Training in progress, step 500, checkpoint

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* 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
+last-checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text

last-checkpoint/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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
+}

last-checkpoint/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

last-checkpoint/config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.52.2"
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01b3db4645b756626ddb7973621c7080eb13b0cd3e61a68e8900b8dad0bdf8cf
+size 2384234968

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3c79b3b09e0fde56710ab2921706a60ecd1ab3863b5011393584ba98921bd47
+size 4768663315

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fd9432b50864b1799d071a2391f13a188cc959e985675ab69fd688672db2853
+size 14645

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cffb954d72cf1189fd8e1ba7b775e0ce7b92c5c02d033bea47ee68057e2ca6b1
+size 1465

last-checkpoint/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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:574de68a0f63f2004784a421c7d42c2b2786c05cb38542d2ed3525757a1f7fde
+size 11422932

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "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": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,524 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.16732201121057474,
+  "eval_steps": 100,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003346440224211495,
+      "grad_norm": 381.50091552734375,
+      "learning_rate": 1.0033444816053512e-07,
+      "loss": 2.3531,
+      "mean_token_accuracy": 0.15974804367870094,
+      "num_tokens": 81920.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.00669288044842299,
+      "grad_norm": 108.59841918945312,
+      "learning_rate": 2.118171683389075e-07,
+      "loss": 1.0615,
+      "mean_token_accuracy": 0.6265044037252665,
+      "num_tokens": 163840.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.010039320672634485,
+      "grad_norm": 11.361440658569336,
+      "learning_rate": 3.2329988851727985e-07,
+      "loss": 0.3431,
+      "mean_token_accuracy": 0.8708292551338672,
+      "num_tokens": 245760.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.01338576089684598,
+      "grad_norm": 3.652024507522583,
+      "learning_rate": 4.347826086956522e-07,
+      "loss": 0.1778,
+      "mean_token_accuracy": 0.8943126246333122,
+      "num_tokens": 327680.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.016732201121057475,
+      "grad_norm": 1.5740631818771362,
+      "learning_rate": 5.462653288740246e-07,
+      "loss": 0.1206,
+      "mean_token_accuracy": 0.9035469651222229,
+      "num_tokens": 409600.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.02007864134526897,
+      "grad_norm": 1.726568341255188,
+      "learning_rate": 6.577480490523969e-07,
+      "loss": 0.1,
+      "mean_token_accuracy": 0.8987769059836864,
+      "num_tokens": 491520.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.023425081569480467,
+      "grad_norm": 1.6954574584960938,
+      "learning_rate": 7.692307692307694e-07,
+      "loss": 0.0884,
+      "mean_token_accuracy": 0.9068860106170178,
+      "num_tokens": 573440.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.02677152179369196,
+      "grad_norm": 1.5214804410934448,
+      "learning_rate": 8.807134894091417e-07,
+      "loss": 0.0763,
+      "mean_token_accuracy": 0.900403618067503,
+      "num_tokens": 655360.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.030117962017903455,
+      "grad_norm": 1.4563462734222412,
+      "learning_rate": 9.92196209587514e-07,
+      "loss": 0.0821,
+      "mean_token_accuracy": 0.9011130131781101,
+      "num_tokens": 737280.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.03346440224211495,
+      "grad_norm": 2.252185106277466,
+      "learning_rate": 1.1036789297658864e-06,
