Training in progress, step 267, checkpoint

.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
+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:cffb36aa50f64717783538c5ee5e8dfcdafa6e5ebf368216980d32f29984a90c
+size 2384234968

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a8be2cb76f0095ad22136d708d6142354f7e4286aaea83113cca6e8888c8e62
+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:ed5c253a48e6001901218a2e9de2ab738bbeb1dc1ea233eaecf6152cbd749c0c
+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 +1,268 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9990645463049579,
+  "eval_steps": 100,
+  "global_step": 267,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.037418147801683815,
+      "grad_norm": 3.605011224746704,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.3411,
+      "mean_token_accuracy": 0.7953277874737978,
+      "num_tokens": 40960.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.07483629560336763,
+      "grad_norm": 3.451061964035034,
+      "learning_rate": 3.518518518518519e-05,
+      "loss": 0.1369,
+      "mean_token_accuracy": 0.9616682939231396,
+      "num_tokens": 81920.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.11225444340505145,
+      "grad_norm": 2.5540621280670166,
+      "learning_rate": 4.958333333333334e-05,
+      "loss": 0.1633,
+      "mean_token_accuracy": 0.954109588265419,
+      "num_tokens": 122880.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.14967259120673526,
+      "grad_norm": 4.433518886566162,
+      "learning_rate": 4.75e-05,
+      "loss": 0.1509,
+      "mean_token_accuracy": 0.9584148712456226,
+      "num_tokens": 163840.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.18709073900841908,
+      "grad_norm": 2.500624179840088,
+      "learning_rate": 4.541666666666667e-05,
+      "loss": 0.1638,
+      "mean_token_accuracy": 0.9535224996507168,
+      "num_tokens": 204800.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.2245088868101029,
+      "grad_norm": 1.5342501401901245,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.1634,
+      "mean_token_accuracy": 0.9534246526658535,
+      "num_tokens": 245760.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.26192703461178674,
+      "grad_norm": 1.9312411546707153,
+      "learning_rate": 4.125e-05,
+      "loss": 0.141,
+      "mean_token_accuracy": 0.9598091915249825,
+      "num_tokens": 286720.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.2993451824134705,
+      "grad_norm": 1.3097331523895264,
+      "learning_rate": 3.9166666666666665e-05,
+      "loss": 0.1598,
+      "mean_token_accuracy": 0.954647745192051,
+      "num_tokens": 327680.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.33676333021515437,
+      "grad_norm": 1.5079143047332764,
+      "learning_rate": 3.708333333333334e-05,
+      "loss": 0.142,
+      "mean_token_accuracy": 0.958488255739212,
+      "num_tokens": 368640.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.37418147801683815,
+      "grad_norm": 1.202209234237671,
+      "learning_rate": 3.5e-05,
+      "loss": 0.1459,
+      "mean_token_accuracy": 0.9584882512688637,
+      "num_tokens": 409600.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.411599625818522,
+      "grad_norm": 1.2866814136505127,
+      "learning_rate": 3.291666666666667e-05,
+      "loss": 0.1466,
+      "mean_token_accuracy": 0.9581213280558586,
+      "num_tokens": 450560.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.4490177736202058,
+      "grad_norm": 1.4433410167694092,
+      "learning_rate": 3.0833333333333335e-05,
+      "loss": 0.1553,
+      "mean_token_accuracy": 0.957167312502861,
+      "num_tokens": 491520.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.4864359214218896,
+      "grad_norm": 1.7865726947784424,
+      "learning_rate": 2.8749999999999997e-05,
+      "loss": 0.1292,
+      "mean_token_accuracy": 0.9638209342956543,
+      "num_tokens": 532480.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.5238540692235735,
+      "grad_norm": 1.4343348741531372,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.1454,
+      "mean_token_accuracy": 0.9584393322467804,
+      "num_tokens": 573440.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.5612722170252572,
+      "grad_norm": 1.2116364240646362,
+      "learning_rate": 2.4583333333333332e-05,
+      "loss": 0.1336,
+      "mean_token_accuracy": 0.9633561626076699,
+      "num_tokens": 614400.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.598690364826941,
+      "grad_norm": 1.7633224725723267,
+      "learning_rate": 2.25e-05,
+      "loss": 0.1319,
+      "mean_token_accuracy": 0.9626712270081044,
+      "num_tokens": 655360.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.6361085126286249,
+      "grad_norm": 1.3809901475906372,
+      "learning_rate": 2.0416666666666667e-05,
+      "loss": 0.129,
+      "mean_token_accuracy": 0.963209392875433,
+      "num_tokens": 696320.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.6735266604303087,
+      "grad_norm": 1.4324010610580444,
+      "learning_rate": 1.8333333333333333e-05,
+      "loss": 0.1278,
+      "mean_token_accuracy": 0.9635273940861225,
+      "num_tokens": 737280.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.7109448082319925,
+      "grad_norm": 1.3217487335205078,
+      "learning_rate": 1.6250000000000002e-05,
+      "loss": 0.2005,
+      "mean_token_accuracy": 0.9594178041443229,
+      "num_tokens": 778240.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.7483629560336763,
+      "grad_norm": 1.0903115272521973,
+      "learning_rate": 1.4166666666666668e-05,
+      "loss": 0.1028,
+      "mean_token_accuracy": 0.9706457890570164,
+      "num_tokens": 819200.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.7857811038353602,
+      "grad_norm": 1.6808840036392212,
+      "learning_rate": 1.2083333333333333e-05,
+      "loss": 0.108,
+      "mean_token_accuracy": 0.9681751407682896,
+      "num_tokens": 860160.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.823199251637044,
+      "grad_norm": 1.3859535455703735,
+      "learning_rate": 1e-05,
+      "loss": 0.1081,
+      "mean_token_accuracy": 0.9688111506402493,
+      "num_tokens": 901120.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.8606173994387278,
+      "grad_norm": 0.9109633564949036,
+      "learning_rate": 7.916666666666667e-06,
+      "loss": 0.1121,
+      "mean_token_accuracy": 0.9680039115250111,
+      "num_tokens": 942080.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.8980355472404116,
+      "grad_norm": 1.237545132637024,
+      "learning_rate": 5.833333333333334e-06,
+      "loss": 0.1042,
+      "mean_token_accuracy": 0.9695939309895039,
+      "num_tokens": 983040.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "grad_norm": 1.4165068864822388,
+      "learning_rate": 3.75e-06,
+      "loss": 0.0941,
+      "mean_token_accuracy": 0.9729452036321163,
+      "num_tokens": 1024000.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.9728718428437793,
+      "grad_norm": 1.478573203086853,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.0988,
+      "mean_token_accuracy": 0.9710616409778595,
+      "num_tokens": 1064960.0,
+      "step": 260
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 267,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2890255829041152.0,
+  "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 sha256:0068838ff84dd3f6911031145c530de057ff9a52ef6f8c8424fa8d98151e6275
+size 5688