Hugging Face's logo

Gaxys
/
DistilBERT-PD_Books

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
text-embeddings-inference
Model card Files
xet
Metrics Community
Gaxys commited on
Commit
22e4176
·
1 Parent(s): 93bdb33

Training in progress, epoch 1

Browse files
Files changed (48) hide show
  1. model.safetensors +1 -1
  2. run-1/checkpoint-20/config.json +35 -0
  3. run-1/checkpoint-20/model.safetensors +3 -0
  4. run-1/checkpoint-20/optimizer.pt +3 -0
  5. run-1/checkpoint-20/rng_state.pth +3 -0
  6. run-1/checkpoint-20/scheduler.pt +3 -0
  7. run-1/checkpoint-20/special_tokens_map.json +7 -0
  8. run-1/checkpoint-20/tokenizer.json +0 -0
  9. run-1/checkpoint-20/tokenizer_config.json +55 -0
  10. run-1/checkpoint-20/trainer_state.json +54 -0
  11. run-1/checkpoint-20/training_args.bin +3 -0
  12. run-1/checkpoint-20/vocab.txt +0 -0
  13. run-1/checkpoint-30/config.json +35 -0
  14. run-1/checkpoint-30/model.safetensors +3 -0
  15. run-1/checkpoint-30/optimizer.pt +3 -0
  16. run-1/checkpoint-30/rng_state.pth +3 -0
  17. run-1/checkpoint-30/scheduler.pt +3 -0
  18. run-1/checkpoint-30/special_tokens_map.json +7 -0
  19. run-1/checkpoint-30/tokenizer.json +0 -0
  20. run-1/checkpoint-30/tokenizer_config.json +55 -0
  21. run-1/checkpoint-30/trainer_state.json +69 -0
  22. run-1/checkpoint-30/training_args.bin +3 -0
  23. run-1/checkpoint-30/vocab.txt +0 -0
  24. run-1/checkpoint-40/config.json +35 -0
  25. run-1/checkpoint-40/model.safetensors +3 -0
  26. run-1/checkpoint-40/optimizer.pt +3 -0
  27. run-1/checkpoint-40/rng_state.pth +3 -0
  28. run-1/checkpoint-40/scheduler.pt +3 -0
  29. run-1/checkpoint-40/special_tokens_map.json +7 -0
  30. run-1/checkpoint-40/tokenizer.json +0 -0
  31. run-1/checkpoint-40/tokenizer_config.json +55 -0
  32. run-1/checkpoint-40/trainer_state.json +84 -0
  33. run-1/checkpoint-40/training_args.bin +3 -0
  34. run-1/checkpoint-40/vocab.txt +0 -0
  35. run-2/checkpoint-5/config.json +35 -0
  36. run-2/checkpoint-5/model.safetensors +3 -0
  37. run-2/checkpoint-5/optimizer.pt +3 -0
  38. run-2/checkpoint-5/rng_state.pth +3 -0
  39. run-2/checkpoint-5/scheduler.pt +3 -0
  40. run-2/checkpoint-5/special_tokens_map.json +7 -0
  41. run-2/checkpoint-5/tokenizer.json +0 -0
  42. run-2/checkpoint-5/tokenizer_config.json +55 -0
  43. run-2/checkpoint-5/trainer_state.json +39 -0
  44. run-2/checkpoint-5/training_args.bin +3 -0
  45. run-2/checkpoint-5/vocab.txt +0 -0
  46. runs/Nov29_01-02-41_37a4be0f03a9/events.out.tfevents.1701220519.37a4be0f03a9.346.2 +2 -2
  47. runs/Nov29_01-02-41_37a4be0f03a9/events.out.tfevents.1701220660.37a4be0f03a9.346.3 +3 -0
  48. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e416576047034dae9e19f403c1a908081e857294f2e87d70e1d9d58fc2426b5d
3
  size 267835644
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98d9f241fe83935d68f18735b6668d5492714595cc5df686be3ec3dc4b4a974f
3
  size 267835644
run-1/checkpoint-20/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "id2label": {
12
+ "0": "CAROLL",
13
+ "1": "DICKENS",
14
+ "2": "DOYLE"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "CAROLL": 0,
19
+ "DICKENS": 1,
20
+ "DOYLE": 2
21
+ },
22
+ "max_position_embeddings": 512,
23
+ "model_type": "distilbert",
24
+ "n_heads": 12,
25
+ "n_layers": 6,
26
+ "pad_token_id": 0,
27
+ "problem_type": "single_label_classification",
28
+ "qa_dropout": 0.1,
29
+ "seq_classif_dropout": 0.2,
30
+ "sinusoidal_pos_embds": false,