+      "loss": 0.0854,
+      "step": 100
+    },
+    {
+      "epoch": 0.03346440224211495,
+      "eval_loss": 0.16463333368301392,
+      "eval_mean_token_accuracy": 0.9641127235538609,
+      "eval_num_tokens": 819200.0,
+      "eval_runtime": 175.4066,
+      "eval_samples_per_second": 30.29,
+      "eval_steps_per_second": 1.898,
+      "step": 100
+    },
+    {
+      "epoch": 0.036810842466326446,
+      "grad_norm": 1.5207161903381348,
+      "learning_rate": 1.2151616499442587e-06,
+      "loss": 0.079,
+      "mean_token_accuracy": 0.9014860544353723,
+      "num_tokens": 901120.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.04015728269053794,
+      "grad_norm": 1.2643405199050903,
+      "learning_rate": 1.326644370122631e-06,
+      "loss": 0.0938,
+      "mean_token_accuracy": 0.8938845384865999,
+      "num_tokens": 983040.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.04350372291474944,
+      "grad_norm": 1.358339786529541,
+      "learning_rate": 1.4381270903010034e-06,
+      "loss": 0.0709,
+      "mean_token_accuracy": 0.9086961820721626,
+      "num_tokens": 1064960.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.04685016313896093,
+      "grad_norm": 1.613029956817627,
+      "learning_rate": 1.5496098104793757e-06,
+      "loss": 0.0808,
+      "mean_token_accuracy": 0.9017000988125801,
+      "num_tokens": 1146880.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.05019660336317242,
+      "grad_norm": 1.4856306314468384,
+      "learning_rate": 1.6610925306577483e-06,
+      "loss": 0.0753,
+      "mean_token_accuracy": 0.9064946159720421,
+      "num_tokens": 1228800.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.05354304358738392,
+      "grad_norm": 1.4290050268173218,
+      "learning_rate": 1.7725752508361204e-06,
+      "loss": 0.079,
+      "mean_token_accuracy": 0.9070816986262799,
+      "num_tokens": 1310720.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.056889483811595414,
+      "grad_norm": 1.8561420440673828,
+      "learning_rate": 1.884057971014493e-06,
+      "loss": 0.0835,
+      "mean_token_accuracy": 0.9007093951106071,
+      "num_tokens": 1392640.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.06023592403580691,
+      "grad_norm": 1.7619956731796265,
+      "learning_rate": 1.9955406911928653e-06,
+      "loss": 0.0777,
+      "mean_token_accuracy": 0.9031800344586373,
+      "num_tokens": 1474560.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.06358236426001841,
+      "grad_norm": 1.7907612323760986,
+      "learning_rate": 2.1070234113712374e-06,
+      "loss": 0.0778,
+      "mean_token_accuracy": 0.901002936810255,
+      "num_tokens": 1556480.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.0669288044842299,
+      "grad_norm": 1.2975612878799438,
+      "learning_rate": 2.21850613154961e-06,
+      "loss": 0.0784,
+      "step": 200
+    },
+    {
+      "epoch": 0.0669288044842299,
+      "eval_loss": 0.1590431183576584,
+      "eval_mean_token_accuracy": 0.9647363902212264,
+      "eval_num_tokens": 1638400.0,
+      "eval_runtime": 176.3424,
+      "eval_samples_per_second": 30.129,
+      "eval_steps_per_second": 1.888,
+      "step": 200
+    },
+    {
+      "epoch": 0.07027524470844139,
+      "grad_norm": 1.2653632164001465,
+      "learning_rate": 2.329988851727982e-06,
+      "loss": 0.0754,
+      "mean_token_accuracy": 0.9063295017927885,
+      "num_tokens": 1720320.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.07362168493265289,
+      "grad_norm": 1.3196860551834106,
+      "learning_rate": 2.4414715719063546e-06,
+      "loss": 0.0831,
+      "mean_token_accuracy": 0.9038772054016591,
+      "num_tokens": 1802240.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.07696812515686438,
+      "grad_norm": 2.6671698093414307,
+      "learning_rate": 2.552954292084727e-06,
+      "loss": 0.0824,
+      "mean_token_accuracy": 0.9060909979045391,
