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/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": "4.51.3",
+  "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": "4.51.3"
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e9eed224d3bd813c5df4c08c85c0e11044545cfb849478ca85f994c86316646
+size 2384234968

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:552a7fd8dc36826bd7d6cd9f01c77507ab64af35744990ede135cb2acdbe3f53
+size 4768662910

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c062f7f375beded48b5337f5a3f3a5cb38807fa3e85dbf3e294c0ab6b627bfc2
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0c8d55f92f35c67a58bda9590da57d8bcab1a0dd313128c3bee737dbccd6b81
+size 1064

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 +1,240 @@
+{
+  "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,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "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": 0.25903380391141045,
+  "eval_steps": 100,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005180676078228209,
+      "grad_norm": 9.631562232971191,
+      "learning_rate": 2.3316062176165805e-06,
+      "loss": 2.0771,
+      "mean_token_accuracy": 0.6386007816530764,
+      "num_tokens": 40960.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.010361352156456418,
+      "grad_norm": 1.819643497467041,
+      "learning_rate": 4.922279792746115e-06,
+      "loss": 0.1913,
+      "mean_token_accuracy": 0.9666340440511704,
+      "num_tokens": 81920.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.015542028234684627,
+      "grad_norm": 2.19582462310791,
+      "learning_rate": 7.512953367875648e-06,
+      "loss": 0.1629,
+      "mean_token_accuracy": 0.9710371799767017,
+      "num_tokens": 122880.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.020722704312912836,
+      "grad_norm": 2.09656023979187,
+      "learning_rate": 1.0103626943005182e-05,
+      "loss": 0.1689,
+      "mean_token_accuracy": 0.9700342409312726,
+      "num_tokens": 163840.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.025903380391141043,
+      "grad_norm": 1.7483199834823608,
+      "learning_rate": 1.2694300518134716e-05,
+      "loss": 0.1487,
+      "mean_token_accuracy": 0.9729207403957844,
+      "num_tokens": 204800.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.031084056469369254,
+      "grad_norm": 2.3294854164123535,
+      "learning_rate": 1.528497409326425e-05,
+      "loss": 0.1494,
+      "mean_token_accuracy": 0.9720156528055668,
+      "num_tokens": 245760.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.03626473254759746,
+      "grad_norm": 1.9827619791030884,
+      "learning_rate": 1.7875647668393784e-05,
+      "loss": 0.1424,
+      "mean_token_accuracy": 0.973532286286354,
+      "num_tokens": 286720.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.04144540862582567,
+      "grad_norm": 1.5699920654296875,
+      "learning_rate": 2.046632124352332e-05,
+      "loss": 0.1562,
+      "mean_token_accuracy": 0.9710616432130337,
+      "num_tokens": 327680.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.046626084704053876,
+      "grad_norm": 2.7447657585144043,
+      "learning_rate": 2.305699481865285e-05,
+      "loss": 0.1479,
+      "mean_token_accuracy": 0.9731653571128845,
+      "num_tokens": 368640.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.05180676078228209,
+      "grad_norm": 2.623384952545166,
+      "learning_rate": 2.5647668393782386e-05,
+      "loss": 0.1422,
+      "step": 100
+    },
+    {
+      "epoch": 0.05180676078228209,
+      "eval_loss": 0.15581642091274261,
+      "eval_mean_token_accuracy": 0.9712158047875693,
+      "eval_num_tokens": 409600.0,
+      "eval_runtime": 177.4594,
+      "eval_samples_per_second": 9.67,
+      "eval_steps_per_second": 1.212,
+      "step": 100
+    },
+    {
+      "epoch": 0.0569874368605103,
+      "grad_norm": 2.979398727416992,
+      "learning_rate": 2.8238341968911917e-05,
+      "loss": 0.1569,
+      "mean_token_accuracy": 0.9724681995809078,
+      "num_tokens": 450560.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.06216811293873851,
+      "grad_norm": 1.68087899684906,
+      "learning_rate": 3.082901554404145e-05,
+      "loss": 0.171,
+      "mean_token_accuracy": 0.9687133096158504,
+      "num_tokens": 491520.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.06734878901696671,
+      "grad_norm": 2.029513359069824,
+      "learning_rate": 3.341968911917099e-05,
+      "loss": 0.1498,
+      "mean_token_accuracy": 0.972235807031393,
+      "num_tokens": 532480.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.07252946509519492,
+      "grad_norm": 2.0309629440307617,
+      "learning_rate": 3.601036269430052e-05,
+      "loss": 0.1564,
+      "mean_token_accuracy": 0.9711105629801751,
+      "num_tokens": 573440.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.07771014117342313,
+      "grad_norm": 1.7547311782836914,
+      "learning_rate": 3.860103626943005e-05,
+      "loss": 0.1536,
+      "mean_token_accuracy": 0.9727984294295311,
+      "num_tokens": 614400.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.08289081725165134,
