_time": "5:48:10", "remaining_time": "1:27:02"}
+{"current_steps": 610, "total_steps": 750, "loss": 0.5831, "lr": 5.192758916120236e-07, "epoch": 0.8143173000709191, "percentage": 81.33, "elapsed_time": "5:53:50", "remaining_time": "1:21:12"}
+{"current_steps": 620, "total_steps": 750, "loss": 0.5937, "lr": 4.5045280969937847e-07, "epoch": 0.8276667640065078, "percentage": 82.67, "elapsed_time": "5:59:39", "remaining_time": "1:15:24"}
+{"current_steps": 630, "total_steps": 750, "loss": 0.5933, "lr": 3.86068590613804e-07, "epoch": 0.8410162279420967, "percentage": 84.0, "elapsed_time": "6:05:25", "remaining_time": "1:09:36"}
+{"current_steps": 640, "total_steps": 750, "loss": 0.5993, "lr": 3.262626762369525e-07, "epoch": 0.8543656918776855, "percentage": 85.33, "elapsed_time": "6:11:14", "remaining_time": "1:03:48"}
+{"current_steps": 650, "total_steps": 750, "loss": 0.6012, "lr": 2.7116459286195887e-07, "epoch": 0.8677151558132744, "percentage": 86.67, "elapsed_time": "6:17:03", "remaining_time": "0:58:00"}
+{"current_steps": 660, "total_steps": 750, "loss": 0.5856, "lr": 2.208936706683351e-07, "epoch": 0.8810646197488632, "percentage": 88.0, "elapsed_time": "6:22:45", "remaining_time": "0:52:11"}
+{"current_steps": 670, "total_steps": 750, "loss": 0.5929, "lr": 1.7555878527937164e-07, "epoch": 0.8944140836844521, "percentage": 89.33, "elapsed_time": "6:28:39", "remaining_time": "0:46:24"}
+{"current_steps": 680, "total_steps": 750, "loss": 0.578, "lr": 1.352581219617824e-07, "epoch": 0.9077635476200409, "percentage": 90.67, "elapsed_time": "6:34:30", "remaining_time": "0:40:36"}
+{"current_steps": 690, "total_steps": 750, "loss": 0.5815, "lr": 1.0007896297828113e-07, "epoch": 0.9211130115556297, "percentage": 92.0, "elapsed_time": "6:40:12", "remaining_time": "0:34:48"}
+{"current_steps": 700, "total_steps": 750, "loss": 0.5984, "lr": 7.009749855363457e-08, "epoch": 0.9344624754912185, "percentage": 93.33, "elapsed_time": "6:46:04", "remaining_time": "0:29:00"}
+{"current_steps": 710, "total_steps": 750, "loss": 0.5797, "lr": 4.537866186360207e-08, "epoch": 0.9478119394268074, "percentage": 94.67, "elapsed_time": "6:51:54", "remaining_time": "0:23:12"}
+{"current_steps": 720, "total_steps": 750, "loss": 0.5822, "lr": 2.59759884041369e-08, "epoch": 0.9611614033623962, "percentage": 96.0, "elapsed_time": "6:57:37", "remaining_time": "0:17:24"}
+{"current_steps": 730, "total_steps": 750, "loss": 0.6017, "lr": 1.193150004542204e-08, "epoch": 0.9745108672979851, "percentage": 97.33, "elapsed_time": "7:03:27", "remaining_time": "0:11:36"}
+{"current_steps": 740, "total_steps": 750, "loss": 0.5792, "lr": 3.275614021857609e-09, "epoch": 0.9878603312335739, "percentage": 98.67, "elapsed_time": "7:09:10", "remaining_time": "0:05:47"}
+{"current_steps": 750, "total_steps": 750, "loss": 0.5653, "lr": 2.7077055103075233e-11, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "7:14:24", "remaining_time": "0:00:00"}
+{"current_steps": 750, "total_steps": 750, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "7:14:49", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,568 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013349463935588836,
+      "grad_norm": 3.8443384275181525,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 0.6301,
+      "step": 10
+    },
+    {
+      "epoch": 0.026698927871177672,
+      "grad_norm": 1.1304019443903548,
+      "learning_rate": 1.2666666666666669e-06,
+      "loss": 0.6325,
+      "step": 20
+    },
+    {
+      "epoch": 0.04004839180676651,
+      "grad_norm": 0.7924252148112436,
+      "learning_rate": 1.9333333333333336e-06,
+      "loss": 0.6061,
+      "step": 30
+    },
+    {
+      "epoch": 0.053397855742355345,
+      "grad_norm": 0.7615554902176207,
+      "learning_rate": 2.6e-06,
+      "loss": 0.6039,
+      "step": 40
+    },
+    {
+      "epoch": 0.06674731967794419,
+      "grad_norm": 0.6884584126571622,
+      "learning_rate": 3.266666666666667e-06,
+      "loss": 0.6035,
+      "step": 50
+    },
+    {
+      "epoch": 0.08009678361353302,
+      "grad_norm": 0.6895907181910402,
+      "learning_rate": 3.9333333333333335e-06,
+      "loss": 0.6177,
+      "step": 60
+    },
+    {
+      "epoch": 0.09344624754912186,
+      "grad_norm": 0.6789285267200114,
+      "learning_rate": 4.600000000000001e-06,
+      "loss": 0.603,
+      "step": 70
+    },
+    {
+      "epoch": 0.10679571148471069,
+      "grad_norm": 0.6467096461947729,
+      "learning_rate": 4.99956677884892e-06,
+      "loss": 0.6118,
+      "step": 80
+    },
+    {
+      "epoch": 0.12014517542029952,
+      "grad_norm": 0.6168635819855449,
+      "learning_rate": 4.994694765050121e-06,
+      "loss": 0.6116,
+      "step": 90
+    },
+    {
+      "epoch": 0.13349463935588837,
+      "grad_norm": 0.5441117690789925,
+      "learning_rate": 4.984419797901491e-06,
+      "loss": 0.6046,
+      "step": 100
+    },
+    {
+      "epoch": 0.1468441032914772,
+      "grad_norm": 0.5172864204707323,
+      "learning_rate": 4.9687641306938766e-06,
+      "loss": 0.5961,
+      "step": 110
+    },
+    {
+      "epoch": 0.16019356722706604,
+      "grad_norm": 0.5120924898252496,
+      "learning_rate": 4.94776167011629e-06,
+      "loss": 0.5891,
+      "step": 120
+    },
+    {
+      "epoch": 0.17354303116265488,
+      "grad_norm": 0.4936858545975663,
+      "learning_rate": 4.921457902821578e-06,
+      "loss": 0.5965,
+      "step": 130
+    },
+    {
+      "epoch": 0.1868924950982437,
+      "grad_norm": 0.5096637378296062,
+      "learning_rate": 4.889909796912454e-06,
+      "loss": 0.5876,
+      "step": 140
+    },
+    {
+      "epoch": 0.20024195903383255,
+      "grad_norm": 0.4893103328332192,
+      "learning_rate": 4.85318567856128e-06,
+      "loss": 0.5866,
+      "step": 150
+    },
+    {
+      "epoch": 0.21359142296942138,
+      "grad_norm": 0.48634183325283653,
+      "learning_rate": 4.811365084030784e-06,
+      "loss": 0.5917,
+      "step": 160
+    },
+    {
+      "epoch": 0.22694088690501021,
+      "grad_norm": 0.5077880866108633,
+      "learning_rate": 4.764538587416233e-06,
+      "loss": 0.5972,
+      "step": 170
+    },
+    {
+      "epoch": 0.24029035084059905,
+      "grad_norm": 0.5531086916036718,
+      "learning_rate": 4.712807604482108e-06,
+      "loss": 0.5692,
+      "step": 180
+    },
+    {
+      "epoch": 0.2536398147761879,
+      "grad_norm": 0.4815973346852316,
+      "learning_rate": 4.656284173018144e-06,
+      "loss": 0.5878,
+      "step": 190
+    },
+    {
+      "epoch": 0.26698927871177675,
+      "grad_norm": 0.4477210102882603,
+      "learning_rate": 4.595090710190419e-06,
+      "loss": 0.606,
+      "step": 200
+    },
+    {
+      "epoch": 0.2803387426473656,
+      "grad_norm": 0.4442300924031833,
+      "learning_rate": 4.529359747413038e-06,
