EhsanAghazadeh commited on
Commit
621a270
1 Parent(s): 2875543

Add model and its dependencies

Browse files
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EhsanAghazadeh/bert-based-uncased-sst2-e3",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "finetuning_task": "sst2",
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "negative",
15
+ "1": "positive"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "negative": 0,
21
+ "positive": 1
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "problem_type": "single_label_classification",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.15.0",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 30522
36
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58f6592f9f2fc4794a776668349adea6bb31bbe008adc8379bd07412aa057e3d
3
+ size 875986717
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91fbe051d9b180be3ffec2842241288acacd861b2a33b08bbc9a85b522aca193
3
+ size 438019245
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9358d8e956a20387ca3d0b109fce662580175a75c51a90664e0613fcf3310ef1
3
+ size 14503
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41d5f0199a5743058d7479ccfbb24a41835cc0a499d5be66159637f713ee5c39
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "EhsanAghazadeh/bert-based-uncased-sst2-e3", "tokenizer_class": "BertTokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.926605504587156,
3
+ "best_model_checkpoint": "./bert_base/fine_tuned_models/checkpoint-2105",
4
+ "epoch": 1.0,
5
+ "global_step": 2105,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 0.0,
13
+ "loss": 0.0571,
14
+ "step": 2105
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.926605504587156,
19
+ "eval_loss": 0.27417176961898804,
20
+ "eval_runtime": 13.7641,
21
+ "eval_samples_per_second": 63.353,
22
+ "eval_steps_per_second": 7.919,
23
+ "step": 2105
24
+ }
25
+ ],
26
+ "max_steps": 2105,
27
+ "num_train_epochs": 1,
28
+ "total_flos": 4430066616860160.0,
29
+ "trial_name": null,
30
+ "trial_params": null
31
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ff996c342d72c425daf1db7403556ca648948b23eda3d1279baa49274db3bfa
3
+ size 2991
vocab.txt ADDED
The diff for this file is too large to render. See raw diff