+      "grad_norm": 1.3721349239349365,
+      "learning_rate": 4.119170984455959e-05,
+      "loss": 0.1548,
+      "mean_token_accuracy": 0.9722113467752933,
+      "num_tokens": 655360.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.08807149332987955,
+      "grad_norm": 1.3339269161224365,
+      "learning_rate": 4.378238341968912e-05,
+      "loss": 0.1533,
+      "mean_token_accuracy": 0.9719911918044091,
+      "num_tokens": 696320.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.09325216940810775,
+      "grad_norm": 1.2086386680603027,
+      "learning_rate": 4.637305699481865e-05,
+      "loss": 0.1655,
+      "mean_token_accuracy": 0.9697407022118568,
+      "num_tokens": 737280.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.09843284548633596,
+      "grad_norm": 1.2023117542266846,
+      "learning_rate": 4.896373056994819e-05,
+      "loss": 0.1638,
+      "mean_token_accuracy": 0.9714774921536445,
+      "num_tokens": 778240.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.10361352156456417,
+      "grad_norm": 1.2918652296066284,
+      "learning_rate": 4.98272884283247e-05,
+      "loss": 0.1709,
+      "step": 200
+    },
+    {
+      "epoch": 0.10361352156456417,
+      "eval_loss": 0.16902239620685577,
+      "eval_mean_token_accuracy": 0.9694170064704363,
+      "eval_num_tokens": 819200.0,
+      "eval_runtime": 177.4638,
+      "eval_samples_per_second": 9.67,
+      "eval_steps_per_second": 1.212,
+      "step": 200
+    },
+    {
+      "epoch": 0.10879419764279238,
+      "grad_norm": 1.277097225189209,
+      "learning_rate": 4.9539435808865864e-05,
+      "loss": 0.1797,
+      "mean_token_accuracy": 0.9680528327822685,
+      "num_tokens": 860160.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.1139748737210206,
+      "grad_norm": 1.4949145317077637,
+      "learning_rate": 4.9251583189407024e-05,
+      "loss": 0.179,
+      "mean_token_accuracy": 0.9680528305470943,
+      "num_tokens": 901120.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.1191555497992488,
+      "grad_norm": 1.0055022239685059,
+      "learning_rate": 4.896373056994819e-05,
+      "loss": 0.1816,
+      "mean_token_accuracy": 0.9672211326658726,
+      "num_tokens": 942080.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.12433622587747702,
+      "grad_norm": 0.9761211276054382,
+      "learning_rate": 4.867587795048935e-05,
+      "loss": 0.1787,
+      "mean_token_accuracy": 0.9677837535738945,
+      "num_tokens": 983040.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.12951690195570523,
+      "grad_norm": 1.2591373920440674,
+      "learning_rate": 4.838802533103051e-05,
+      "loss": 0.1656,
+      "mean_token_accuracy": 0.9696673184633255,
+      "num_tokens": 1024000.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.13469757803393342,
+      "grad_norm": 1.2907938957214355,
+      "learning_rate": 4.810017271157168e-05,
+      "loss": 0.1882,
+      "mean_token_accuracy": 0.9655088044703006,
+      "num_tokens": 1064960.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.13987825411216165,
+      "grad_norm": 0.9908541440963745,
+      "learning_rate": 4.781232009211284e-05,
+      "loss": 0.1618,
+      "mean_token_accuracy": 0.9706947103142738,
+      "num_tokens": 1105920.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.14505893019038985,
+      "grad_norm": 0.9391453266143799,
+      "learning_rate": 4.7524467472654005e-05,
+      "loss": 0.1855,
+      "mean_token_accuracy": 0.9663405083119869,
+      "num_tokens": 1146880.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.15023960626861804,
+      "grad_norm": 1.1234341859817505,
+      "learning_rate": 4.7236614853195165e-05,
+      "loss": 0.1743,
+      "mean_token_accuracy": 0.969251461327076,
+      "num_tokens": 1187840.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.15542028234684627,
+      "grad_norm": 1.5260945558547974,
+      "learning_rate": 4.694876223373633e-05,
+      "loss": 0.1791,
+      "step": 300
+    },
+    {
+      "epoch": 0.15542028234684627,
+      "eval_loss": 0.17322979867458344,
+      "eval_mean_token_accuracy": 0.9691120893456215,
+      "eval_num_tokens": 1228800.0,
+      "eval_runtime": 177.4355,
+      "eval_samples_per_second": 9.671,
+      "eval_steps_per_second": 1.212,
+      "step": 300
+    },
+    {
+      "epoch": 0.16060095842507446,
+      "grad_norm": 0.9628911018371582,
+      "learning_rate": 4.666090961427749e-05,
+      "loss": 0.1636,
+      "mean_token_accuracy": 0.9689946133643389,
+      "num_tokens": 1269760.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.1657816345033027,
+      "grad_norm": 0.9426960945129395,
+      "learning_rate": 4.637305699481865e-05,
+      "loss": 0.167,
+      "mean_token_accuracy": 0.968272989988327,
+      "num_tokens": 1310720.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.17096231058153089,
+      "grad_norm": 1.0766854286193848,
+      "learning_rate": 4.608520437535982e-05,
+      "loss": 0.1692,
+      "mean_token_accuracy": 0.970156553387642,
