fresh-2-layer-medmcqa50000-distill-of-fresh-2-layer-gpqa_EVAL_gpqa

README.md

@@ -0,0 +1,94 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: fresh-2-layer-medmcqa50000-distill-of-fresh-2-layer-gpqa_EVAL_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-2-layer-medmcqa50000-distill-of-fresh-2-layer-gpqa_EVAL_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: 4.6855
+- Accuracy: 0.7828
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 321
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- training_steps: 5000
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 0.06  | 100  | 14.3260         | 0.3333   |
+| No log        | 0.13  | 200  | 12.1073         | 0.4899   |
+| No log        | 0.19  | 300  | 11.0435         | 0.5101   |
+| No log        | 0.26  | 400  | 9.6543          | 0.5808   |
+| 3.466         | 0.32  | 500  | 9.4758          | 0.5960   |
+| 3.466         | 0.38  | 600  | 8.5372          | 0.6263   |
+| 3.466         | 0.45  | 700  | 8.3611          | 0.6566   |
+| 3.466         | 0.51  | 800  | 7.3273          | 0.6919   |
+| 3.466         | 0.58  | 900  | 8.0522          | 0.6414   |
+| 1.1408        | 0.64  | 1000 | 7.5545          | 0.6515   |
+| 1.1408        | 0.7   | 1100 | 6.9424          | 0.7020   |
+| 1.1408        | 0.77  | 1200 | 6.5618          | 0.6869   |
+| 1.1408        | 0.83  | 1300 | 6.1301          | 0.7121   |
+| 1.1408        | 0.9   | 1400 | 7.3708          | 0.7121   |
+| 0.7156        | 0.96  | 1500 | 5.9791          | 0.7172   |
+| 0.7156        | 1.02  | 1600 | 6.0925          | 0.7172   |
+| 0.7156        | 1.09  | 1700 | 6.1228          | 0.7121   |
+| 0.7156        | 1.15  | 1800 | 6.2473          | 0.7222   |
+| 0.7156        | 1.22  | 1900 | 6.3483          | 0.7172   |
+| 0.4805        | 1.28  | 2000 | 5.6959          | 0.7071   |
+| 0.4805        | 1.34  | 2100 | 5.5578          | 0.7424   |
+| 0.4805        | 1.41  | 2200 | 5.2385          | 0.7626   |
+| 0.4805        | 1.47  | 2300 | 5.6583          | 0.7374   |
+| 0.4805        | 1.54  | 2400 | 5.1442          | 0.7475   |
+| 0.3914        | 1.6   | 2500 | 5.0866          | 0.7677   |
+| 0.3914        | 1.66  | 2600 | 5.0077          | 0.7626   |
+| 0.3914        | 1.73  | 2700 | 4.6813          | 0.7778   |
+| 0.3914        | 1.79  | 2800 | 4.8810          | 0.7677   |
+| 0.3914        | 1.86  | 2900 | 4.6941          | 0.7626   |
+| 0.3368        | 1.92  | 3000 | 4.8332          | 0.7727   |
+| 0.3368        | 1.98  | 3100 | 4.6855          | 0.7828   |
+| 0.3368        | 2.05  | 3200 | 4.7359          | 0.7778   |
+| 0.3368        | 2.11  | 3300 | 4.5992          | 0.7778   |
+| 0.3368        | 2.18  | 3400 | 4.5406          | 0.7677   |
+| 0.2459        | 2.24  | 3500 | 4.8480          | 0.7828   |
+| 0.2459        | 2.3   | 3600 | 4.6215          | 0.7677   |
+
+
+### 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": 2,
+  "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:b842d80f44994705f41eeab14f6ec3f508be602adf5a8c24a45d43d4c1d5e7ab
+size 98247916

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 sha256:1bd56040b090544beb07fed7d6eea38223fff41a172f9814a936784c3178d5c1
+size 4091