Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.9310344827586206,
+    "eval_loss": 0.0974782332777977,
+    "eval_runtime": 0.4539,
+    "eval_samples_per_second": 13.217,
+    "eval_steps_per_second": 4.406,
+    "total_flos": 3917060505600.0,
+    "train_loss": 0.09816603043249675,
+    "train_runtime": 131.6086,
+    "train_samples_per_second": 8.753,
+    "train_steps_per_second": 0.106
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-Math-1.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 4096,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.9310344827586206,
+    "eval_loss": 0.0974782332777977,
+    "eval_runtime": 0.4539,
+    "eval_samples_per_second": 13.217,
+    "eval_steps_per_second": 4.406
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "transformers_version": "4.46.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e40b87b173b70e7f77b34dd15af8203995c82ea00128c9134de3e56f422b1eb
+size 3087467144

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": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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
+    }
+  },
+  "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    {%- else %}\n        {{- 'Please reason step by step, and put your final answer within \\\\boxed{}.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\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    {%- else %}\n        {{- '<|im_start|>system\\nPlease reason step by step, and put your final answer within \\\\boxed{}.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) 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{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.9310344827586206,
+    "total_flos": 3917060505600.0,
+    "train_loss": 0.09816603043249675,
+    "train_runtime": 131.6086,
+    "train_samples_per_second": 8.753,
+    "train_steps_per_second": 0.106
+}

