Upload folder using huggingface_hub

.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

README.md

@@ -0,0 +1,63 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: Qwen2.5-1.5B-Instruct-all-new
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Qwen2.5-1.5B-Instruct-all-new
+
+This model is a fine-tuned version of [/ssd1/models/Qwen2.5-1.5B-Instruct/](https://huggingface.co//ssd1/models/Qwen2.5-1.5B-Instruct/) on the papertrain dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5940
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- total_eval_batch_size: 4
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.48.3
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.21.0

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": 1.9777777777777779,
+    "eval_loss": 0.5940256714820862,
+    "eval_runtime": 18.0133,
+    "eval_samples_per_second": 5.551,
+    "eval_steps_per_second": 1.388,
+    "total_flos": 15337468788736.0,
+    "train_loss": 0.5112001879939011,
+    "train_runtime": 1525.5061,
+    "train_samples_per_second": 1.18,
+    "train_steps_per_second": 0.073
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/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": "bfloat16",
+  "transformers_version": "4.48.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.9777777777777779,
+    "eval_loss": 0.5940256714820862,
+    "eval_runtime": 18.0133,
+    "eval_samples_per_second": 5.551,
+    "eval_steps_per_second": 1.388
+}

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": "4.48.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbb8d386714b1a34d2ca9cfbbd5f55ad56d34d7e924be4d6df07f2ccc05ade48
+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 +1,209 @@
+{
+  "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",
+  "extra_special_tokens": {},
+  "model_max_length": 16384,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.9777777777777779,
+    "total_flos": 15337468788736.0,
+    "train_loss": 0.5112001879939011,
+    "train_runtime": 1525.5061,
+    "train_samples_per_second": 1.18,
+    "train_steps_per_second": 0.073
+}

trainer_log.jsonl

@@ -0,0 +1,12 @@
+{"current_steps": 10, "total_steps": 112, "loss": 0.7523, "lr": 8.333333333333334e-06, "epoch": 0.17777777777777778, "percentage": 8.93, "elapsed_time": "0:03:02", "remaining_time": "0:31:06"}
+{"current_steps": 20, "total_steps": 112, "loss": 0.7075, "lr": 9.842915805643156e-06, "epoch": 0.35555555555555557, "percentage": 17.86, "elapsed_time": "0:06:05", "remaining_time": "0:28:02"}
+{"current_steps": 30, "total_steps": 112, "loss": 0.6473, "lr": 9.221639627510076e-06, "epoch": 0.5333333333333333, "percentage": 26.79, "elapsed_time": "0:08:04", "remaining_time": "0:22:03"}
+{"current_steps": 40, "total_steps": 112, "loss": 0.6078, "lr": 8.18711994874345e-06, "epoch": 0.7111111111111111, "percentage": 35.71, "elapsed_time": "0:10:08", "remaining_time": "0:18:14"}
+{"current_steps": 50, "total_steps": 112, "loss": 0.5699, "lr": 6.840622763423391e-06, "epoch": 0.8888888888888888, "percentage": 44.64, "elapsed_time": "0:12:14", "remaining_time": "0:15:10"}
+{"current_steps": 60, "total_steps": 112, "loss": 0.5587, "lr": 5.3139525976465675e-06, "epoch": 1.0533333333333332, "percentage": 53.57, "elapsed_time": "0:14:13", "remaining_time": "0:12:19"}
+{"current_steps": 70, "total_steps": 112, "loss": 0.382, "lr": 3.756550564175727e-06, "epoch": 1.231111111111111, "percentage": 62.5, "elapsed_time": "0:16:14", "remaining_time": "0:09:44"}
+{"current_steps": 80, "total_steps": 112, "loss": 0.3424, "lr": 2.320866025105016e-06, "epoch": 1.4088888888888889, "percentage": 71.43, "elapsed_time": "0:18:20", "remaining_time": "0:07:20"}
+{"current_steps": 90, "total_steps": 112, "loss": 0.3815, "lr": 1.1474337861210543e-06, "epoch": 1.5866666666666667, "percentage": 80.36, "elapsed_time": "0:20:31", "remaining_time": "0:05:01"}
+{"current_steps": 100, "total_steps": 112, "loss": 0.3416, "lr": 3.511175705587433e-07, "epoch": 1.7644444444444445, "percentage": 89.29, "elapsed_time": "0:22:33", "remaining_time": "0:02:42"}
+{"current_steps": 110, "total_steps": 112, "loss": 0.3558, "lr": 9.866357858642206e-09, "epoch": 1.942222222222222, "percentage": 98.21, "elapsed_time": "0:24:47", "remaining_time": "0:00:27"}
+{"current_steps": 112, "total_steps": 112, "epoch": 1.9777777777777779, "percentage": 100.0, "elapsed_time": "0:25:24", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,119 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9777777777777779,
+  "eval_steps": 500,
+  "global_step": 112,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 1.1333891966940177,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.7523,
+      "step": 10
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.958010004815403,
+      "learning_rate": 9.842915805643156e-06,
+      "loss": 0.7075,
+      "step": 20
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.7853045645588168,
+      "learning_rate": 9.221639627510076e-06,
+      "loss": 0.6473,
+      "step": 30
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.8825698012004065,
+      "learning_rate": 8.18711994874345e-06,
+      "loss": 0.6078,
+      "step": 40
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.7151740400775302,
+      "learning_rate": 6.840622763423391e-06,
+      "loss": 0.5699,
+      "step": 50
+    },
+    {
+      "epoch": 1.0533333333333332,
+      "grad_norm": 0.7570773917821664,
+      "learning_rate": 5.3139525976465675e-06,
+      "loss": 0.5587,
+      "step": 60
+    },
+    {
+      "epoch": 1.231111111111111,
+      "grad_norm": 0.8230371816683825,
+      "learning_rate": 3.756550564175727e-06,
+      "loss": 0.382,
+      "step": 70
+    },
+    {
+      "epoch": 1.4088888888888889,
+      "grad_norm": 0.6621112845262395,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 0.3424,
+      "step": 80
+    },
+    {
+      "epoch": 1.5866666666666667,
+      "grad_norm": 0.8311851524519195,
+      "learning_rate": 1.1474337861210543e-06,
+      "loss": 0.3815,
+      "step": 90
+    },
+    {
+      "epoch": 1.7644444444444445,
+      "grad_norm": 0.7404603826818766,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 0.3416,
+      "step": 100
+    },
+    {
+      "epoch": 1.942222222222222,
+      "grad_norm": 0.7121753922595842,
+      "learning_rate": 9.866357858642206e-09,
+      "loss": 0.3558,
+      "step": 110
+    },
+    {
+      "epoch": 1.9777777777777779,
+      "step": 112,
+      "total_flos": 15337468788736.0,
+      "train_loss": 0.5112001879939011,
+      "train_runtime": 1525.5061,
+      "train_samples_per_second": 1.18,
+      "train_steps_per_second": 0.073
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 112,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 15337468788736.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19ef446bce6ab5e2b1eac411b9c2c41cbf4ec56efe4dca405b4004a412b7ebfd
+size 7416