anhnv125/reward-model

README.md

@@ -0,0 +1,79 @@
+---
+base_model: ChaiML/reward_models_100_170000000_cp_498032
+tags:
+- generated_from_trainer
+model-index:
+- name: reward-model
+  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. -->
+
+# reward-model
+
+This model is a fine-tuned version of [ChaiML/reward_models_100_170000000_cp_498032](https://huggingface.co/ChaiML/reward_models_100_170000000_cp_498032) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6275
+
+## 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-06
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 7
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 200
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.6911        | 0.04  | 200  | 0.6674          |
+| 0.654         | 0.09  | 400  | 0.6472          |
+| 0.6654        | 0.13  | 600  | 0.6429          |
+| 0.6381        | 0.17  | 800  | 0.6391          |
+| 0.6546        | 0.21  | 1000 | 0.6381          |
+| 0.6575        | 0.26  | 1200 | 0.6352          |
+| 0.6458        | 0.3   | 1400 | 0.6344          |
+| 0.6574        | 0.34  | 1600 | 0.6335          |
+| 0.6409        | 0.39  | 1800 | 0.6314          |
+| 0.6255        | 0.43  | 2000 | 0.6306          |
+| 0.6342        | 0.47  | 2200 | 0.6300          |
+| 0.6117        | 0.51  | 2400 | 0.6298          |
+| 0.6651        | 0.56  | 2600 | 0.6307          |
+| 0.6624        | 0.6   | 2800 | 0.6294          |
+| 0.6213        | 0.64  | 3000 | 0.6286          |
+| 0.6486        | 0.68  | 3200 | 0.6278          |
+| 0.6258        | 0.73  | 3400 | 0.6277          |
+| 0.6336        | 0.77  | 3600 | 0.6278          |
+| 0.5842        | 0.81  | 3800 | 0.6277          |
+| 0.6748        | 0.86  | 4000 | 0.6275          |
+| 0.5985        | 0.9   | 4200 | 0.6275          |
+| 0.6207        | 0.94  | 4400 | 0.6275          |
+| 0.5901        | 0.98  | 4600 | 0.6275          |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.0.1+cu117
+- Datasets 2.14.6
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "ChaiML/reward_models_100_170000000_cp_498032",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2ForSequenceClassification"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 50256,
+  "problem_type": "single_label_classification",
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c77f3c439e79b61353c7d208bb56505daf62353607e797738738c1ca330a015
+size 497780432

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:513e7d7e373ae76c6639bb27cab878f2d1198dd9669f21b92ce1e737a81403af
+size 497813601

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": false,
+      "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 sha256:2476ce46368e55f2548101f9c52721bb520a3d61335f0cb050bcde326b7c5640
+size 4027