+      "num_tokens": 1351680.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.1761429866597591,
+      "grad_norm": 1.1832035779953003,
+      "learning_rate": 4.579735175590098e-05,
+      "loss": 0.1818,
+      "mean_token_accuracy": 0.9677348293364048,
+      "num_tokens": 1392640.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.1813236627379873,
+      "grad_norm": 0.8449466228485107,
+      "learning_rate": 4.550949913644215e-05,
+      "loss": 0.1615,
+      "mean_token_accuracy": 0.9707191742956638,
+      "num_tokens": 1433600.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.1865043388162155,
+      "grad_norm": 0.9959536194801331,
+      "learning_rate": 4.522164651698331e-05,
+      "loss": 0.1717,
+      "mean_token_accuracy": 0.9689334571361542,
+      "num_tokens": 1474560.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.19168501489444373,
+      "grad_norm": 0.7823560833930969,
+      "learning_rate": 4.493379389752447e-05,
+      "loss": 0.1616,
+      "mean_token_accuracy": 0.9712084122002125,
+      "num_tokens": 1515520.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.19686569097267193,
+      "grad_norm": 0.7874719500541687,
+      "learning_rate": 4.4645941278065634e-05,
+      "loss": 0.1724,
+      "mean_token_accuracy": 0.9685909941792488,
+      "num_tokens": 1556480.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.20204636705090015,
+      "grad_norm": 1.198121428489685,
+      "learning_rate": 4.4358088658606794e-05,
+      "loss": 0.1747,
+      "mean_token_accuracy": 0.9693737730383873,
+      "num_tokens": 1597440.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.20722704312912835,
+      "grad_norm": 1.0949692726135254,
+      "learning_rate": 4.407023603914796e-05,
+      "loss": 0.1589,
+      "step": 400
+    },
+    {
+      "epoch": 0.20722704312912835,
+      "eval_loss": 0.1715448498725891,
+      "eval_mean_token_accuracy": 0.9692747881246168,
+      "eval_num_tokens": 1638400.0,
+      "eval_runtime": 177.4616,
+      "eval_samples_per_second": 9.67,
+      "eval_steps_per_second": 1.212,
+      "step": 400
+    },
+    {
+      "epoch": 0.21240771920735657,
+      "grad_norm": 0.926072359085083,
+      "learning_rate": 4.378238341968912e-05,
+      "loss": 0.1626,
+      "mean_token_accuracy": 0.9709271017462016,
+      "num_tokens": 1679360.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.21758839528558477,
+      "grad_norm": 0.9391428232192993,
+      "learning_rate": 4.349453080023028e-05,
+      "loss": 0.1664,
+      "mean_token_accuracy": 0.9698140874505043,
+      "num_tokens": 1720320.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.22276907136381296,
+      "grad_norm": 0.8835638165473938,
+      "learning_rate": 4.320667818077145e-05,
+      "loss": 0.1628,
+      "mean_token_accuracy": 0.9712328791618348,
+      "num_tokens": 1761280.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.2279497474420412,
+      "grad_norm": 0.8858859539031982,
+      "learning_rate": 4.291882556131261e-05,
+      "loss": 0.1617,
+      "mean_token_accuracy": 0.970278862118721,
+      "num_tokens": 1802240.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.2331304235202694,
+      "grad_norm": 1.376945972442627,
+      "learning_rate": 4.2630972941853775e-05,
+      "loss": 0.1694,
+      "mean_token_accuracy": 0.9701320916414261,
+      "num_tokens": 1843200.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.2383110995984976,
+      "grad_norm": 0.9776697754859924,
+      "learning_rate": 4.2343120322394935e-05,
+      "loss": 0.1678,
+      "mean_token_accuracy": 0.9696428522467613,
+      "num_tokens": 1884160.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.2434917756767258,
+      "grad_norm": 0.8785173892974854,
+      "learning_rate": 4.2055267702936095e-05,
+      "loss": 0.1629,
+      "mean_token_accuracy": 0.970865947753191,
+      "num_tokens": 1925120.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.24867245175495403,
+      "grad_norm": 1.2828736305236816,
+      "learning_rate": 4.176741508347726e-05,
+      "loss": 0.165,
+      "mean_token_accuracy": 0.9694960802793503,
+      "num_tokens": 1966080.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.25385312783318226,
+      "grad_norm": 0.9352325797080994,
+      "learning_rate": 4.147956246401842e-05,
+      "loss": 0.1694,
+      "mean_token_accuracy": 0.968590997159481,
+      "num_tokens": 2007040.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.25903380391141045,
+      "grad_norm": 1.1846671104431152,
+      "learning_rate": 4.119170984455959e-05,
+      "loss": 0.1715,
+      "step": 500
+    },
+    {
+      "epoch": 0.25903380391141045,
+      "eval_loss": 0.16875512897968292,
+      "eval_mean_token_accuracy": 0.9695910847464273,
+      "eval_num_tokens": 2048000.0,
+      "eval_runtime": 177.4339,
+      "eval_samples_per_second": 9.671,
+      "eval_steps_per_second": 1.212,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1930,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 5412464099328000.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7afb97c4f060e8acc8324a4c39a9536f1001cd777884a040902b96e560db7741
+size 5624