Model save

README.md

@@ -0,0 +1,77 @@
+---
+license: other
+base_model: facebook/opt-350m
+tags:
+- trl
+- reward-trainer
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: my_first_reward_modeling
+  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. -->
+
+# my_first_reward_modeling
+
+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: 0.6161
+- Accuracy: 0.6461
+
+## 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: 64
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 1024
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.7387        | 0.07  | 10   | 0.6877          | 0.5700   |
+| 0.6892        | 0.14  | 20   | 0.6735          | 0.5774   |
+| 0.6704        | 0.21  | 30   | 0.6650          | 0.5939   |
+| 0.6579        | 0.28  | 40   | 0.6563          | 0.6003   |
+| 0.6542        | 0.35  | 50   | 0.6483          | 0.6111   |
+| 0.6509        | 0.42  | 60   | 0.6398          | 0.6209   |
+| 0.64          | 0.49  | 70   | 0.6334          | 0.6301   |
+| 0.6322        | 0.56  | 80   | 0.6291          | 0.6354   |
+| 0.6268        | 0.63  | 90   | 0.6253          | 0.6397   |
+| 0.6254        | 0.7   | 100  | 0.6219          | 0.6401   |
+| 0.6213        | 0.77  | 110  | 0.6201          | 0.6436   |
+| 0.6284        | 0.83  | 120  | 0.6170          | 0.6454   |
+| 0.6233        | 0.9   | 130  | 0.6160          | 0.6452   |
+| 0.6192        | 0.97  | 140  | 0.6161          | 0.6461   |
+
+
+### Framework versions
+
+- Transformers 4.39.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "facebook/opt-350m",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForSequenceClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "init_std": 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>",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.2",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5621e3aa5e1dbdc7026b03245f682d0bf8894419f21136f4354ba0feb685563
+size 1324833016

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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
+  }
+}

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "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>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "</s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "</s>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bc292854f530b9d6a7f1673a6194dc632094b3ffe0dabf30cb2f4e834e559c2
+size 4984