Upload 16 files

README.md

@@ -1,3 +1,60 @@
----
-license: mit
----
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: Qwen2/Qwen2-7B-Instruct
+model-index:
+- name: sft_0626_after_2_dpo_9
+  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. -->
+
+# sft_0626_after_2_dpo_9
+
+This model is a fine-tuned version of [/root/LLM_Data_Engineer/LLaMA-Factory/models/Qwen2-7B-Instruct-dpo-06250115-iter2-after-dpo-0.6](https://huggingface.co//root/LLM_Data_Engineer/LLaMA-Factory/models/Qwen2-7B-Instruct-dpo-06250115-iter2-after-dpo-0.6) on the sft_data_1474_0624_9_iter2 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7347
+
+## 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: 0.0001
+- train_batch_size: 6
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 48
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.2
+- Pytorch 2.1.2
+- Datasets 2.19.2
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/root/LLM_Data_Engineer/LLaMA-Factory/models/Qwen2-7B-Instruct-dpo-06250115-iter2-after-dpo-0.6",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45571b69e1586a4387165833a371bdb8023080bdda55b77e7cd232886bec2279
+size 80792096

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.8656716417910446,
+    "eval_loss": 0.7347341775894165,
+    "eval_runtime": 0.2127,
+    "eval_samples_per_second": 23.506,
+    "eval_steps_per_second": 23.506,
+    "total_flos": 1.2058224578297856e+16,
+    "train_loss": 1.0678408990303676,
+    "train_runtime": 102.2691,
+    "train_samples_per_second": 11.675,
+    "train_steps_per_second": 0.235
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.8656716417910446,
+    "eval_loss": 0.7347341775894165,
+    "eval_runtime": 0.2127,
+    "eval_samples_per_second": 23.506,
+    "eval_steps_per_second": 23.506
+}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "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_config.json

@@ -0,0 +1,44 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "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": 2.8656716417910446,
+    "total_flos": 1.2058224578297856e+16,
+    "train_loss": 1.0678408990303676,
+    "train_runtime": 102.2691,
+    "train_samples_per_second": 11.675,
+    "train_steps_per_second": 0.235
+}

trainer_log.jsonl

@@ -0,0 +1,13 @@
+{"current_steps": 2, "total_steps": 24, "loss": 1.4111, "learning_rate": 9.829629131445342e-05, "epoch": 0.23880597014925373, "percentage": 8.33, "elapsed_time": "0:00:09", "remaining_time": "0:01:41", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 4, "total_steps": 24, "loss": 1.4368, "learning_rate": 9.330127018922194e-05, "epoch": 0.47761194029850745, "percentage": 16.67, "elapsed_time": "0:00:18", "remaining_time": "0:01:30", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 6, "total_steps": 24, "loss": 1.2286, "learning_rate": 8.535533905932738e-05, "epoch": 0.7164179104477612, "percentage": 25.0, "elapsed_time": "0:00:27", "remaining_time": "0:01:22", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 8, "total_steps": 24, "loss": 1.1773, "learning_rate": 7.500000000000001e-05, "epoch": 0.9552238805970149, "percentage": 33.33, "elapsed_time": "0:00:34", "remaining_time": "0:01:09", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 10, "total_steps": 24, "loss": 0.9521, "learning_rate": 6.294095225512603e-05, "epoch": 1.1940298507462686, "percentage": 41.67, "elapsed_time": "0:00:42", "remaining_time": "0:00:59", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 12, "total_steps": 24, "loss": 0.9986, "learning_rate": 5e-05, "epoch": 1.4328358208955223, "percentage": 50.0, "elapsed_time": "0:00:50", "remaining_time": "0:00:50", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 14, "total_steps": 24, "loss": 0.9659, "learning_rate": 3.705904774487396e-05, "epoch": 1.671641791044776, "percentage": 58.33, "elapsed_time": "0:00:59", "remaining_time": "0:00:42", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 16, "total_steps": 24, "loss": 0.9646, "learning_rate": 2.500000000000001e-05, "epoch": 1.9104477611940298, "percentage": 66.67, "elapsed_time": "0:01:07", "remaining_time": "0:00:33", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 18, "total_steps": 24, "loss": 0.9083, "learning_rate": 1.4644660940672627e-05, "epoch": 2.1492537313432836, "percentage": 75.0, "elapsed_time": "0:01:17", "remaining_time": "0:00:25", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 20, "total_steps": 24, "loss": 0.9453, "learning_rate": 6.698729810778065e-06, "epoch": 2.388059701492537, "percentage": 83.33, "elapsed_time": "0:01:24", "remaining_time": "0:00:16", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 22, "total_steps": 24, "loss": 0.9429, "learning_rate": 1.70370868554659e-06, "epoch": 2.626865671641791, "percentage": 91.67, "elapsed_time": "0:01:33", "remaining_time": "0:00:08", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 24, "total_steps": 24, "loss": 0.8827, "learning_rate": 0.0, "epoch": 2.8656716417910446, "percentage": 100.0, "elapsed_time": "0:01:42", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 24, "total_steps": 24, "epoch": 2.8656716417910446, "percentage": 100.0, "elapsed_time": "0:01:42", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}

trainer_state.json

@@ -0,0 +1,126 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.8656716417910446,
+  "eval_steps": 500,
+  "global_step": 24,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23880597014925373,
+      "grad_norm": 0.585221529006958,
+      "learning_rate": 9.829629131445342e-05,
+      "loss": 1.4111,
+      "step": 2
+    },
+    {
+      "epoch": 0.47761194029850745,
+      "grad_norm": 0.6329778432846069,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 1.4368,
+      "step": 4
+    },
+    {
+      "epoch": 0.7164179104477612,
+      "grad_norm": 0.6056985259056091,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.2286,
+      "step": 6
+    },
+    {
+      "epoch": 0.9552238805970149,
+      "grad_norm": 0.5265995860099792,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.1773,
+      "step": 8
+    },
+    {
+      "epoch": 1.1940298507462686,
+      "grad_norm": 0.3901197910308838,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.9521,
+      "step": 10
+    },
+    {
+      "epoch": 1.4328358208955223,
+      "grad_norm": 0.342200368642807,
+      "learning_rate": 5e-05,
+      "loss": 0.9986,
+      "step": 12
+    },
+    {
+      "epoch": 1.671641791044776,
+      "grad_norm": 0.29529017210006714,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.9659,
+      "step": 14
+    },
+    {
+      "epoch": 1.9104477611940298,
+      "grad_norm": 0.27741575241088867,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.9646,
+      "step": 16
+    },
+    {
+      "epoch": 2.1492537313432836,
+      "grad_norm": 0.308491051197052,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.9083,
+      "step": 18
+    },
+    {
+      "epoch": 2.388059701492537,
+      "grad_norm": 0.30398857593536377,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.9453,
+      "step": 20
+    },
+    {
+      "epoch": 2.626865671641791,
+      "grad_norm": 0.27445322275161743,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.9429,
+      "step": 22
+    },
+    {
+      "epoch": 2.8656716417910446,
+      "grad_norm": 0.2563874423503876,
+      "learning_rate": 0.0,
+      "loss": 0.8827,
+      "step": 24
+    },
+    {
+      "epoch": 2.8656716417910446,
+      "step": 24,
+      "total_flos": 1.2058224578297856e+16,
+      "train_loss": 1.0678408990303676,
+      "train_runtime": 102.2691,
+      "train_samples_per_second": 11.675,
+      "train_steps_per_second": 0.235
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 24,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2058224578297856e+16,
+  "train_batch_size": 6,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31e8653ac75c88fcb9b4a7d48ff70ef8402807b2237566c25a2f62867406c941
+size 5304