Hugging Face's logo

Zenith754
/
goodreads-bert-classifier

Text Classification
Transformers
Safetensors
distilbert
text-embeddings-inference
Model card Files
xet
 Community
Zenith754 commited on
Commit
2802ee8
·
verified ·
1 Parent(s): 0a5a996

Upload folder using huggingface_hub

Browse files
Files changed (39) hide show
  1. checkpoint-125/config.json +34 -0
  2. checkpoint-125/model.safetensors +3 -0
  3. checkpoint-125/optimizer.pt +3 -0
  4. checkpoint-125/rng_state.pth +3 -0
  5. checkpoint-125/scheduler.pt +3 -0
  6. checkpoint-125/special_tokens_map.json +7 -0
  7. checkpoint-125/tokenizer.json +0 -0
  8. checkpoint-125/tokenizer_config.json +55 -0
  9. checkpoint-125/trainer_state.json +33 -0
  10. checkpoint-125/training_args.bin +3 -0
  11. checkpoint-125/vocab.txt +0 -0
  12. checkpoint-250/config.json +34 -0
  13. checkpoint-250/model.safetensors +3 -0
  14. checkpoint-250/optimizer.pt +3 -0
  15. checkpoint-250/rng_state.pth +3 -0
  16. checkpoint-250/scheduler.pt +3 -0
  17. checkpoint-250/special_tokens_map.json +7 -0
  18. checkpoint-250/tokenizer.json +0 -0
  19. checkpoint-250/tokenizer_config.json +55 -0
  20. checkpoint-250/trainer_state.json +45 -0
  21. checkpoint-250/training_args.bin +3 -0
  22. checkpoint-250/vocab.txt +0 -0
  23. checkpoint-375/config.json +34 -0
  24. checkpoint-375/model.safetensors +3 -0
  25. checkpoint-375/optimizer.pt +3 -0
  26. checkpoint-375/rng_state.pth +3 -0
  27. checkpoint-375/scheduler.pt +3 -0
  28. checkpoint-375/special_tokens_map.json +7 -0
  29. checkpoint-375/tokenizer.json +0 -0
  30. checkpoint-375/tokenizer_config.json +55 -0
  31. checkpoint-375/trainer_state.json +57 -0
  32. checkpoint-375/training_args.bin +3 -0
  33. checkpoint-375/vocab.txt +0 -0
  34. config.json +34 -0
  35. model.safetensors +3 -0
  36. special_tokens_map.json +7 -0
  37. tokenizer.json +0 -0
  38. tokenizer_config.json +55 -0
  39. vocab.txt +0 -0
checkpoint-125/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "NEGATIVE",
13
+ "1": "POSITIVE"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "NEGATIVE": 0,
18
+ "POSITIVE": 1
19
+ },
20
+ "max_position_embeddings": 512,
21
+ "model_type": "distilbert",
22
+ "n_heads": 12,
23
+ "n_layers": 6,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "problem_type": "single_label_classification",
27
+ "qa_dropout": 0.1,
28
+ "seq_classif_dropout": 0.2,
29
+ "sinusoidal_pos_embds": false,
30
+ "tie_weights_": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.38.2",
33
+ "vocab_size": 28996
34
+ }
checkpoint-125/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f9d34aa309e7f1ab6b60be930dd8fd4340020e76b151e9fa7af26baee15d7ad
3
+ size 263144680
checkpoint-125/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf4c974df0f6225899f8fa813ae0a7f19ea7be530423584dade065212d84d126
3
+ size 526351109
checkpoint-125/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31534358a651b79b50a2dd745c92d5242b63b65f92064957f722f76ce33c2f31
3
+ size 14575
checkpoint-125/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e6f60fd22e075dda5be6742863ea270658394a7b21acad37e32593454c851ec
3
+ size 627
checkpoint-125/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
checkpoint-125/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-125/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
checkpoint-125/trainer_state.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.34977033734321594,
3
+ "best_model_checkpoint": "./final_model/checkpoint-125",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 125,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.858,
14
+ "eval_f1": 0.8647619047619047,
15
+ "eval_loss": 0.34977033734321594,
