Hugging Face's logo

heruberuto
/
distilbert-base-uncased-sa-imdb

TensorBoard
Model card Files Metrics Community
heruberuto commited on
Commit
f829f49
·
1 Parent(s): e68c39f

models done

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +2 -0
  2. checkpoint-1000/config.json +25 -0
  3. checkpoint-1000/optimizer.pt +3 -0
  4. checkpoint-1000/pytorch_model.bin +3 -0
  5. checkpoint-1000/rng_state.pth +0 -0
  6. checkpoint-1000/scheduler.pt +0 -0
  7. checkpoint-1000/special_tokens_map.json +1 -0
  8. checkpoint-1000/tokenizer.json +0 -0
  9. checkpoint-1000/tokenizer_config.json +1 -0
  10. checkpoint-1000/trainer_state.json +28 -0
  11. checkpoint-1000/training_args.bin +0 -0
  12. checkpoint-1000/vocab.txt +0 -0
  13. checkpoint-1500/config.json +25 -0
  14. checkpoint-1500/optimizer.pt +3 -0
  15. checkpoint-1500/pytorch_model.bin +3 -0
  16. checkpoint-1500/rng_state.pth +0 -0
  17. checkpoint-1500/scheduler.pt +0 -0
  18. checkpoint-1500/special_tokens_map.json +1 -0
  19. checkpoint-1500/tokenizer.json +0 -0
  20. checkpoint-1500/tokenizer_config.json +1 -0
  21. checkpoint-1500/trainer_state.json +34 -0
  22. checkpoint-1500/training_args.bin +0 -0
  23. checkpoint-1500/vocab.txt +0 -0
  24. checkpoint-2000/config.json +25 -0
  25. checkpoint-2000/optimizer.pt +3 -0
  26. checkpoint-2000/pytorch_model.bin +3 -0
  27. checkpoint-2000/rng_state.pth +0 -0
  28. checkpoint-2000/scheduler.pt +0 -0
  29. checkpoint-2000/special_tokens_map.json +1 -0
  30. checkpoint-2000/tokenizer.json +0 -0
  31. checkpoint-2000/tokenizer_config.json +1 -0
  32. checkpoint-2000/trainer_state.json +40 -0
  33. checkpoint-2000/training_args.bin +0 -0
  34. checkpoint-2000/vocab.txt +0 -0
  35. checkpoint-2500/config.json +25 -0
  36. checkpoint-2500/optimizer.pt +3 -0
  37. checkpoint-2500/pytorch_model.bin +3 -0
  38. checkpoint-2500/rng_state.pth +0 -0
  39. checkpoint-2500/scheduler.pt +0 -0
  40. checkpoint-2500/special_tokens_map.json +1 -0
  41. checkpoint-2500/tokenizer.json +0 -0
  42. checkpoint-2500/tokenizer_config.json +1 -0
  43. checkpoint-2500/trainer_state.json +46 -0
  44. checkpoint-2500/training_args.bin +0 -0
  45. checkpoint-2500/vocab.txt +0 -0
  46. checkpoint-3000/config.json +25 -0
  47. checkpoint-3000/optimizer.pt +3 -0
  48. checkpoint-3000/pytorch_model.bin +3 -0
  49. checkpoint-3000/rng_state.pth +0 -0
  50. checkpoint-3000/scheduler.pt +0 -0
.gitattributes CHANGED
@@ -25,3 +25,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ */pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
29
+ */optimizer.pt filter=lfs diff=lfs merge=lfs -text
checkpoint-1000/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
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
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.13.0.dev0",
24
+ "vocab_size": 30522
25
+ }
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9a6ed83b3ab9e114c56f7a65febbe3f919a03a78e470549f0ffd5226316690a
3
+ size 535703734
checkpoint-1000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b5373e04441bec36f1b43b1b54f5c0167cc1ae9b51f30db30f1653080dec069
3
+ size 267862159
checkpoint-1000/rng_state.pth ADDED
Binary file (14.6 kB). View file
 
checkpoint-1000/scheduler.pt ADDED
Binary file (623 Bytes). View file
 
checkpoint-1000/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
checkpoint-1000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/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": "distilbert-base-uncased", "tokenizer_class": "DistilBertTokenizer"}
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.6397952655150352,
5
+ "global_step": 1000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.32,
12
+ "learning_rate": 1.872040946896993e-05,
13
+ "loss": 0.3165,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.64,
18
+ "learning_rate": 1.744081893793986e-05,
19
+ "loss": 0.2508,
20
+ "step": 1000
21
+ }
22
+ ],
23
+ "max_steps": 7815,
24
+ "num_train_epochs": 5,
25
+ "total_flos": 2100332699784000.0,
26
+ "trial_name": null,
27
+ "trial_params": null
28
+ }
checkpoint-1000/training_args.bin ADDED
Binary file (2.8 kB). View file
 
checkpoint-1000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1500/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
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
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.13.0.dev0",
24
+ "vocab_size": 30522
25
+ }
checkpoint-1500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82785261bcd8fd5d590d2f8fcf3be31380284a51a02495b5beb18aabbefc6e34
3
+ size 535703734
checkpoint-1500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57ea5b2718e0880ecbf85637530a68bf5ba2d46a0a3e353d602541378599722d
3
+ size 267862159
checkpoint-1500/rng_state.pth ADDED
Binary file (14.6 kB). View file
 
checkpoint-1500/scheduler.pt ADDED
Binary file (623 Bytes). View file
 
checkpoint-1500/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
checkpoint-1500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1500/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": "distilbert-base-uncased", "tokenizer_class": "DistilBertTokenizer"}
checkpoint-1500/trainer_state.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9596928982725528,
5
+ "global_step": 1500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.32,
12
+ "learning_rate": 1.872040946896993e-05,
13
+ "loss": 0.3165,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.64,
18
+ "learning_rate": 1.744081893793986e-05,
19
+ "loss": 0.2508,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.96,
24
+ "learning_rate": 1.616122840690979e-05,
25
+ "loss": 0.2268,
26
+ "step": 1500
27
+ }
28
+ ],
29
+ "max_steps": 7815,
30
+ "num_train_epochs": 5,
31
+ "total_flos": 3150811589944704.0,
32
+ "trial_name": null,
33
+ "trial_params": null
34
+ }
checkpoint-1500/training_args.bin ADDED
Binary file (2.8 kB). View file
 
checkpoint-1500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2000/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
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
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.13.0.dev0",
24
+ "vocab_size": 30522
25
+ }
checkpoint-2000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ada633d4e891b7e174167d603b755ba4ee2726d72248590366b5df08a8ae6ddf
3
+ size 535703734
checkpoint-2000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2848ad231f58ff0e4c095178198bf5b1012192e98a9ae9b864cf4123f1402cbd
3
+ size 267862159
checkpoint-2000/rng_state.pth ADDED
Binary file (14.6 kB). View file
 
checkpoint-2000/scheduler.pt ADDED
Binary file (623 Bytes). View file
 
checkpoint-2000/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
checkpoint-2000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2000/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": "distilbert-base-uncased", "tokenizer_class": "DistilBertTokenizer"}
checkpoint-2000/trainer_state.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.2795905310300704,
5
+ "global_step": 2000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.32,
12
+ "learning_rate": 1.872040946896993e-05,
13
+ "loss": 0.3165,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.64,
18
+ "learning_rate": 1.744081893793986e-05,
19
+ "loss": 0.2508,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.96,
24
+ "learning_rate": 1.616122840690979e-05,
25
+ "loss": 0.2268,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 1.28,
30
+ "learning_rate": 1.488163787587972e-05,
31
+ "loss": 0.1718,
32
+ "step": 2000
33
+ }
34
+ ],
35
+ "max_steps": 7815,
36
+ "num_train_epochs": 5,
37
+ "total_flos": 4193866096371360.0,
38
+ "trial_name": null,
39
+ "trial_params": null
40
+ }
checkpoint-2000/training_args.bin ADDED
Binary file (2.8 kB). View file
 
checkpoint-2000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2500/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
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
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.13.0.dev0",
24
+ "vocab_size": 30522
25
+ }
checkpoint-2500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f5bfd363b18260da50c9aaaff5b38ded1fcb935ea57abf639b2db9bf3e94894
3
+ size 535703734
checkpoint-2500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:713888053243ba822f673ec9bb61bee035beefd371a31ce9637b668d4c196fd0
3
+ size 267862159
checkpoint-2500/rng_state.pth ADDED
Binary file (14.6 kB). View file
 
checkpoint-2500/scheduler.pt ADDED
Binary file (623 Bytes). View file
 
checkpoint-2500/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
checkpoint-2500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2500/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": "distilbert-base-uncased", "tokenizer_class": "DistilBertTokenizer"}
checkpoint-2500/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.599488163787588,
5
+ "global_step": 2500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.32,
12
+ "learning_rate": 1.872040946896993e-05,
13
+ "loss": 0.3165,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.64,
18
+ "learning_rate": 1.744081893793986e-05,
19
+ "loss": 0.2508,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.96,
24
+ "learning_rate": 1.616122840690979e-05,
25
+ "loss": 0.2268,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 1.28,
30
+ "learning_rate": 1.488163787587972e-05,
31
+ "loss": 0.1718,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 1.6,
36
+ "learning_rate": 1.3602047344849649e-05,
37
+ "loss": 0.1513,
38
+ "step": 2500
39
+ }
40
+ ],
41
+ "max_steps": 7815,
42
+ "num_train_epochs": 5,
43
+ "total_flos": 5244957648250848.0,
44
+ "trial_name": null,
45
+ "trial_params": null
46
+ }
checkpoint-2500/training_args.bin ADDED
Binary file (2.8 kB). View file
 
checkpoint-2500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-3000/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
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
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.13.0.dev0",
24
+ "vocab_size": 30522
25
+ }
checkpoint-3000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:def467cfc678d17099532ea2048fcb80128927260f229731756452379dd9f140
3
+ size 535703734
checkpoint-3000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fc0511c28da4071afe36a515e99ff908f5376ad2a6e7a6cc27c0afe9f8a6eeb
3
+ size 267862159
checkpoint-3000/rng_state.pth ADDED
Binary file (14.6 kB). View file
 
checkpoint-3000/scheduler.pt ADDED
Binary file (623 Bytes). View file