Upload 14 files

.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 +1,8 @@
+{
+    "epoch": 2.9952,
+    "total_flos": 64311364943872.0,
+    "train_loss": 0.2557532644679404,
+    "train_runtime": 6755.8147,
+    "train_samples_per_second": 8.881,
+    "train_steps_per_second": 0.069
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/d1/zhaojihao/models/Qwen2.5-1.5B-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": 32768,
+  "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": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.3"
+}

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 +1,207 @@
+{
+  "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        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\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\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|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|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train.log

@@ -0,0 +1,286 @@
+2024-12-26 19:18:51.609 | INFO     | __main__:setup_everything:71 - train_args:TrainingArguments(
+_n_gpu=1,
+accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None, 'use_configured_state': False},
+adafactor=False,
+adam_beta1=0.9,
+adam_beta2=0.999,
+adam_epsilon=1e-08,
+auto_find_batch_size=False,
+average_tokens_across_devices=False,
+batch_eval_metrics=False,
+bf16=False,
+bf16_full_eval=False,
+data_seed=None,
+dataloader_drop_last=False,
+dataloader_num_workers=0,
+dataloader_persistent_workers=False,
+dataloader_pin_memory=True,
+dataloader_prefetch_factor=None,
+ddp_backend=None,
+ddp_broadcast_buffers=None,
+ddp_bucket_cap_mb=None,
+ddp_find_unused_parameters=None,
+ddp_timeout=1800,
+debug=[],
+deepspeed=./train_args/ds_z3_config.json,
+disable_tqdm=False,
+dispatch_batches=None,
+do_eval=False,
+do_predict=False,
+do_train=False,
+eval_accumulation_steps=None,
+eval_delay=0,
+eval_do_concat_batches=True,
+eval_on_start=False,
+eval_steps=None,
+eval_strategy=no,
+eval_use_gather_object=False,
+evaluation_strategy=None,
+fp16=True,
+fp16_backend=auto,
+fp16_full_eval=False,
+fp16_opt_level=O1,
+fsdp=[],
+fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False},
+fsdp_min_num_params=0,
+fsdp_transformer_layer_cls_to_wrap=None,
+full_determinism=False,
+gradient_accumulation_steps=16,
+gradient_checkpointing=False,
+gradient_checkpointing_kwargs=None,
+greater_is_better=None,
+group_by_length=False,
+half_precision_backend=auto,
+hub_always_push=False,
+hub_model_id=None,
+hub_private_repo=False,
+hub_strategy=every_save,
+hub_token=<HUB_TOKEN>,
+ignore_data_skip=False,
+include_for_metrics=[],
+include_inputs_for_metrics=False,
+include_num_input_tokens_seen=False,
+include_tokens_per_second=False,
+jit_mode_eval=False,
+label_names=None,
+label_smoothing_factor=0.0,
+learning_rate=1e-05,
+length_column_name=length,
+load_best_model_at_end=False,
+local_rank=0,
+log_level=passive,
+log_level_replica=warning,
+log_on_each_node=True,
+logging_dir=output/firefly-qwen25-15b-sft-full-all-M-3/runs/Dec26_19-18-51_h800-2,
+logging_first_step=False,
+logging_nan_inf_filter=True,
+logging_steps=200,
+logging_strategy=steps,
+lr_scheduler_kwargs={},
+lr_scheduler_type=cosine,
+max_grad_norm=1.0,
+max_steps=-1,
+metric_for_best_model=None,
+mp_parameters=,
+neftune_noise_alpha=None,
+no_cuda=False,
+num_train_epochs=3,
+optim=adamw_hf,
+optim_args=None,
+optim_target_modules=None,
+output_dir=output/firefly-qwen25-15b-sft-full-all-M-3,
+overwrite_output_dir=False,
+past_index=-1,
+per_device_eval_batch_size=8,
+per_device_train_batch_size=4,
+prediction_loss_only=False,
+push_to_hub=False,
+push_to_hub_model_id=None,
+push_to_hub_organization=None,
+push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
+ray_scope=last,
+remove_unused_columns=False,
+report_to=['tensorboard'],
+restore_callback_states_from_checkpoint=False,
+resume_from_checkpoint=None,
+run_name=output/firefly-qwen25-15b-sft-full-all-M-3,
+save_on_each_node=False,
+save_only_model=False,
+save_safetensors=True,
+save_steps=200,
+save_strategy=steps,
+save_total_limit=1,
+seed=42,
+skip_memory_metrics=True,
+split_batches=None,
+tf32=None,
+torch_compile=False,
+torch_compile_backend=None,
+torch_compile_mode=None,
+torch_empty_cache_steps=None,
+torchdynamo=None,
+tpu_metrics_debug=False,
+tpu_num_cores=None,
+use_cpu=False,
+use_ipex=False,
+use_legacy_prediction_loop=False,
+use_liger_kernel=False,
+use_mps_device=False,
+warmup_ratio=0.0,
+warmup_steps=50,
+weight_decay=0,
+)
+2024-12-26 19:18:51.612 | INFO     | __main__:init_components:383 - Initializing components...
+2024-12-26 19:18:51.784 | INFO     | __main__:setup_everything:71 - train_args:TrainingArguments(
+_n_gpu=1,
+accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None, 'use_configured_state': False},
+adafactor=False,
+adam_beta1=0.9,
+adam_beta2=0.999,
+adam_epsilon=1e-08,
+auto_find_batch_size=False,
+average_tokens_across_devices=False,
+batch_eval_metrics=False,
+bf16=False,
+bf16_full_eval=False,
+data_seed=None,
+dataloader_drop_last=False,
+dataloader_num_workers=0,
+dataloader_persistent_workers=False,
+dataloader_pin_memory=True,