16
+ "eval_precision": 0.8136200716845878,
17
+ "eval_recall": 0.9227642276422764,
18
+ "eval_runtime": 22.0786,
19
+ "eval_samples_per_second": 22.646,
20
+ "eval_steps_per_second": 1.449,
21
+ "step": 125
22
+ }
23
+ ],
24
+ "logging_steps": 500,
25
+ "max_steps": 375,
26
+ "num_input_tokens_seen": 0,
27
+ "num_train_epochs": 3,
28
+ "save_steps": 500,
29
+ "total_flos": 264934797312000.0,
30
+ "train_batch_size": 16,
31
+ "trial_name": null,
32
+ "trial_params": null
33
+ }
checkpoint-125/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c093f90d8703f22d175d80a7ddcbf4e368b39dd2162f4da6293894fc3b414382
3
+ size 4411
checkpoint-125/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-250/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "NEGATIVE",
13
+ "1": "POSITIVE"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "NEGATIVE": 0,
18
+ "POSITIVE": 1
19
+ },
20
+ "max_position_embeddings": 512,
21
+ "model_type": "distilbert",
22
+ "n_heads": 12,
23
+ "n_layers": 6,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "problem_type": "single_label_classification",
27
+ "qa_dropout": 0.1,
28
+ "seq_classif_dropout": 0.2,
29
+ "sinusoidal_pos_embds": false,
30
+ "tie_weights_": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.38.2",
33
+ "vocab_size": 28996
34
+ }
checkpoint-250/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eae09b13e7b7d4b68c784cd8f7dfe77b95f7d296e8ed0478ad134611268e2e22
3
+ size 263144680
checkpoint-250/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd531136e2358ddcc74a9fa9d63caff659f0f8b74c467a14ddbfd860c5ad1161
3
+ size 526351109
checkpoint-250/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78a7c71e75607df266dd4ab3adbddaa8e4ba033da53111d7db86c5bceee3ab74
3
+ size 14575
checkpoint-250/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9200b31d49e3a707a318eff93c21cf029675e0b1bf7bb0341f13f8dba032321
3
+ size 627
checkpoint-250/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
checkpoint-250/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-250/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
checkpoint-250/trainer_state.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3336826264858246,
3
+ "best_model_checkpoint": "./final_model/checkpoint-250",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 250,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.858,
14
+ "eval_f1": 0.8647619047619047,
15
+ "eval_loss": 0.34977033734321594,
16
+ "eval_precision": 0.8136200716845878,
17
+ "eval_recall": 0.9227642276422764,
18
+ "eval_runtime": 22.0786,
19
+ "eval_samples_per_second": 22.646,
20
+ "eval_steps_per_second": 1.449,
21
+ "step": 125
22
+ },
23
+ {
24
+ "epoch": 2.0,
25
+ "eval_accuracy": 0.872,
26
+ "eval_f1": 0.875968992248062,
27
+ "eval_loss": 0.3336826264858246,
28
+ "eval_precision": 0.837037037037037,
29
+ "eval_recall": 0.9186991869918699,
30
+ "eval_runtime": 14.4795,
31
+ "eval_samples_per_second": 34.532,
32
+ "eval_steps_per_second": 2.21,
33
+ "step": 250
34
+ }
35
+ ],
36
+ "logging_steps": 500,
37
+ "max_steps": 375,
38
+ "num_input_tokens_seen": 0,
39
+ "num_train_epochs": 3,
40
+ "save_steps": 500,
41
+ "total_flos": 529869594624000.0,
42
+ "train_batch_size": 16,
43
+ "trial_name": null,
44
+ "trial_params": null
45
+ }
checkpoint-250/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c093f90d8703f22d175d80a7ddcbf4e368b39dd2162f4da6293894fc3b414382
3
+ size 4411
checkpoint-250/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-375/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "NEGATIVE",
13
+ "1": "POSITIVE"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "NEGATIVE": 0,
18
+ "POSITIVE": 1
