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:e1c00bebe717c527c663bbb7872f80e13e28e3c96bffd87f71abc7578f2658f4
+size 2384234968

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03616edfc33afa96591f4cb51076780e4080222d11e2115f646950d7f1221a82
+size 4768662910

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d92eaef5e5c63e3c05cb81fe22d3cf5cc510dc53d82dfba31676b70afd1b48d5
+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 +1,484 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.048330191870861725,
+  "eval_steps": 100,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0009666038374172345,
+      "grad_norm": 369.5231018066406,
+      "learning_rate": 4.347826086956522e-07,
+      "loss": 3.4461,
+      "mean_token_accuracy": 0.3868150700815022,
+      "num_tokens": 40960.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.001933207674834469,
+      "grad_norm": 8.95268726348877,
+      "learning_rate": 9.178743961352658e-07,
+      "loss": 0.5822,
+      "mean_token_accuracy": 0.9254892326891422,
+      "num_tokens": 81920.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.0028998115122517037,
+      "grad_norm": 2.769016742706299,
+      "learning_rate": 1.4009661835748794e-06,
+      "loss": 0.2376,
+      "mean_token_accuracy": 0.9577788576483727,
+      "num_tokens": 122880.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.003866415349668938,
+      "grad_norm": 3.782710075378418,
+      "learning_rate": 1.884057971014493e-06,
+      "loss": 0.1884,
+      "mean_token_accuracy": 0.9636497043073178,
+      "num_tokens": 163840.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.004833019187086173,
+      "grad_norm": 2.789309024810791,
+      "learning_rate": 2.3671497584541067e-06,
+      "loss": 0.1947,
+      "mean_token_accuracy": 0.9627446144819259,
+      "num_tokens": 204800.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.005799623024503407,
+      "grad_norm": 2.422899007797241,
+      "learning_rate": 2.85024154589372e-06,
+      "loss": 0.1824,
+      "mean_token_accuracy": 0.9645058684051037,
+      "num_tokens": 245760.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.006766226861920642,
+      "grad_norm": 2.6900641918182373,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.2097,
+      "mean_token_accuracy": 0.9602005794644356,
+      "num_tokens": 286720.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.007732830699337876,
+      "grad_norm": 2.63094162940979,
+      "learning_rate": 3.816425120772947e-06,
+      "loss": 0.1768,
+      "mean_token_accuracy": 0.9676859058439732,
+      "num_tokens": 327680.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.008699434536755112,
+      "grad_norm": 2.2906432151794434,
+      "learning_rate": 4.29951690821256e-06,
+      "loss": 0.1648,
+      "mean_token_accuracy": 0.9686643809080124,
+      "num_tokens": 368640.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.009666038374172346,
+      "grad_norm": 2.4756522178649902,
+      "learning_rate": 4.782608695652174e-06,
+      "loss": 0.1925,
+      "mean_token_accuracy": 0.9628179989755153,
+      "num_tokens": 409600.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.01063264221158958,
+      "grad_norm": 2.2673470973968506,
+      "learning_rate": 5.265700483091788e-06,
+      "loss": 0.1747,
+      "mean_token_accuracy": 0.9666585102677345,
+      "num_tokens": 450560.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.011599246049006815,
+      "grad_norm": 2.789449453353882,
+      "learning_rate": 5.748792270531401e-06,
+      "loss": 0.1906,
+      "mean_token_accuracy": 0.9634784705936908,
+      "num_tokens": 491520.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.01256584988642405,
+      "grad_norm": 2.7611072063446045,
+      "learning_rate": 6.231884057971015e-06,
+      "loss": 0.1761,
+      "mean_token_accuracy": 0.9657534249126911,
+      "num_tokens": 532480.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.013532453723841284,
+      "grad_norm": 3.519171953201294,
+      "learning_rate": 6.7149758454106285e-06,
+      "loss": 0.1764,
+      "mean_token_accuracy": 0.9660469628870487,
+      "num_tokens": 573440.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.014499057561258518,
+      "grad_norm": 2.1807825565338135,
+      "learning_rate": 7.1980676328502416e-06,
+      "loss": 0.1614,
+      "mean_token_accuracy": 0.9683953016996384,
+      "num_tokens": 614400.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.015465661398675752,
+      "grad_norm": 3.275883197784424,
+      "learning_rate": 7.681159420289856e-06,