+dataloader_prefetch_factor=None,
+ddp_backend=None,
+ddp_broadcast_buffers=None,
+ddp_bucket_cap_mb=None,
+ddp_find_unused_parameters=None,
+ddp_timeout=1800,
+debug=[],
+deepspeed=./train_args/ds_z3_config.json,
+disable_tqdm=False,
+dispatch_batches=None,
+do_eval=False,
+do_predict=False,
+do_train=False,
+eval_accumulation_steps=None,
+eval_delay=0,
+eval_do_concat_batches=True,
+eval_on_start=False,
+eval_steps=None,
+eval_strategy=no,
+eval_use_gather_object=False,
+evaluation_strategy=None,
+fp16=True,
+fp16_backend=auto,
+fp16_full_eval=False,
+fp16_opt_level=O1,
+fsdp=[],
+fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False},
+fsdp_min_num_params=0,
+fsdp_transformer_layer_cls_to_wrap=None,
+full_determinism=False,
+gradient_accumulation_steps=16,
+gradient_checkpointing=False,
+gradient_checkpointing_kwargs=None,
+greater_is_better=None,
+group_by_length=False,
+half_precision_backend=auto,
+hub_always_push=False,
+hub_model_id=None,
+hub_private_repo=False,
+hub_strategy=every_save,
+hub_token=<HUB_TOKEN>,
+ignore_data_skip=False,
+include_for_metrics=[],
+include_inputs_for_metrics=False,
+include_num_input_tokens_seen=False,
+include_tokens_per_second=False,
+jit_mode_eval=False,
+label_names=None,
+label_smoothing_factor=0.0,
+learning_rate=1e-05,
+length_column_name=length,
+load_best_model_at_end=False,
+local_rank=1,
+log_level=passive,
+log_level_replica=warning,
+log_on_each_node=True,
+logging_dir=output/firefly-qwen25-15b-sft-full-all-M-3/runs/Dec26_19-18-51_h800-2,
+logging_first_step=False,
+logging_nan_inf_filter=True,
+logging_steps=200,
+logging_strategy=steps,
+lr_scheduler_kwargs={},
+lr_scheduler_type=cosine,
+max_grad_norm=1.0,
+max_steps=-1,
+metric_for_best_model=None,
+mp_parameters=,
+neftune_noise_alpha=None,
+no_cuda=False,
+num_train_epochs=3,
+optim=adamw_hf,
+optim_args=None,
+optim_target_modules=None,
+output_dir=output/firefly-qwen25-15b-sft-full-all-M-3,
+overwrite_output_dir=False,
+past_index=-1,
+per_device_eval_batch_size=8,
+per_device_train_batch_size=4,
+prediction_loss_only=False,
+push_to_hub=False,
+push_to_hub_model_id=None,
+push_to_hub_organization=None,
+push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
+ray_scope=last,
+remove_unused_columns=False,
+report_to=['tensorboard'],
+restore_callback_states_from_checkpoint=False,
+resume_from_checkpoint=None,
+run_name=output/firefly-qwen25-15b-sft-full-all-M-3,
+save_on_each_node=False,
+save_only_model=False,
+save_safetensors=True,
+save_steps=200,
+save_strategy=steps,
+save_total_limit=1,
+seed=42,
+skip_memory_metrics=True,
+split_batches=None,
+tf32=None,
+torch_compile=False,
+torch_compile_backend=None,
+torch_compile_mode=None,
+torch_empty_cache_steps=None,
+torchdynamo=None,
+tpu_metrics_debug=False,
+tpu_num_cores=None,
+use_cpu=False,
+use_ipex=False,
+use_legacy_prediction_loop=False,
+use_liger_kernel=False,
+use_mps_device=False,
+warmup_ratio=0.0,
+warmup_steps=50,
+weight_decay=0,
+)
+2024-12-26 19:18:51.787 | INFO     | __main__:init_components:383 - Initializing components...
+2024-12-26 19:18:51.917 | INFO     | __main__:load_tokenizer:231 - vocab_size of tokenizer: 151643
+2024-12-26 19:18:51.917 | INFO     | __main__:load_model:270 - Loading model from base model: /d1/zhaojihao/models/Qwen2.5-1.5B-Instruct
+2024-12-26 19:18:51.917 | INFO     | __main__:load_model:271 - Train model with full
+2024-12-26 19:18:52.125 | INFO     | __main__:load_tokenizer:231 - vocab_size of tokenizer: 151643
+2024-12-26 19:18:52.126 | INFO     | __main__:load_model:270 - Loading model from base model: /d1/zhaojihao/models/Qwen2.5-1.5B-Instruct
+2024-12-26 19:18:52.126 | INFO     | __main__:load_model:271 - Train model with full
+2024-12-26 19:18:56.469 | INFO     | __main__:load_model:345 - Total model params: 0.00M
+2024-12-26 19:18:56.470 | INFO     | __main__:init_components:402 - Train model with sft task
+2024-12-26 19:18:56.470 | INFO     | __main__:load_sft_dataset:365 - Loading data with UnifiedSFTDataset
+2024-12-26 19:18:56.470 | INFO     | component.dataset:__init__:19 - Loading data: /d1/zhaojihao/chunk2/train_GPT/conversations_20000_MASK.jsonl
+2024-12-26 19:18:56.557 | INFO     | __main__:load_model:345 - Total model params: 0.00M
+2024-12-26 19:18:56.557 | INFO     | __main__:init_components:402 - Train model with sft task
+2024-12-26 19:18:56.557 | INFO     | __main__:load_sft_dataset:365 - Loading data with UnifiedSFTDataset
+2024-12-26 19:18:56.557 | INFO     | component.dataset:__init__:19 - Loading data: /d1/zhaojihao/chunk2/train_GPT/conversations_20000_MASK.jsonl
+2024-12-26 19:18:56.672 | INFO     | component.dataset:__init__:22 - Use template "qwen" for training
+2024-12-26 19:18:56.673 | INFO     | component.dataset:__init__:23 - There are 20000 data in dataset
+2024-12-26 19:18:56.729 | INFO     | __main__:main:440 - *** starting training ***
+2024-12-26 19:18:56.766 | INFO     | component.dataset:__init__:22 - Use template "qwen" for training
+2024-12-26 19:18:56.766 | INFO     | component.dataset:__init__:23 - There are 20000 data in dataset
+2024-12-26 19:18:56.819 | INFO     | __main__:main:440 - *** starting training ***