trainer_log.jsonl

@@ -0,0 +1,15 @@
+{"current_steps": 1, "total_steps": 14, "loss": 0.1155, "lr": 9.874639560909118e-06, "epoch": 0.13793103448275862, "percentage": 7.14, "elapsed_time": "0:00:10", "remaining_time": "0:02:16"}
+{"current_steps": 2, "total_steps": 14, "loss": 0.1122, "lr": 9.504844339512096e-06, "epoch": 0.27586206896551724, "percentage": 14.29, "elapsed_time": "0:00:18", "remaining_time": "0:01:53"}
+{"current_steps": 3, "total_steps": 14, "loss": 0.1111, "lr": 8.90915741234015e-06, "epoch": 0.41379310344827586, "percentage": 21.43, "elapsed_time": "0:00:27", "remaining_time": "0:01:39"}
+{"current_steps": 4, "total_steps": 14, "loss": 0.1049, "lr": 8.117449009293668e-06, "epoch": 0.5517241379310345, "percentage": 28.57, "elapsed_time": "0:00:35", "remaining_time": "0:01:28"}
+{"current_steps": 5, "total_steps": 14, "loss": 0.0975, "lr": 7.169418695587791e-06, "epoch": 0.6896551724137931, "percentage": 35.71, "elapsed_time": "0:00:43", "remaining_time": "0:01:19"}
+{"current_steps": 6, "total_steps": 14, "loss": 0.0939, "lr": 6.112604669781572e-06, "epoch": 0.8275862068965517, "percentage": 42.86, "elapsed_time": "0:00:52", "remaining_time": "0:01:09"}
+{"current_steps": 7, "total_steps": 14, "loss": 0.0941, "lr": 5e-06, "epoch": 0.9655172413793104, "percentage": 50.0, "elapsed_time": "0:01:00", "remaining_time": "0:01:00"}
+{"current_steps": 8, "total_steps": 14, "loss": 0.1563, "lr": 3.887395330218429e-06, "epoch": 1.103448275862069, "percentage": 57.14, "elapsed_time": "0:01:09", "remaining_time": "0:00:51"}
+{"current_steps": 9, "total_steps": 14, "loss": 0.0807, "lr": 2.83058130441221e-06, "epoch": 1.2413793103448276, "percentage": 64.29, "elapsed_time": "0:01:17", "remaining_time": "0:00:42"}
+{"current_steps": 10, "total_steps": 14, "loss": 0.0818, "lr": 1.8825509907063328e-06, "epoch": 1.3793103448275863, "percentage": 71.43, "elapsed_time": "0:01:25", "remaining_time": "0:00:34"}
+{"current_steps": 11, "total_steps": 14, "loss": 0.0826, "lr": 1.0908425876598512e-06, "epoch": 1.5172413793103448, "percentage": 78.57, "elapsed_time": "0:01:34", "remaining_time": "0:00:25"}
+{"current_steps": 12, "total_steps": 14, "loss": 0.0805, "lr": 4.951556604879049e-07, "epoch": 1.6551724137931034, "percentage": 85.71, "elapsed_time": "0:01:42", "remaining_time": "0:00:17"}
+{"current_steps": 13, "total_steps": 14, "loss": 0.0843, "lr": 1.253604390908819e-07, "epoch": 1.793103448275862, "percentage": 92.86, "elapsed_time": "0:01:50", "remaining_time": "0:00:08"}
+{"current_steps": 14, "total_steps": 14, "loss": 0.0789, "lr": 0.0, "epoch": 1.9310344827586206, "percentage": 100.0, "elapsed_time": "0:01:59", "remaining_time": "0:00:00"}
+{"current_steps": 14, "total_steps": 14, "epoch": 1.9310344827586206, "percentage": 100.0, "elapsed_time": "0:02:11", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,140 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9310344827586206,
+  "eval_steps": 500,
+  "global_step": 14,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 0.4272040277310641,
+      "learning_rate": 9.874639560909118e-06,
+      "loss": 0.1155,
+      "step": 1
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 0.33370397348921355,
+      "learning_rate": 9.504844339512096e-06,
+      "loss": 0.1122,
+      "step": 2
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 0.2722318279876112,
+      "learning_rate": 8.90915741234015e-06,
+      "loss": 0.1111,
+      "step": 3
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 0.2450831855602725,
+      "learning_rate": 8.117449009293668e-06,
+      "loss": 0.1049,
+      "step": 4
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.19900057099760882,
+      "learning_rate": 7.169418695587791e-06,
+      "loss": 0.0975,
+      "step": 5
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 0.18810176402486756,
+      "learning_rate": 6.112604669781572e-06,
+      "loss": 0.0939,
+      "step": 6
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 0.17410072415985545,
+      "learning_rate": 5e-06,
+      "loss": 0.0941,
+      "step": 7
+    },
+    {
+      "epoch": 1.103448275862069,
+      "grad_norm": 0.2902949965960051,
+      "learning_rate": 3.887395330218429e-06,
+      "loss": 0.1563,
+      "step": 8
+    },
+    {
+      "epoch": 1.2413793103448276,
+      "grad_norm": 0.1157793373052799,
+      "learning_rate": 2.83058130441221e-06,
+      "loss": 0.0807,
+      "step": 9
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 0.1269089918618396,
+      "learning_rate": 1.8825509907063328e-06,
+      "loss": 0.0818,
+      "step": 10
+    },
+    {
+      "epoch": 1.5172413793103448,
+      "grad_norm": 0.13718545049887143,
+      "learning_rate": 1.0908425876598512e-06,
+      "loss": 0.0826,
+      "step": 11
+    },
+    {
+      "epoch": 1.6551724137931034,
+      "grad_norm": 0.13360227237878022,
+      "learning_rate": 4.951556604879049e-07,
+      "loss": 0.0805,
+      "step": 12
+    },
+    {
+      "epoch": 1.793103448275862,
+      "grad_norm": 0.1373240247538753,
+      "learning_rate": 1.253604390908819e-07,
+      "loss": 0.0843,
+      "step": 13
+    },
+    {
+      "epoch": 1.9310344827586206,
+      "grad_norm": 0.13563216403584644,
+      "learning_rate": 0.0,
+      "loss": 0.0789,
+      "step": 14
+    },
+    {
+      "epoch": 1.9310344827586206,
+      "step": 14,
+      "total_flos": 3917060505600.0,
+      "train_loss": 0.09816603043249675,
+      "train_runtime": 131.6086,
+      "train_samples_per_second": 8.753,
+      "train_steps_per_second": 0.106
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 14,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 5000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3917060505600.0,
+  "train_batch_size": 5,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a820aa4329ccd2cbbeccacafa2f0e93189fa8797986510dc4ca17c3d9a5422ef
+size 7224