+      "loss": 0.1929,
+      "mean_token_accuracy": 0.9619618356227875,
+      "num_tokens": 655360.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.016432265236092987,
+      "grad_norm": 3.863208055496216,
+      "learning_rate": 8.164251207729469e-06,
+      "loss": 0.161,
+      "mean_token_accuracy": 0.9687133029103279,
+      "num_tokens": 696320.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.017398869073510223,
+      "grad_norm": 2.4544122219085693,
+      "learning_rate": 8.647342995169083e-06,
+      "loss": 0.1639,
+      "mean_token_accuracy": 0.9678082123398781,
+      "num_tokens": 737280.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.018365472910927456,
+      "grad_norm": 4.147322177886963,
+      "learning_rate": 9.130434782608697e-06,
+      "loss": 0.1807,
+      "mean_token_accuracy": 0.9645058669149875,
+      "num_tokens": 778240.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.019332076748344692,
+      "grad_norm": 2.3229196071624756,
+      "learning_rate": 9.61352657004831e-06,
+      "loss": 0.1891,
+      "mean_token_accuracy": 0.9627690717577935,
+      "num_tokens": 819200.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.020298680585761925,
+      "grad_norm": 2.643085479736328,
+      "learning_rate": 1.0096618357487923e-05,
+      "loss": 0.1819,
+      "mean_token_accuracy": 0.9640900187194348,
+      "num_tokens": 860160.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.02126528442317916,
+      "grad_norm": 2.9034485816955566,
+      "learning_rate": 1.0579710144927536e-05,
+      "loss": 0.1759,
+      "mean_token_accuracy": 0.9664138928055763,
+      "num_tokens": 901120.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.022231888260596393,
+      "grad_norm": 2.4179847240448,
+      "learning_rate": 1.106280193236715e-05,
+      "loss": 0.1813,
+      "mean_token_accuracy": 0.9657044969499111,
+      "num_tokens": 942080.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.02319849209801363,
+      "grad_norm": 2.562081813812256,
+      "learning_rate": 1.1545893719806764e-05,
+      "loss": 0.2016,
+      "mean_token_accuracy": 0.9601027369499207,
+      "num_tokens": 983040.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.024165095935430862,
+      "grad_norm": 2.3962156772613525,
+      "learning_rate": 1.2028985507246379e-05,
+      "loss": 0.2054,
+      "mean_token_accuracy": 0.9603228941559792,
+      "num_tokens": 1024000.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.0251316997728481,
+      "grad_norm": 1.6276367902755737,
+      "learning_rate": 1.2512077294685992e-05,
+      "loss": 0.1957,
+      "mean_token_accuracy": 0.9611056745052338,
+      "num_tokens": 1064960.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.02609830361026533,
+      "grad_norm": 3.4532032012939453,
+      "learning_rate": 1.2995169082125605e-05,
+      "loss": 0.1865,
+      "mean_token_accuracy": 0.9638943210244179,
+      "num_tokens": 1105920.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.027064907447682567,
+      "grad_norm": 2.283540964126587,
+      "learning_rate": 1.3478260869565218e-05,
+      "loss": 0.1789,
+      "mean_token_accuracy": 0.9653864935040474,
+      "num_tokens": 1146880.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.028031511285099803,
+      "grad_norm": 2.705214738845825,
+      "learning_rate": 1.3961352657004831e-05,
+      "loss": 0.1784,
+      "mean_token_accuracy": 0.9650195673108101,
+      "num_tokens": 1187840.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.028998115122517036,
+      "grad_norm": 2.3114984035491943,
+      "learning_rate": 1.4444444444444444e-05,
+      "loss": 0.1652,
+      "mean_token_accuracy": 0.9679060652852058,
+      "num_tokens": 1228800.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.029964718959934272,
+      "grad_norm": 3.872532367706299,
+      "learning_rate": 1.4927536231884059e-05,
+      "loss": 0.1736,
+      "mean_token_accuracy": 0.9662181988358498,
+      "num_tokens": 1269760.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.030931322797351505,
+      "grad_norm": 2.0760674476623535,
+      "learning_rate": 1.5410628019323672e-05,
+      "loss": 0.1862,
+      "mean_token_accuracy": 0.9638453960418701,
+      "num_tokens": 1310720.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.03189792663476874,
+      "grad_norm": 2.7817180156707764,
+      "learning_rate": 1.5893719806763285e-05,
+      "loss": 0.1815,
+      "mean_token_accuracy": 0.9642123267054558,
+      "num_tokens": 1351680.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.032864530472185974,