train_args.json

@@ -0,0 +1,29 @@
+{
+    "output_dir": "output",
+    "model_name_or_path": "models/Qwen2.5-1.5B-Instruct",
+    "deepspeed": "./train_args/ds_z3_config.json",
+    "train_file": "train_GPT/conversations_20000_MASK.jsonl",
+    "template_name": "qwen",
+    "train_mode": "full",
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 4,
+    "gradient_accumulation_steps": 16,
+    "learning_rate": 1e-05,
+    "max_seq_length": 4096,
+    "logging_steps": 200,
+    "save_steps": 200,
+    "save_total_limit": 1,
+    "lr_scheduler_type": "cosine",
+    "warmup_steps": 50,
+    "gradient_checkpointing": false,
+    "disable_tqdm": false,
+    "optim": "adamw_hf",
+    "seed": 42,
+    "fp16": true,
+    "report_to": "tensorboard",
+    "dataloader_num_workers": 0,
+    "save_strategy": "steps",
+    "weight_decay": 0,
+    "max_grad_norm": 1.0,
+    "remove_unused_columns": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9952,
+    "total_flos": 64311364943872.0,
+    "train_loss": 0.2557532644679404,
+    "train_runtime": 6755.8147,
+    "train_samples_per_second": 8.881,
+    "train_steps_per_second": 0.069
+}

trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9952,
+  "eval_steps": 500,
+  "global_step": 468,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.09104396402835846,
+      "learning_rate": 1e-05,
+      "loss": 0.3624,
+      "step": 200
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.1047985777258873,
+      "learning_rate": 1e-05,
+      "loss": 0.1875,
+      "step": 400
+    },
+    {
+      "epoch": 2.9952,
+      "step": 468,
+      "total_flos": 64311364943872.0,
+      "train_loss": 0.2557532644679404,
+      "train_runtime": 6755.8147,
+      "train_samples_per_second": 8.881,
+      "train_steps_per_second": 0.069
+    }
+  ],
+  "logging_steps": 200,
+  "max_steps": 468,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 64311364943872.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:446b2bdb990ddab0bd058086434dc4c0d9b2abb402a58d4d4ac844966bd12878
+size 7736