19
+ },
20
+ "max_position_embeddings": 512,
21
+ "model_type": "distilbert",
22
+ "n_heads": 12,
23
+ "n_layers": 6,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "problem_type": "single_label_classification",
27
+ "qa_dropout": 0.1,
28
+ "seq_classif_dropout": 0.2,
29
+ "sinusoidal_pos_embds": false,
30
+ "tie_weights_": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.38.2",
33
+ "vocab_size": 28996
34
+ }
checkpoint-375/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c366723e15119597d8751a4e1a1f5717f48f08b41bfb4f0f9cee66cbcb4c983e
3
+ size 263144680
checkpoint-375/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e2f2eec3fc67bd0ff4a86dfa22aa9e69279a48227945ea7fde9ecf45c0dde41
3
+ size 526351109
checkpoint-375/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af8a7fe22e0ce11bf78660c0a7e9f642278c4296538eb1bfec0c7cdf014772f9
3
+ size 14575
checkpoint-375/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f23724ff4d7c845b1dc0676ea3af8abdc294d9247ce526b3a4b06fbdb54c60d
3
+ size 627
checkpoint-375/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
checkpoint-375/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-375/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
checkpoint-375/trainer_state.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3336826264858246,
3
+ "best_model_checkpoint": "./final_model/checkpoint-250",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 375,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.858,
14
+ "eval_f1": 0.8647619047619047,
15
+ "eval_loss": 0.34977033734321594,
16
+ "eval_precision": 0.8136200716845878,
17
+ "eval_recall": 0.9227642276422764,
18
+ "eval_runtime": 22.0786,
19
+ "eval_samples_per_second": 22.646,
20
+ "eval_steps_per_second": 1.449,
21
+ "step": 125
22
+ },
23
+ {
24
+ "epoch": 2.0,
25
+ "eval_accuracy": 0.872,
26
+ "eval_f1": 0.875968992248062,
27
+ "eval_loss": 0.3336826264858246,
28
+ "eval_precision": 0.837037037037037,
29
+ "eval_recall": 0.9186991869918699,
30
+ "eval_runtime": 14.4795,
31
+ "eval_samples_per_second": 34.532,
32
+ "eval_steps_per_second": 2.21,
33
+ "step": 250
34
+ },
35
+ {
36
+ "epoch": 3.0,
37
+ "eval_accuracy": 0.878,
38
+ "eval_f1": 0.8767676767676768,
39
+ "eval_loss": 0.3653552234172821,
40
+ "eval_precision": 0.8714859437751004,
41
+ "eval_recall": 0.8821138211382114,
42
+ "eval_runtime": 15.9886,
43
+ "eval_samples_per_second": 31.272,
44
+ "eval_steps_per_second": 2.001,
45
+ "step": 375
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 375,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 3,
52
+ "save_steps": 500,
53
+ "total_flos": 794804391936000.0,
54
+ "train_batch_size": 16,
55
+ "trial_name": null,
56
+ "trial_params": null
57
+ }
checkpoint-375/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c093f90d8703f22d175d80a7ddcbf4e368b39dd2162f4da6293894fc3b414382
3
+ size 4411
checkpoint-375/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "NEGATIVE",
13
+ "1": "POSITIVE"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "NEGATIVE": 0,
18
+ "POSITIVE": 1
19
+ },
20
+ "max_position_embeddings": 512,
21
+ "model_type": "distilbert",
22
+ "n_heads": 12,
23
+ "n_layers": 6,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "problem_type": "single_label_classification",
27
+ "qa_dropout": 0.1,
28
+ "seq_classif_dropout": 0.2,
29
+ "sinusoidal_pos_embds": false,
30
+ "tie_weights_": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.38.2",
33
+ "vocab_size": 28996
34
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eae09b13e7b7d4b68c784cd8f7dfe77b95f7d296e8ed0478ad134611268e2e22
3
+ size 263144680
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff