add model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,74 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- commonsense_qa
+metrics:
+- accuracy
+model_index:
+- name: albert-xxlarge-v2-finetuned-csqa
+  results:
+  - dataset:
+      name: commonsense_qa
+      type: commonsense_qa
+      args: default
+    metric:
+      name: Accuracy
+      type: accuracy
+      value: 0.7870597839355469
+---
+
+<!-- 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. -->
+
+# albert-xxlarge-v2-finetuned-csqa
+
+This model is a fine-tuned version of [albert-xxlarge-v2](https://huggingface.co/albert-xxlarge-v2) on the commonsense_qa dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6177
+- Accuracy: 0.7871
+
+## 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: 1e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.7464        | 1.0   | 609  | 0.5319          | 0.7985   |
+| 0.3116        | 2.0   | 1218 | 0.6422          | 0.7936   |
+| 0.0769        | 3.0   | 1827 | 1.2674          | 0.7952   |
+| 0.0163        | 4.0   | 2436 | 1.4839          | 0.7903   |
+| 0.0122        | 5.0   | 3045 | 1.6177          | 0.7871   |
+
+
+### Framework versions
+
+- Transformers 4.8.2
+- Pytorch 1.9.0
+- Datasets 1.10.2
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "albert-xxlarge-v2",
+  "architectures": [
+    "AlbertForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 16384,
+  "layer_norm_eps": 1e-12,
+  "layers_to_keep": [],
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 64,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.8.2",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71af2a621125cea11d1b5fb40ae676a11eabb34fb15cb6c481dace02a22aa38f
+size 890413777

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "remove_space": true, "keep_accents": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "albert-xxlarge-v2", "tokenizer_class": "AlbertTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f12874138df81c2ed43b50631b01d8e4a0ec813f8a8a6655fe9461a95c2568f6
+size 2671