distilroberta-base-reward-model

README.md

@@ -0,0 +1,87 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: distilroberta-base
+tags:
+- trl
+- reward-trainer
+- generated_from_trainer
+metrics:
+- accuracy
+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 [distilroberta-base](https://huggingface.co/distilroberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5988
+- Accuracy: 0.65
+
+## 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: 32
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 500
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 0.7043        | 0.0150 | 20   | 0.6886          | 0.54     |
+| 0.6671        | 0.0301 | 40   | 0.6924          | 0.53     |
+| 0.6131        | 0.0451 | 60   | 0.7038          | 0.58     |
+| 0.6149        | 0.0602 | 80   | 0.6759          | 0.6      |
+| 0.6539        | 0.0752 | 100  | 0.6593          | 0.58     |
+| 0.6671        | 0.0902 | 120  | 0.7227          | 0.59     |
+| 0.6863        | 0.1053 | 140  | 0.6452          | 0.58     |
+| 0.6332        | 0.1203 | 160  | 0.6394          | 0.64     |
+| 0.6259        | 0.1353 | 180  | 0.6630          | 0.61     |
+| 0.6257        | 0.1504 | 200  | 0.6369          | 0.61     |
+| 0.5376        | 0.1654 | 220  | 0.6460          | 0.62     |
+| 0.6734        | 0.1805 | 240  | 0.6404          | 0.62     |
+| 0.724         | 0.1955 | 260  | 0.7469          | 0.6      |
+| 0.541         | 0.2105 | 280  | 0.6295          | 0.64     |
+| 0.5495        | 0.2256 | 300  | 0.6182          | 0.65     |
+| 0.7581        | 0.2406 | 320  | 0.6262          | 0.6      |
+| 0.5234        | 0.2556 | 340  | 0.6228          | 0.63     |
+| 0.5787        | 0.2707 | 360  | 0.6208          | 0.64     |
+| 0.6025        | 0.2857 | 380  | 0.6069          | 0.65     |
+| 0.6061        | 0.3008 | 400  | 0.6166          | 0.65     |
+| 0.8482        | 0.3158 | 420  | 0.6078          | 0.65     |
+| 0.5613        | 0.3308 | 440  | 0.5940          | 0.65     |
+| 0.7284        | 0.3459 | 460  | 0.6042          | 0.65     |
+| 0.5778        | 0.3609 | 480  | 0.5990          | 0.65     |
+| 0.6848        | 0.3759 | 500  | 0.5988          | 0.65     |
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.5.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "distilroberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5aaa92093c12204e2f8e5fe6139a8aa4de71bc9615eeb8573d47dadce842de0
+size 328489204

runs/Dec02_12-37-30_2fdf3026ab9f/events.out.tfevents.1733143058.2fdf3026ab9f.194.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa6cb8bb78f3401308f008e453b74dfaad5b80f0cc93c4e88820d011fd3d1cbb
+size 118483

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "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
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f9f5956d7398dd70ec5eb04aa255f0c3a7452534be0e75bccb9e48f403c37e4
+size 5240