End of training

README.md

@@ -1,13 +1,11 @@
 ---
 library_name: transformers
-license: other
-base_model: facebook/opt-350m
+license: mit
+base_model: gpt2
 tags:
 - trl
 - reward-trainer
 - generated_from_trainer
-metrics:
-- accuracy
 model-index:
 - name: reward_modeling_anthropic_hh
   results: []
@@ -18,10 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # reward_modeling_anthropic_hh
 
-This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.6029
-- Accuracy: 0.6612
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 
 ## Model description
 
@@ -52,9 +47,6 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
-|:-------------:|:------:|:----:|:---------------:|:--------:|
-| 0.6125        | 0.8696 | 500  | 0.6029          | 0.6612   |
 
 
 ### Framework versions

config.json

@@ -1,37 +1,46 @@
 {
-  "_name_or_path": "facebook/opt-350m",
-  "_remove_final_layer_norm": false,
-  "activation_dropout": 0.0,
-  "activation_function": "relu",
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
   "architectures": [
-    "OPTForSequenceClassification"
+    "GPT2ForSequenceClassification"
   ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 2,
-  "do_layer_norm_before": false,
-  "dropout": 0.1,
-  "enable_bias": true,
-  "eos_token_id": 2,
-  "ffn_dim": 4096,
-  "hidden_size": 1024,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
   "id2label": {
     "0": "LABEL_0"
   },
-  "init_std": 0.02,
+  "initializer_range": 0.02,
   "label2id": {
     "LABEL_0": 0
   },
-  "layer_norm_elementwise_affine": true,
-  "layerdrop": 0.0,
-  "max_position_embeddings": 2048,
-  "model_type": "opt",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
-  "pad_token_id": 1,
-  "prefix": "</s>",
+  "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,
+  "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": "4.44.1",
   "use_cache": true,
-  "vocab_size": 50272,
-  "word_embed_proj_dim": 512
+  "vocab_size": 50257
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6f44fab9df899ebb803a144494025cd746cd588ea64027bcc8a1bc9d7abc9f0
-size 1324833016
+oid sha256:ae2e0ac6d11fd8f3beebe3a70dcd3ae8fa4fcd213ea68c868c11e9b5859ad95a
+size 497777360

special_tokens_map.json

@@ -1,30 +1,6 @@
 {
-  "bos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
 }

tokenizer_config.json

@@ -1,17 +1,8 @@
 {
-  "add_bos_token": true,
   "add_prefix_space": false,
   "added_tokens_decoder": {
-    "1": {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
+    "50256": {
+      "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -19,12 +10,11 @@
       "special": true
     }
   },
-  "bos_token": "</s>",
+  "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "</s>",
-  "errors": "replace",
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
   "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "</s>"
+  "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3f955a6417a2f9c16ccdd481640788d63f7a1cafbc8ba4a4f4f56c26def8895
+oid sha256:a63c9bda74d37531557c8758fde795b9e8a8a39621a60642aa6690a5089e8f88
 size 5304