End of training

README.md

@@ -0,0 +1,112 @@
+---
+license: mit
+library_name: peft
+tags:
+- trl
+- reward-trainer
+- generated_from_trainer
+base_model: openai-community/gpt2-large
+metrics:
+- accuracy
+model-index:
+- name: RM-HH-AllMix_helpful_gpt3_loraR64_20000_gpt2-large_shuffleTrue_extractchosenFalse
+  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. -->
+
+# RM-HH-AllMix_helpful_gpt3_loraR64_20000_gpt2-large_shuffleTrue_extractchosenFalse
+
+This model is a fine-tuned version of [openai-community/gpt2-large](https://huggingface.co/openai-community/gpt2-large) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4894
+- Accuracy: 0.7351
+
+## 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: 1.41e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2.0
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.6628        | 0.04  | 250   | 0.6390          | 0.6277   |
+| 0.598         | 0.08  | 500   | 0.5673          | 0.6933   |
+| 0.5479        | 0.13  | 750   | 0.5415          | 0.7076   |
+| 0.5397        | 0.17  | 1000  | 0.5308          | 0.7110   |
+| 0.5094        | 0.21  | 1250  | 0.5261          | 0.7159   |
+| 0.5142        | 0.25  | 1500  | 0.5203          | 0.7193   |
+| 0.5414        | 0.29  | 1750  | 0.5161          | 0.7197   |
+| 0.5189        | 0.33  | 2000  | 0.5131          | 0.7189   |
+| 0.5151        | 0.38  | 2250  | 0.5100          | 0.7216   |
+| 0.4942        | 0.42  | 2500  | 0.5089          | 0.7208   |
+| 0.5067        | 0.46  | 2750  | 0.5057          | 0.7216   |
+| 0.5026        | 0.5   | 3000  | 0.5041          | 0.7238   |
+| 0.4926        | 0.54  | 3250  | 0.5038          | 0.7265   |
+| 0.4931        | 0.59  | 3500  | 0.5022          | 0.7310   |
+| 0.4946        | 0.63  | 3750  | 0.4993          | 0.7329   |
+| 0.5058        | 0.67  | 4000  | 0.4968          | 0.7313   |
+| 0.4822        | 0.71  | 4250  | 0.4963          | 0.7306   |
+| 0.4924        | 0.75  | 4500  | 0.4961          | 0.7329   |
+| 0.4654        | 0.8   | 4750  | 0.4959          | 0.7302   |
+| 0.4924        | 0.84  | 5000  | 0.4971          | 0.7310   |
+| 0.4674        | 0.88  | 5250  | 0.4948          | 0.7310   |
+| 0.4704        | 0.92  | 5500  | 0.4950          | 0.7336   |
+| 0.5089        | 0.96  | 5750  | 0.4905          | 0.7306   |
+| 0.4673        | 1.0   | 6000  | 0.4929          | 0.7313   |
+| 0.4594        | 1.05  | 6250  | 0.4932          | 0.7291   |
+| 0.479         | 1.09  | 6500  | 0.4919          | 0.7332   |
+| 0.5112        | 1.13  | 6750  | 0.4895          | 0.7355   |
+| 0.4794        | 1.17  | 7000  | 0.4888          | 0.7332   |
+| 0.5188        | 1.21  | 7250  | 0.4881          | 0.7340   |
+| 0.4541        | 1.26  | 7500  | 0.4892          | 0.7359   |
+| 0.4617        | 1.3   | 7750  | 0.4898          | 0.7366   |
+| 0.4747        | 1.34  | 8000  | 0.4898          | 0.7362   |
+| 0.4834        | 1.38  | 8250  | 0.4893          | 0.7389   |
+| 0.4954        | 1.42  | 8500  | 0.4875          | 0.7385   |
+| 0.5029        | 1.47  | 8750  | 0.4875          | 0.7385   |
+| 0.4742        | 1.51  | 9000  | 0.4872          | 0.7400   |
+| 0.4802        | 1.55  | 9250  | 0.4884          | 0.7393   |
+| 0.5009        | 1.59  | 9500  | 0.4877          | 0.7400   |
+| 0.4619        | 1.63  | 9750  | 0.4875          | 0.7396   |
+| 0.4433        | 1.67  | 10000 | 0.4902          | 0.7404   |
+| 0.4844        | 1.72  | 10250 | 0.4903          | 0.7400   |
+| 0.4337        | 1.76  | 10500 | 0.4917          | 0.7400   |
+| 0.4897        | 1.8   | 10750 | 0.4901          | 0.7396   |
+| 0.4783        | 1.84  | 11000 | 0.4894          | 0.7366   |
+| 0.4929        | 1.88  | 11250 | 0.4892          | 0.7359   |
+| 0.4776        | 1.93  | 11500 | 0.4891          | 0.7362   |
+| 0.4574        | 1.97  | 11750 | 0.4894          | 0.7351   |
+
+
+### Framework versions
+
+- PEFT 0.9.0
+- Transformers 4.38.2
+- Pytorch 2.1.2
+- Datasets 2.18.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openai-community/gpt2-large",
+  "bias": "none",
+  "fan_in_fan_out": true,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_attn"
+  ],
+  "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:dde31911cd0f4e6d29c048624639a3d87c182a3c174b2504b1278d3e9003a3a8
+size 47195336

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a0e97a7d0ebb8b86787e77c64af1fb4e98545e04e4ff4e08a7e1963dd61ce5b
+size 4984