+      "loss": 0.5921,
+      "step": 210
+    },
+    {
+      "epoch": 0.2936882065829544,
+      "grad_norm": 0.4318914186907017,
+      "learning_rate": 4.4592336433146e-06,
+      "loss": 0.5954,
+      "step": 220
+    },
+    {
+      "epoch": 0.30703767051854325,
+      "grad_norm": 0.4822511296612312,
+      "learning_rate": 4.384864275421109e-06,
+      "loss": 0.6013,
+      "step": 230
+    },
+    {
+      "epoch": 0.3203871344541321,
+      "grad_norm": 0.44291005932494015,
+      "learning_rate": 4.30641271122307e-06,
+      "loss": 0.6083,
+      "step": 240
+    },
+    {
+      "epoch": 0.3337365983897209,
+      "grad_norm": 0.48203103136482495,
+      "learning_rate": 4.224048859339175e-06,
+      "loss": 0.6216,
+      "step": 250
+    },
+    {
+      "epoch": 0.34708606232530975,
+      "grad_norm": 0.45150578106097233,
+      "learning_rate": 4.1379511015320625e-06,
+      "loss": 0.6042,
+      "step": 260
+    },
+    {
+      "epoch": 0.3604355262608986,
+      "grad_norm": 0.4551136191346761,
+      "learning_rate": 4.048305906373151e-06,
+      "loss": 0.6163,
+      "step": 270
+    },
+    {
+      "epoch": 0.3737849901964874,
+      "grad_norm": 0.46692000639310954,
+      "learning_rate": 3.955307425393224e-06,
+      "loss": 0.576,
+      "step": 280
+    },
+    {
+      "epoch": 0.38713445413207626,
+      "grad_norm": 0.43289733012383014,
+      "learning_rate": 3.859157072593459e-06,
+      "loss": 0.5905,
+      "step": 290
+    },
+    {
+      "epoch": 0.4004839180676651,
+      "grad_norm": 0.47300144920672366,
+      "learning_rate": 3.760063088227542e-06,
+      "loss": 0.6046,
+      "step": 300
+    },
+    {
+      "epoch": 0.4138333820032539,
+      "grad_norm": 0.43427902038611416,
+      "learning_rate": 3.658240087799655e-06,
+      "loss": 0.5795,
+      "step": 310
+    },
+    {
+      "epoch": 0.42718284593884276,
+      "grad_norm": 0.4321634460614613,
+      "learning_rate": 3.5539085972550786e-06,
+      "loss": 0.6001,
+      "step": 320
+    },
+    {
+      "epoch": 0.4405323098744316,
+      "grad_norm": 0.4751769823117227,
+      "learning_rate": 3.4472945753701038e-06,
+      "loss": 0.5969,
+      "step": 330
+    },
+    {
+      "epoch": 0.45388177381002043,
+      "grad_norm": 0.4523747463622145,
+      "learning_rate": 3.338628924375638e-06,
+      "loss": 0.5809,
+      "step": 340
+    },
+    {
+      "epoch": 0.46723123774560926,
+      "grad_norm": 0.4571186296564021,
+      "learning_rate": 3.228146989874389e-06,
+      "loss": 0.5884,
+      "step": 350
+    },
+    {
+      "epoch": 0.4805807016811981,
+      "grad_norm": 0.48390017792164,
+      "learning_rate": 3.116088051134695e-06,
+      "loss": 0.5854,
+      "step": 360
+    },
+    {
+      "epoch": 0.49393016561678693,
+      "grad_norm": 0.4656758402293932,
+      "learning_rate": 3.002694802864912e-06,
+      "loss": 0.6115,
+      "step": 370
+    },
+    {
+      "epoch": 0.5072796295523758,
+      "grad_norm": 0.4624954532839225,
+      "learning_rate": 2.888212829590719e-06,
+      "loss": 0.6079,
+      "step": 380
+    },
+    {
+      "epoch": 0.5206290934879646,
+      "grad_norm": 0.436497560779719,
+      "learning_rate": 2.77289007377372e-06,
+      "loss": 0.5787,
+      "step": 390
+    },
+    {
+      "epoch": 0.5339785574235535,
+      "grad_norm": 0.46334201651691187,
+      "learning_rate": 2.6569762988232838e-06,
