fresh-2-layer-qasc5000-distill-of-fresh-2-layer-mmlu_EVAL_mmlu

README.md

@@ -0,0 +1,73 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: fresh-2-layer-qasc5000-distill-of-fresh-2-layer-mmlu_EVAL_mmlu
+  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-qasc5000-distill-of-fresh-2-layer-mmlu_EVAL_mmlu
+
+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: 207.7788
+- Accuracy: 0.3764
+
+## 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        | 0.64  | 100  | 202.2836        | 0.24     |
+| No log        | 1.27  | 200  | 206.3151        | 0.34     |
+| No log        | 1.91  | 300  | 195.0245        | 0.35     |
+| No log        | 2.55  | 400  | 201.5064        | 0.388    |
+| 98.9054       | 3.18  | 500  | 200.6433        | 0.386    |
+| 98.9054       | 3.82  | 600  | 193.7714        | 0.388    |
+| 98.9054       | 4.46  | 700  | 189.6684        | 0.39     |
+| 98.9054       | 5.1   | 800  | 192.2281        | 0.378    |
+| 98.9054       | 5.73  | 900  | 194.5975        | 0.388    |
+| 23.6632       | 6.37  | 1000 | 199.0726        | 0.42     |
+| 23.6632       | 7.01  | 1100 | 192.3244        | 0.402    |
+| 23.6632       | 7.64  | 1200 | 186.5772        | 0.402    |
+| 23.6632       | 8.28  | 1300 | 190.7620        | 0.402    |
+| 23.6632       | 8.92  | 1400 | 198.1279        | 0.394    |
+| 14.2685       | 9.55  | 1500 | 194.6297        | 0.366    |
+
+
+### 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 sha256:0892758fac20a31e7a0f794c1ffbedda7b34386afabc6b3d56ec9e3f3adf94d2
+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 sha256:215dc9497662dfa999394b430e6195d5f323fa756398fbb64462244addffba0c
+size 4091