fresh-8-layer-swag-distill-of-fresh-8-layer-gpqa

README.md

@@ -0,0 +1,78 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: fresh-8-layer-swag-distill-of-fresh-8-layer-gpqa
+  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. -->
+
+# fresh-8-layer-swag-distill-of-fresh-8-layer-gpqa
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 22.9598
+- Accuracy: 0.4040
+
+## 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: 0.0005
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 321
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 63   | 22.7715         | 0.2677   |
+| No log        | 2.0   | 126  | 24.4035         | 0.2879   |
+| No log        | 3.0   | 189  | 21.6171         | 0.3131   |
+| No log        | 4.0   | 252  | 22.9241         | 0.3333   |
+| No log        | 5.0   | 315  | 36.3034         | 0.3788   |
+| No log        | 6.0   | 378  | 22.9598         | 0.4040   |
+| No log        | 7.0   | 441  | 25.2469         | 0.3485   |
+| 5.5235        | 8.0   | 504  | 29.2667         | 0.3687   |
+| 5.5235        | 9.0   | 567  | 24.0718         | 0.3687   |
+| 5.5235        | 10.0  | 630  | 25.5240         | 0.3030   |
+| 5.5235        | 11.0  | 693  | 28.6147         | 0.3283   |
+| 5.5235        | 12.0  | 756  | 33.3811         | 0.3434   |
+| 5.5235        | 13.0  | 819  | 28.3026         | 0.3232   |
+| 5.5235        | 14.0  | 882  | 27.7010         | 0.2677   |
+| 5.5235        | 15.0  | 945  | 26.9798         | 0.3182   |
+| 3.9997        | 16.0  | 1008 | 26.8561         | 0.3232   |
+| 3.9997        | 17.0  | 1071 | 25.9683         | 0.3687   |
+| 3.9997        | 18.0  | 1134 | 23.6478         | 0.3333   |
+| 3.9997        | 19.0  | 1197 | 24.1695         | 0.3232   |
+| 3.9997        | 20.0  | 1260 | 24.7100         | 0.3485   |
+
+
+### Framework versions
+
+- Transformers 4.34.0.dev0
+- Pytorch 2.0.1+cu117
+- Datasets 2.14.5
+- Tokenizers 0.14.0

config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "BertForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcaeff518bba8c777a80318e74c266231fb999f5ebe61040419721e5d4ddc25a
+size 199128369

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fef8ae74e060c6d63aa0d854949c23ef3a0c1e44f82fa3b4af902fec4b9dba8
+size 4091