+      "loss": 0.6069,
+      "step": 400
+    },
+    {
+      "epoch": 0.5473280213591423,
+      "grad_norm": 0.4806566661003276,
+      "learning_rate": 2.5407225481646146e-06,
+      "loss": 0.575,
+      "step": 410
+    },
+    {
+      "epoch": 0.5606774852947312,
+      "grad_norm": 0.460214567270956,
+      "learning_rate": 2.4243806015345988e-06,
+      "loss": 0.5858,
+      "step": 420
+    },
+    {
+      "epoch": 0.5740269492303199,
+      "grad_norm": 0.42739545970036125,
+      "learning_rate": 2.3082024296829538e-06,
+      "loss": 0.5699,
+      "step": 430
+    },
+    {
+      "epoch": 0.5873764131659088,
+      "grad_norm": 0.4503645884785317,
+      "learning_rate": 2.192439648659699e-06,
+      "loss": 0.5823,
+      "step": 440
+    },
+    {
+      "epoch": 0.6007258771014976,
+      "grad_norm": 0.4776520102412501,
+      "learning_rate": 2.0773429748708153e-06,
+      "loss": 0.5974,
+      "step": 450
+    },
+    {
+      "epoch": 0.6140753410370865,
+      "grad_norm": 0.4600206541871604,
+      "learning_rate": 1.963161682082342e-06,
+      "loss": 0.5905,
+      "step": 460
+    },
+    {
+      "epoch": 0.6274248049726753,
+      "grad_norm": 0.42642177736501347,
+      "learning_rate": 1.850143061548907e-06,
+      "loss": 0.5841,
+      "step": 470
+    },
+    {
+      "epoch": 0.6407742689082642,
+      "grad_norm": 0.4374872861905679,
+      "learning_rate": 1.7385318864359304e-06,
+      "loss": 0.5883,
+      "step": 480
+    },
+    {
+      "epoch": 0.654123732843853,
+      "grad_norm": 0.4539731186521712,
+      "learning_rate": 1.6285698816954626e-06,
+      "loss": 0.5981,
+      "step": 490
+    },
+    {
+      "epoch": 0.6674731967794418,
+      "grad_norm": 0.49549560937788556,
+      "learning_rate": 1.520495200543754e-06,
+      "loss": 0.594,
+      "step": 500
+    },
+    {
+      "epoch": 0.6808226607150306,
+      "grad_norm": 0.442220991522498,
+      "learning_rate": 1.41454190867443e-06,
+      "loss": 0.5978,
+      "step": 510
+    },
+    {
+      "epoch": 0.6941721246506195,
+      "grad_norm": 0.44323894790772966,
+      "learning_rate": 1.3109394773243117e-06,
+      "loss": 0.5867,
+      "step": 520
+    },
+    {
+      "epoch": 0.7075215885862083,
+      "grad_norm": 0.4233660170980954,
+      "learning_rate": 1.2099122862898214e-06,
+      "loss": 0.6018,
+      "step": 530
+    },
+    {
+      "epoch": 0.7208710525217972,
+      "grad_norm": 0.43218789543451824,
+      "learning_rate": 1.1116791379703032e-06,
+      "loss": 0.6013,
+      "step": 540
+    },
+    {
+      "epoch": 0.7342205164573861,
+      "grad_norm": 0.44159730183002366,
+      "learning_rate": 1.0164527834907468e-06,
+      "loss": 0.591,
+      "step": 550
+    },
+    {
+      "epoch": 0.7475699803929748,
+      "grad_norm": 0.43870818069759426,
+      "learning_rate": 9.244394619302338e-07,
+      "loss": 0.5691,
+      "step": 560
+    },
+    {
+      "epoch": 0.7609194443285637,
+      "grad_norm": 0.4477385893330783,
+      "learning_rate": 8.35838453654009e-07,
+      "loss": 0.6041,
+      "step": 570
+    },
+    {
+      "epoch": 0.7742689082641525,
+      "grad_norm": 0.43072214351782917,
+      "learning_rate": 7.508416487165862e-07,
+      "loss": 0.5886,
+      "step": 580
+    },
+    {
+      "epoch": 0.7876183721997414,
+      "grad_norm": 0.4279974728470172,
+      "learning_rate": 6.696331312706245e-07,
+      "loss": 0.5754,
+      "step": 590
+    },
+    {
+      "epoch": 0.8009678361353302,
+      "grad_norm": 0.3917096350694494,
+      "learning_rate": 5.923887808816373e-07,
+      "loss": 0.5896,
+      "step": 600
+    },
+    {
+      "epoch": 0.8143173000709191,
+      "grad_norm": 0.4434938485219406,
+      "learning_rate": 5.192758916120236e-07,
+      "loss": 0.5831,
+      "step": 610
+    },
+    {
+      "epoch": 0.8276667640065078,
+      "grad_norm": 0.41679775408713765,
+      "learning_rate": 4.5045280969937847e-07,
+      "loss": 0.5937,
+      "step": 620
+    },
+    {
+      "epoch": 0.8410162279420967,
+      "grad_norm": 0.4268405005566493,
+      "learning_rate": 3.86068590613804e-07,
+      "loss": 0.5933,
+      "step": 630
+    },
+    {
+      "epoch": 0.8543656918776855,
+      "grad_norm": 0.4166184793700984,
+      "learning_rate": 3.262626762369525e-07,
+      "loss": 0.5993,
+      "step": 640
+    },
+    {
+      "epoch": 0.8677151558132744,
+      "grad_norm": 0.41797554779045376,
+      "learning_rate": 2.7116459286195887e-07,
+      "loss": 0.6012,
+      "step": 650
+    },
+    {
+      "epoch": 0.8810646197488632,
+      "grad_norm": 0.4255310425370243,
+      "learning_rate": 2.208936706683351e-07,
+      "loss": 0.5856,
+      "step": 660
+    },
+    {
+      "epoch": 0.8944140836844521,
+      "grad_norm": 0.42943616856150774,
+      "learning_rate": 1.7555878527937164e-07,
+      "loss": 0.5929,
+      "step": 670
+    },
+    {
+      "epoch": 0.9077635476200409,
+      "grad_norm": 0.41759560647733296,
+      "learning_rate": 1.352581219617824e-07,
+      "loss": 0.578,
+      "step": 680
+    },
+    {
+      "epoch": 0.9211130115556297,
+      "grad_norm": 0.41217774020393527,
+      "learning_rate": 1.0007896297828113e-07,
+      "loss": 0.5815,
+      "step": 690
+    },
+    {
+      "epoch": 0.9344624754912185,
+      "grad_norm": 0.4305528132965425,
+      "learning_rate": 7.009749855363457e-08,
+      "loss": 0.5984,
+      "step": 700
+    },
+    {
+      "epoch": 0.9478119394268074,
+      "grad_norm": 0.4237537569089471,
+      "learning_rate": 4.537866186360207e-08,
+      "loss": 0.5797,
+      "step": 710
+    },
+    {
+      "epoch": 0.9611614033623962,
+      "grad_norm": 0.4354601270782283,
+      "learning_rate": 2.59759884041369e-08,
+      "loss": 0.5822,
+      "step": 720
+    },
+    {
+      "epoch": 0.9745108672979851,
+      "grad_norm": 0.4236057022989506,
+      "learning_rate": 1.193150004542204e-08,
+      "loss": 0.6017,
+      "step": 730
+    },
+    {
+      "epoch": 0.9878603312335739,
+      "grad_norm": 0.4253092913652658,
+      "learning_rate": 3.275614021857609e-09,
+      "loss": 0.5792,
+      "step": 740
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.4153479478058976,
+      "learning_rate": 2.7077055103075233e-11,
+      "loss": 0.5653,
+      "step": 750
+    },
+    {
+      "epoch": 1.0,
+      "step": 750,
+      "total_flos": 9.514760021422899e+17,
+      "train_loss": 0.5942036323547363,
+      "train_runtime": 26089.1141,
+      "train_samples_per_second": 14.701,
+      "train_steps_per_second": 0.029
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 250,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.514760021422899e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fad137bd57106bcc425db1982a265d9cdb67508fd32301ed13eaa826b7122860
+size 8017