Hugging Face's logo

k4black
/
roberta-large-e-snli-classification-nli_explanation-base-b16

Text Classification
Transformers
PyTorch
roberta
Inference Endpoints
Model card Files Community
k4black commited on
Commit
8b7dc52
•
1 Parent(s): fc5c11a

Training in progress, step 400

Browse files
Files changed (21) hide show
  1. .gitignore +1 -0
  2. config.json +38 -0
  3. last-checkpoint/config.json +38 -0
  4. last-checkpoint/merges.txt +0 -0
  5. last-checkpoint/optimizer.pt +3 -0
  6. last-checkpoint/pytorch_model.bin +3 -0
  7. last-checkpoint/rng_state.pth +3 -0
  8. last-checkpoint/scheduler.pt +3 -0
  9. last-checkpoint/special_tokens_map.json +15 -0
  10. last-checkpoint/tokenizer.json +0 -0
  11. last-checkpoint/tokenizer_config.json +15 -0
  12. last-checkpoint/trainer_state.json +32 -0
  13. last-checkpoint/training_args.bin +3 -0
  14. last-checkpoint/vocab.json +0 -0
  15. merges.txt +0 -0
  16. pytorch_model.bin +3 -0
  17. special_tokens_map.json +15 -0
  18. tokenizer.json +0 -0
  19. tokenizer_config.json +15 -0
  20. training_args.bin +3 -0
  21. vocab.json +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-large",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "entailment",
15
+ "1": "neutral",
16
+ "2": "contradiction"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 4096,
20
+ "label2id": {
21
+ "contradiction": 2,
22
+ "entailment": 0,
23
+ "neutral": 1
24
+ },
25
+ "layer_norm_eps": 1e-05,
26
+ "max_position_embeddings": 514,
27
+ "model_type": "roberta",
28
+ "num_attention_heads": 16,
29
+ "num_hidden_layers": 24,
30
+ "pad_token_id": 1,
31
+ "position_embedding_type": "absolute",
32
+ "problem_type": "single_label_classification",
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.27.4",
35
+ "type_vocab_size": 1,
36
+ "use_cache": true,
37
+ "vocab_size": 50265
38
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-large",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "entailment",
15
+ "1": "neutral",
16
+ "2": "contradiction"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 4096,
20
+ "label2id": {
21
+ "contradiction": 2,
22
+ "entailment": 0,
23
+ "neutral": 1
24
+ },
25
+ "layer_norm_eps": 1e-05,
26
+ "max_position_embeddings": 514,
27
+ "model_type": "roberta",
28
+ "num_attention_heads": 16,
29
+ "num_hidden_layers": 24,
30
+ "pad_token_id": 1,
31
+ "position_embedding_type": "absolute",
32
+ "problem_type": "single_label_classification",
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.27.4",
35
+ "type_vocab_size": 1,
36
+ "use_cache": true,
37
+ "vocab_size": 50265
38
+ }
last-checkpoint/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e47913498cc62e3d622e030fa2381e7512d18d5065ac931177b2dc5decc8f98
3
+ size 2843230968
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ad67941a343ddab4739bbed3aafcbc93cf909ef47fa983f60de65a1f5efea2d
3
+ size 1421591285
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8df2fbb5eae4ba8d93df3cabc2751ec21112d1099f8e59f83bee856092c76626
3
+ size 14575
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b5c0c9d70ab7582ef8cee0fb535ed73768bfc895b20793c16cf28f34c9dff83
3
+ size 627
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "mask_token": "<mask>",
8
+ "model_max_length": 512,
9
+ "pad_token": "<pad>",
10
+ "sep_token": "</s>",
11
+ "special_tokens_map_file": null,
12
+ "tokenizer_class": "RobertaTokenizer",
13
+ "trim_offsets": true,
14
+ "unk_token": "<unk>"
15
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7974911320075254,
3
+ "best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/roberta-large-e-snli-classification-nli_explanation-base-b16/checkpoint-400",
4
+ "epoch": 0.011649580615097856,
5
+ "global_step": 400,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 7.765482430596001e-07,
13
+ "loss": 1.0726,
14
+ "step": 400
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "eval_accuracy": 0.7982117455801666,
19
+ "eval_f1": 0.7974911320075254,
20
+ "eval_loss": 0.8326770067214966,
21
+ "eval_runtime": 12.8669,
22
+ "eval_samples_per_second": 764.91,
23
+ "eval_steps_per_second": 47.875,
24
+ "step": 400
25
+ }
26
+ ],
27
+ "max_steps": 103008,
28
+ "num_train_epochs": 3,
29
+ "total_flos": 792493810750848.0,
30
+ "trial_name": null,
31
+ "trial_params": null
32
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a16630b6af4565718b5f8011185502435b6a822b680096e06d599e447b11d874
3
+ size 3771
last-checkpoint/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ad67941a343ddab4739bbed3aafcbc93cf909ef47fa983f60de65a1f5efea2d
3
+ size 1421591285
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "mask_token": "<mask>",
8
+ "model_max_length": 512,
9
+ "pad_token": "<pad>",
10
+ "sep_token": "</s>",
11
+ "special_tokens_map_file": null,
12
+ "tokenizer_class": "RobertaTokenizer",
13
+ "trim_offsets": true,
14
+ "unk_token": "<unk>"
15
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a16630b6af4565718b5f8011185502435b6a822b680096e06d599e447b11d874
3
+ size 3771
vocab.json ADDED
The diff for this file is too large to render. See raw diff