+      "grad_norm": 2.575498342514038,
+      "learning_rate": 1.6376811594202898e-05,
+      "loss": 0.1848,
+      "mean_token_accuracy": 0.9633806228637696,
+      "num_tokens": 1392640.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.03383113430960321,
+      "grad_norm": 2.7221779823303223,
+      "learning_rate": 1.6859903381642515e-05,
+      "loss": 0.1734,
+      "mean_token_accuracy": 0.9656800329685211,
+      "num_tokens": 1433600.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.034797738147020446,
+      "grad_norm": 2.8657000064849854,
+      "learning_rate": 1.7342995169082128e-05,
+      "loss": 0.2035,
+      "mean_token_accuracy": 0.9611056722700596,
+      "num_tokens": 1474560.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.035764341984437675,
+      "grad_norm": 2.5631914138793945,
+      "learning_rate": 1.782608695652174e-05,
+      "loss": 0.1989,
+      "mean_token_accuracy": 0.9594178073108196,
+      "num_tokens": 1515520.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.03673094582185491,
+      "grad_norm": 1.6768838167190552,
+      "learning_rate": 1.8309178743961354e-05,
+      "loss": 0.1751,
+      "mean_token_accuracy": 0.9656311109662056,
+      "num_tokens": 1556480.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.03769754965927215,
+      "grad_norm": 2.1092283725738525,
+      "learning_rate": 1.8792270531400967e-05,
+      "loss": 0.171,
+      "mean_token_accuracy": 0.9668786637485027,
+      "num_tokens": 1597440.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.038664153496689384,
+      "grad_norm": 1.6527000665664673,
+      "learning_rate": 1.927536231884058e-05,
+      "loss": 0.1859,
+      "mean_token_accuracy": 0.9633806236088276,
+      "num_tokens": 1638400.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.03963075733410661,
+      "grad_norm": 1.8731212615966797,
+      "learning_rate": 1.9758454106280193e-05,
+      "loss": 0.1793,
+      "mean_token_accuracy": 0.9640655569732189,
+      "num_tokens": 1679360.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.04059736117152385,
+      "grad_norm": 2.0293846130371094,
+      "learning_rate": 2.0241545893719806e-05,
+      "loss": 0.1973,
+      "mean_token_accuracy": 0.9617906019091607,
+      "num_tokens": 1720320.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.041563965008941085,
+      "grad_norm": 1.9152086973190308,
+      "learning_rate": 2.072463768115942e-05,
+      "loss": 0.1761,
+      "mean_token_accuracy": 0.9663894273340702,
+      "num_tokens": 1761280.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.04253056884635832,
+      "grad_norm": 2.1609811782836914,
+      "learning_rate": 2.1207729468599036e-05,
+      "loss": 0.1928,
+      "mean_token_accuracy": 0.9629158526659012,
+      "num_tokens": 1802240.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.04349717268377556,
+      "grad_norm": 1.874552845954895,
+      "learning_rate": 2.169082125603865e-05,
+      "loss": 0.1857,
+      "mean_token_accuracy": 0.9633316978812217,
+      "num_tokens": 1843200.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.04446377652119279,
+      "grad_norm": 1.9282889366149902,
+      "learning_rate": 2.2173913043478262e-05,
+      "loss": 0.2035,
+      "mean_token_accuracy": 0.9598581179976463,
+      "num_tokens": 1884160.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.04543038035861002,
+      "grad_norm": 2.0976312160491943,
+      "learning_rate": 2.2657004830917875e-05,
+      "loss": 0.1834,
+      "mean_token_accuracy": 0.9649461798369885,
+      "num_tokens": 1925120.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.04639698419602726,
+      "grad_norm": 3.162335157394409,
+      "learning_rate": 2.314009661835749e-05,
+      "loss": 0.1836,
+      "mean_token_accuracy": 0.9647260263562203,
+      "num_tokens": 1966080.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.047363588033444495,
+      "grad_norm": 2.107750177383423,
+      "learning_rate": 2.36231884057971e-05,
+      "loss": 0.1799,
+      "mean_token_accuracy": 0.9659246519207955,
+      "num_tokens": 2007040.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.048330191870861725,
+      "grad_norm": 2.098088026046753,
+      "learning_rate": 2.4106280193236715e-05,
+      "loss": 0.183,
+      "mean_token_accuracy": 0.9639921717345714,
+      "num_tokens": 2048000.0,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 10345,
+  "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 sha256:923dcbba36717bc48fcf276ff3d77a13cc027207e3c1ddba95a3815de676cdb7
+size 5688