Upload 13 files

README.md

@@ -0,0 +1,59 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: Qwen/Qwen1.5-14B-Chat
+model-index:
+- name: train_2024-04-05-06-48-04
+  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. -->
+
+# train_2024-04-05-06-48-04
+
+This model is a fine-tuned version of [Qwen/Qwen1.5-14B-Chat](https://huggingface.co/Qwen/Qwen1.5-14B-Chat) on the sent_classify dataset.
+
+## 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: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 5.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.39.3
+- Pytorch 2.2.2+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-14B-Chat",
+  "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": 128,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "v_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 sha256:24e53ffecb977410cf19658de5c134a4e733cea3d5155c5966b58e0c5a2e5369
+size 997533656

added_tokens.json

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

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 4.92,
+    "train_loss": 0.020610336679965258,
+    "train_runtime": 1360.5648,
+    "train_samples_per_second": 0.474,
+    "train_steps_per_second": 0.029
+}

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": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 4.92,
+    "train_loss": 0.020610336679965258,
+    "train_runtime": 1360.5648,
+    "train_samples_per_second": 0.474,
+    "train_steps_per_second": 0.029
+}

trainer_log.jsonl

@@ -0,0 +1,9 @@
+{"current_steps": 5, "total_steps": 40, "loss": 0.0652, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.0001923879532511287, "epoch": 0.62, "percentage": 12.5, "elapsed_time": "0:02:49", "remaining_time": "0:19:46"}
+{"current_steps": 10, "total_steps": 40, "loss": 0.0346, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.00017071067811865476, "epoch": 1.23, "percentage": 25.0, "elapsed_time": "0:05:39", "remaining_time": "0:16:59"}
+{"current_steps": 15, "total_steps": 40, "loss": 0.0214, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.000138268343236509, "epoch": 1.85, "percentage": 37.5, "elapsed_time": "0:08:33", "remaining_time": "0:14:15"}
+{"current_steps": 20, "total_steps": 40, "loss": 0.0145, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.0001, "epoch": 2.46, "percentage": 50.0, "elapsed_time": "0:11:20", "remaining_time": "0:11:20"}
+{"current_steps": 25, "total_steps": 40, "loss": 0.0117, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 6.173165676349103e-05, "epoch": 3.08, "percentage": 62.5, "elapsed_time": "0:14:10", "remaining_time": "0:08:30"}
+{"current_steps": 30, "total_steps": 40, "loss": 0.007, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.9289321881345254e-05, "epoch": 3.69, "percentage": 75.0, "elapsed_time": "0:17:00", "remaining_time": "0:05:40"}
+{"current_steps": 35, "total_steps": 40, "loss": 0.0056, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 7.612046748871327e-06, "epoch": 4.31, "percentage": 87.5, "elapsed_time": "0:19:49", "remaining_time": "0:02:49"}
+{"current_steps": 40, "total_steps": 40, "loss": 0.0049, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.0, "epoch": 4.92, "percentage": 100.0, "elapsed_time": "0:22:40", "remaining_time": "0:00:00"}
+{"current_steps": 40, "total_steps": 40, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 4.92, "percentage": 100.0, "elapsed_time": "0:22:40", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.923076923076923,
+  "eval_steps": 500,
+  "global_step": 40,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.1295962631702423,
+      "learning_rate": 0.0001923879532511287,
+      "loss": 0.0652,
+      "step": 5
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 0.046223945915699005,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.0346,
+      "step": 10
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.07042355835437775,
+      "learning_rate": 0.000138268343236509,
+      "loss": 0.0214,
+      "step": 15
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 0.036413274705410004,
+      "learning_rate": 0.0001,
+      "loss": 0.0145,
+      "step": 20
+    },
+    {
+      "epoch": 3.08,
+      "grad_norm": 0.0433778315782547,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.0117,
+      "step": 25
+    },
+    {
+      "epoch": 3.69,
+      "grad_norm": 0.02845873311161995,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.007,
+      "step": 30
+    },
+    {
+      "epoch": 4.31,
+      "grad_norm": 0.02572229690849781,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0056,
+      "step": 35
+    },
+    {
+      "epoch": 4.92,
+      "grad_norm": 0.022463396191596985,
+      "learning_rate": 0.0,
+      "loss": 0.0049,
+      "step": 40
+    },
+    {
+      "epoch": 4.92,
+      "step": 40,
+      "total_flos": 6.324624974954496e+16,
+      "train_loss": 0.020610336679965258,
+      "train_runtime": 1360.5648,
+      "train_samples_per_second": 0.474,
+      "train_steps_per_second": 0.029
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 40,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 100,
+  "total_flos": 6.324624974954496e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df41029ab8ee1cce7233e15585e3c01b7641707e7c1f21fc3f93accdf26f8c2f
+size 5112