Upload folder using huggingface_hub

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,58 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: NeuralNovel/Tiger-7B-v0.1
+model-index:
+- name: train_2024-02-16-12-09-1733333
+  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_2024-02-16-12-09-1733333
+
+This model is a fine-tuned version of [NeuralNovel/Tiger-7B-v0.1](https://huggingface.co/NeuralNovel/Tiger-7B-v0.1) on the Neural-DPO 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: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.37.2
+- Pytorch 2.2.0+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.2

README.md

@@ -1,3 +1,58 @@
 ---
-license: apache-2.0
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: NeuralNovel/Tiger-7B-v0.1
+model-index:
+- name: train_2024-02-16-12-09-1733333
+  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_2024-02-16-12-09-1733333
+
+This model is a fine-tuned version of [NeuralNovel/Tiger-7B-v0.1](https://huggingface.co/NeuralNovel/Tiger-7B-v0.1) on the Neural-DPO 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: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.37.2
+- Pytorch 2.2.0+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NeuralNovel/Tiger-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e28ea1da01f3f0c5fec45a02bb570eef56f51975f874b2cd52ac195a9a004cee
+size 13648432

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.99,
+    "train_loss": 1.7228616259314797,
+    "train_runtime": 47.9316,
+    "train_samples_per_second": 22.157,
+    "train_steps_per_second": 1.377
+}

runs/Feb16_12-46-09_n4mofsestq/events.out.tfevents.1708087575.n4mofsestq.853.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e98e0feebfbc84505ba1d0a95bb9c4c1d2df921e1925e45494b822bd445758d
+size 6899

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.99,
+    "train_loss": 1.7228616259314797,
+    "train_runtime": 47.9316,
+    "train_samples_per_second": 22.157,
+    "train_steps_per_second": 1.377
+}

trainer_log.jsonl

@@ -0,0 +1,14 @@
+{"current_steps": 5, "total_steps": 66, "loss": 3.4468, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.929528920808854e-05, "epoch": 0.08, "percentage": 7.58, "elapsed_time": "0:00:03", "remaining_time": "0:00:45"}
+{"current_steps": 10, "total_steps": 66, "loss": 3.5567, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.722088621637309e-05, "epoch": 0.15, "percentage": 15.15, "elapsed_time": "0:00:07", "remaining_time": "0:00:40"}
+{"current_steps": 15, "total_steps": 66, "loss": 2.5191, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.389373935885646e-05, "epoch": 0.23, "percentage": 22.73, "elapsed_time": "0:00:10", "remaining_time": "0:00:36"}
+{"current_steps": 20, "total_steps": 66, "loss": 2.0085, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.9501422739279956e-05, "epoch": 0.3, "percentage": 30.3, "elapsed_time": "0:00:14", "remaining_time": "0:00:33"}
+{"current_steps": 25, "total_steps": 66, "loss": 1.475, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.4291561391508185e-05, "epoch": 0.38, "percentage": 37.88, "elapsed_time": "0:00:18", "remaining_time": "0:00:29"}
+{"current_steps": 30, "total_steps": 66, "loss": 1.462, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8557870956832132e-05, "epoch": 0.45, "percentage": 45.45, "elapsed_time": "0:00:21", "remaining_time": "0:00:25"}
+{"current_steps": 35, "total_steps": 66, "loss": 1.1812, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2623598917395438e-05, "epoch": 0.53, "percentage": 53.03, "elapsed_time": "0:00:25", "remaining_time": "0:00:22"}
+{"current_steps": 40, "total_steps": 66, "loss": 1.2592, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.682330091706446e-05, "epoch": 0.6, "percentage": 60.61, "elapsed_time": "0:00:29", "remaining_time": "0:00:18"}
+{"current_steps": 45, "total_steps": 66, "loss": 1.0798, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.148397956361007e-05, "epoch": 0.68, "percentage": 68.18, "elapsed_time": "0:00:32", "remaining_time": "0:00:15"}
+{"current_steps": 50, "total_steps": 66, "loss": 1.0623, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.906649047373246e-06, "epoch": 0.75, "percentage": 75.76, "elapsed_time": "0:00:36", "remaining_time": "0:00:11"}
+{"current_steps": 55, "total_steps": 66, "loss": 1.346, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.3493649053890326e-06, "epoch": 0.83, "percentage": 83.33, "elapsed_time": "0:00:40", "remaining_time": "0:00:08"}
+{"current_steps": 60, "total_steps": 66, "loss": 1.1372, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0126756596375686e-06, "epoch": 0.9, "percentage": 90.91, "elapsed_time": "0:00:43", "remaining_time": "0:00:04"}
+{"current_steps": 65, "total_steps": 66, "loss": 1.047, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.831652042480093e-08, "epoch": 0.98, "percentage": 98.48, "elapsed_time": "0:00:47", "remaining_time": "0:00:00"}
+{"current_steps": 66, "total_steps": 66, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.99, "percentage": 100.0, "elapsed_time": "0:00:47", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,108 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9924812030075187,
+  "eval_steps": 500,
+  "global_step": 66,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.929528920808854e-05,
+      "loss": 3.4468,
+      "step": 5
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.722088621637309e-05,
+      "loss": 3.5567,
+      "step": 10
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.389373935885646e-05,
+      "loss": 2.5191,
+      "step": 15
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 3.9501422739279956e-05,
+      "loss": 2.0085,
+      "step": 20
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.4291561391508185e-05,
+      "loss": 1.475,
+      "step": 25
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.8557870956832132e-05,
+      "loss": 1.462,
+      "step": 30
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.2623598917395438e-05,
+      "loss": 1.1812,
+      "step": 35
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.682330091706446e-05,
+      "loss": 1.2592,
+      "step": 40
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.148397956361007e-05,
+      "loss": 1.0798,
+      "step": 45
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 6.906649047373246e-06,
+      "loss": 1.0623,
+      "step": 50
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.3493649053890326e-06,
+      "loss": 1.346,
+      "step": 55
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.0126756596375686e-06,
+      "loss": 1.1372,
+      "step": 60
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.831652042480093e-08,
+      "loss": 1.047,
+      "step": 65
+    },
+    {
+      "epoch": 0.99,
+      "step": 66,
+      "total_flos": 4369517458489344.0,
+      "train_loss": 1.7228616259314797,
+      "train_runtime": 47.9316,
+      "train_samples_per_second": 22.157,
+      "train_steps_per_second": 1.377
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 66,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 4369517458489344.0,
+  "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 sha256:874fb7ae39df62fbc8ecdc39b54b121c82d85b49c3cf016092d23181d011c85a
+size 4920