31
+ "tie_weights_": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.35.2",
34
+ "vocab_size": 30522
35
+ }
run-1/checkpoint-20/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2a3081022db6569ec8cf9c9f559ea321bf6c7803bbce28bc3f4e5102d6e83f6
3
+ size 267835644
run-1/checkpoint-20/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1033d6b2baea1848a83977867baf2e287390da7c3c811a7de8b0fea90c54200c
3
+ size 535733434
run-1/checkpoint-20/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa1e06cac33626c42457907c094472f46880be76931a1a37930aaf343b19d9d8
3
+ size 14308
run-1/checkpoint-20/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ec240730cb9d463257c1bea2b363b51fe1d2be5225c26f791cf9f03e972cf5d
3
+ size 1064
run-1/checkpoint-20/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
+ }
run-1/checkpoint-20/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-20/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": true,
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
+ }
run-1/checkpoint-20/trainer_state.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.0257869958877563,
3
+ "best_model_checkpoint": "DistilBERT-PD_Books/run-1/checkpoint-20",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 20,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.6246851385390428,
14
+ "eval_loss": 1.0437079668045044,
15
+ "eval_macro-f1": 0.4250961051798347,
16
+ "eval_macro-precision": 0.4049519842647229,
17
+ "eval_macro-recall": 0.44806754834044743,
18
+ "eval_micro-f1": 0.6246851385390428,
19
+ "eval_micro-precision": 0.6246851385390428,
20
+ "eval_micro-recall": 0.6246851385390428,
21
+ "eval_runtime": 15.1824,
22
+ "eval_samples_per_second": 52.297,
23
+ "eval_steps_per_second": 3.293,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_accuracy": 0.6360201511335013,
29
+ "eval_loss": 1.0257869958877563,
30
+ "eval_macro-f1": 0.36366715571736496,
31
+ "eval_macro-precision": 0.48950953678474113,
32
+ "eval_macro-recall": 0.39682025983719355,
33
+ "eval_micro-f1": 0.6360201511335013,
34
+ "eval_micro-precision": 0.6360201511335013,
35
+ "eval_micro-recall": 0.6360201511335013,
36
+ "eval_runtime": 16.6991,
37
+ "eval_samples_per_second": 47.547,
38
+ "eval_steps_per_second": 2.994,
39
+ "step": 20
40
+ }
41
+ ],
42
+ "logging_steps": 500,
43
+ "max_steps": 40,
44
+ "num_train_epochs": 4,
45
+ "save_steps": 500,
46
+ "total_flos": 0,
47
+ "trial_name": null,
48
+ "trial_params": {
49
+ "learning_rate": 2.056719275757213e-06,
50
+ "num_train_epochs": 4,
51
+ "per_device_train_batch_size": 32,
52
+ "seed": 37
53
+ }
54
+ }
run-1/checkpoint-20/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6979160f04a8c400b011acf29c779deb101dc33edcd8024742710578175447af
3
+ size 4600
run-1/checkpoint-20/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-30/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "id2label": {
12
+ "0": "CAROLL",
13
+ "1": "DICKENS",
14
+ "2": "DOYLE"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "CAROLL": 0,
19
+ "DICKENS": 1,
20
+ "DOYLE": 2
21
+ },
22
+ "max_position_embeddings": 512,
23
+ "model_type": "distilbert",
24
+ "n_heads": 12,
25
+ "n_layers": 6,
26
+ "pad_token_id": 0,
27
+ "problem_type": "single_label_classification",
28
+ "qa_dropout": 0.1,
29
+ "seq_classif_dropout": 0.2,
30
+ "sinusoidal_pos_embds": false,
31
+ "tie_weights_": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.35.2",
34
+ "vocab_size": 30522
35
+ }