+      "num_tokens": 1884160.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.08031456538107588,
+      "grad_norm": 1.3936796188354492,
+      "learning_rate": 2.6644370122630997e-06,
+      "loss": 0.0818,
+      "mean_token_accuracy": 0.9011741690337658,
+      "num_tokens": 1966080.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.08366100560528737,
+      "grad_norm": 1.2653836011886597,
+      "learning_rate": 2.7759197324414714e-06,
+      "loss": 0.0824,
+      "mean_token_accuracy": 0.9036448128521443,
+      "num_tokens": 2048000.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.08700744582949888,
+      "grad_norm": 1.739853024482727,
+      "learning_rate": 2.887402452619844e-06,
+      "loss": 0.084,
+      "mean_token_accuracy": 0.9064579255878925,
+      "num_tokens": 2129920.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.09035388605371036,
+      "grad_norm": 1.2843964099884033,
+      "learning_rate": 2.9988851727982165e-06,
+      "loss": 0.0802,
+      "mean_token_accuracy": 0.9025440298020839,
+      "num_tokens": 2211840.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.09370032627792187,
+      "grad_norm": 1.6027252674102783,
+      "learning_rate": 3.110367892976589e-06,
+      "loss": 0.0856,
+      "mean_token_accuracy": 0.8990215286612511,
+      "num_tokens": 2293760.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.09704676650213336,
+      "grad_norm": 1.1412756443023682,
+      "learning_rate": 3.2218506131549616e-06,
+      "loss": 0.0828,
+      "mean_token_accuracy": 0.898263206705451,
+      "num_tokens": 2375680.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.10039320672634484,
+      "grad_norm": 1.7126843929290771,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.0832,
+      "step": 300
+    },
+    {
+      "epoch": 0.10039320672634484,
+      "eval_loss": 0.15664729475975037,
+      "eval_mean_token_accuracy": 0.9648091143315977,
+      "eval_num_tokens": 2457600.0,
+      "eval_runtime": 175.0886,
+      "eval_samples_per_second": 30.345,
+      "eval_steps_per_second": 1.902,
+      "step": 300
+    },
+    {
+      "epoch": 0.10373964695055635,
+      "grad_norm": 1.1052848100662231,
+      "learning_rate": 3.444816053511706e-06,
+      "loss": 0.0801,
+      "mean_token_accuracy": 0.9030760779976845,
+      "num_tokens": 2539520.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.10708608717476784,
+      "grad_norm": 1.6072983741760254,
+      "learning_rate": 3.5562987736900784e-06,
+      "loss": 0.071,
+      "mean_token_accuracy": 0.9074119366705418,
+      "num_tokens": 2621440.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.11043252739897934,
+      "grad_norm": 1.0676347017288208,
+      "learning_rate": 3.667781493868451e-06,
+      "loss": 0.0839,
+      "mean_token_accuracy": 0.9030088067054749,
+      "num_tokens": 2703360.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.11377896762319083,
+      "grad_norm": 1.418855905532837,
+      "learning_rate": 3.7792642140468235e-06,
+      "loss": 0.0781,
+      "mean_token_accuracy": 0.9011252447962761,
+      "num_tokens": 2785280.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.11712540784740233,
+      "grad_norm": 1.4775986671447754,
+      "learning_rate": 3.890746934225196e-06,
+      "loss": 0.0892,
+      "mean_token_accuracy": 0.899718688428402,
+      "num_tokens": 2867200.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.12047184807161382,
+      "grad_norm": 1.73708176612854,
+      "learning_rate": 4.002229654403568e-06,
+      "loss": 0.0779,
+      "mean_token_accuracy": 0.9028987258672714,
+      "num_tokens": 2949120.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.12381828829582532,
+      "grad_norm": 1.9001389741897583,
+      "learning_rate": 4.11371237458194e-06,
+      "loss": 0.0847,
+      "mean_token_accuracy": 0.901920247823,
+      "num_tokens": 3031040.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.12716472852003682,
+      "grad_norm": 1.1271719932556152,
+      "learning_rate": 4.225195094760313e-06,
+      "loss": 0.0756,
+      "mean_token_accuracy": 0.8988625220954418,
+      "num_tokens": 3112960.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.1305111687442483,
+      "grad_norm": 1.6783229112625122,
+      "learning_rate": 4.336677814938685e-06,
+      "loss": 0.0801,
+      "mean_token_accuracy": 0.8964407987892627,
+      "num_tokens": 3194880.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.1338576089684598,
+      "grad_norm": 1.6774762868881226,
+      "learning_rate": 4.448160535117057e-06,
+      "loss": 0.081,
+      "step": 400
+    },
+    {
+      "epoch": 0.1338576089684598,
+      "eval_loss": 0.15611669421195984,
+      "eval_mean_token_accuracy": 0.9646247326432764,
+      "eval_num_tokens": 3276800.0,
+      "eval_runtime": 175.7197,
+      "eval_samples_per_second": 30.236,
+      "eval_steps_per_second": 1.895,
+      "step": 400
+    },
+    {
+      "epoch": 0.1372040491926713,
+      "grad_norm": 1.566451907157898,
+      "learning_rate": 4.559643255295429e-06,
+      "loss": 0.0748,
+      "mean_token_accuracy": 0.902238254994154,
+      "num_tokens": 3358720.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.14055048941688278,
+      "grad_norm": 1.9855010509490967,
+      "learning_rate": 4.671125975473802e-06,
+      "loss": 0.0793,
+      "mean_token_accuracy": 0.8993517622351647,
+      "num_tokens": 3440640.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.1438969296410943,
+      "grad_norm": 1.4213474988937378,
+      "learning_rate": 4.782608695652174e-06,
+      "loss": 0.081,
+      "mean_token_accuracy": 0.9107754409313202,
+      "num_tokens": 3522560.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.14724336986530578,
+      "grad_norm": 1.1975512504577637,
+      "learning_rate": 4.894091415830547e-06,
+      "loss": 0.0779,
+      "mean_token_accuracy": 0.9046599790453911,
+      "num_tokens": 3604480.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.15058981008951727,
+      "grad_norm": 1.486319661140442,
+      "learning_rate": 5.0055741360089194e-06,
+      "loss": 0.0774,
+      "mean_token_accuracy": 0.908084636181593,
+      "num_tokens": 3686400.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.15393625031372876,
+      "grad_norm": 1.5909311771392822,
+      "learning_rate": 5.1170568561872916e-06,
+      "loss": 0.0738,
+      "mean_token_accuracy": 0.9056506864726543,
+      "num_tokens": 3768320.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.15728269053794028,
+      "grad_norm": 1.4979009628295898,
+      "learning_rate": 5.228539576365663e-06,
+      "loss": 0.08,
+      "mean_token_accuracy": 0.8925146766006946,
+      "num_tokens": 3850240.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.16062913076215177,
+      "grad_norm": 1.234427809715271,
+      "learning_rate": 5.340022296544037e-06,
+      "loss": 0.0737,
+      "mean_token_accuracy": 0.9070327773690223,
+      "num_tokens": 3932160.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.16397557098636326,
+      "grad_norm": 1.022118091583252,
+      "learning_rate": 5.451505016722408e-06,
+      "loss": 0.0714,
+      "mean_token_accuracy": 0.9069349311292172,
+      "num_tokens": 4014080.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.16732201121057474,
+      "grad_norm": 1.6332159042358398,
+      "learning_rate": 5.562987736900781e-06,
+      "loss": 0.075,
+      "step": 500
+    },
+    {
+      "epoch": 0.16732201121057474,
+      "eval_loss": 0.15604229271411896,
+      "eval_mean_token_accuracy": 0.9643613817813518,
+      "eval_num_tokens": 4096000.0,
+      "eval_runtime": 175.0619,
+      "eval_samples_per_second": 30.349,
+      "eval_steps_per_second": 1.902,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 8967,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0824928198656e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d4f6f13fea75164963245fb8d890903867d91777044058c6a0690e2ac12c8aa
+size 6033