run-1/checkpoint-30/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e861f3b9793fb31a3299af6c910005650b035594e999d8793271d5766f98b45c
3
+ size 267835644
run-1/checkpoint-30/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:051ca65887b352784acf17251f3c403b42de79c6589d1cfe1f79b8cf3fd76e6c
3
+ size 535733434
run-1/checkpoint-30/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9878cc06e106d8af3b0a457ab5f5e44a23af3bad2fd48ccb7b8fa4e2dcedf945
3
+ size 14308
run-1/checkpoint-30/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:834be401a78bc491d684f803b658846a703ce8d2e460472bbfa3db0e74ca9ef3
3
+ size 1064
run-1/checkpoint-30/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
+ }
run-1/checkpoint-30/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-30/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": true,
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
+ }
run-1/checkpoint-30/trainer_state.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.0149487257003784,
3
+ "best_model_checkpoint": "DistilBERT-PD_Books/run-1/checkpoint-30",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 30,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.6246851385390428,
14
+ "eval_loss": 1.0437079668045044,
15
+ "eval_macro-f1": 0.4250961051798347,
16
+ "eval_macro-precision": 0.4049519842647229,
17
+ "eval_macro-recall": 0.44806754834044743,
18
+ "eval_micro-f1": 0.6246851385390428,
19
+ "eval_micro-precision": 0.6246851385390428,
20
+ "eval_micro-recall": 0.6246851385390428,
21
+ "eval_runtime": 15.1824,
22
+ "eval_samples_per_second": 52.297,
23
+ "eval_steps_per_second": 3.293,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_accuracy": 0.6360201511335013,
29
+ "eval_loss": 1.0257869958877563,
30
+ "eval_macro-f1": 0.36366715571736496,
31
+ "eval_macro-precision": 0.48950953678474113,
32
+ "eval_macro-recall": 0.39682025983719355,
33
+ "eval_micro-f1": 0.6360201511335013,
34
+ "eval_micro-precision": 0.6360201511335013,
35
+ "eval_micro-recall": 0.6360201511335013,
36
+ "eval_runtime": 16.6991,
37
+ "eval_samples_per_second": 47.547,
38
+ "eval_steps_per_second": 2.994,
39
+ "step": 20
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "eval_accuracy": 0.5994962216624685,
44
+ "eval_loss": 1.0149487257003784,
45
+ "eval_macro-f1": 0.2880622522817352,
46
+ "eval_macro-precision": 0.47855121675155626,
47
+ "eval_macro-recall": 0.35411564387843164,
48
+ "eval_micro-f1": 0.5994962216624685,
49
+ "eval_micro-precision": 0.5994962216624685,
50
+ "eval_micro-recall": 0.5994962216624685,
51
+ "eval_runtime": 15.8836,
52
+ "eval_samples_per_second": 49.989,
53
+ "eval_steps_per_second": 3.148,
54
+ "step": 30
55
+ }
56
+ ],
57
+ "logging_steps": 500,
58
+ "max_steps": 40,
59
+ "num_train_epochs": 4,
60
+ "save_steps": 500,
61
+ "total_flos": 0,
62
+ "trial_name": null,
63
+ "trial_params": {
64
+ "learning_rate": 2.056719275757213e-06,
65
+ "num_train_epochs": 4,
66
+ "per_device_train_batch_size": 32,
67
+ "seed": 37
68
+ }
69
+ }
run-1/checkpoint-30/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6979160f04a8c400b011acf29c779deb101dc33edcd8024742710578175447af
3
+ size 4600
run-1/checkpoint-30/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-40/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "id2label": {
12
+ "0": "CAROLL",
13
+ "1": "DICKENS",
14
+ "2": "DOYLE"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "CAROLL": 0,
19
+ "DICKENS": 1,
20
+ "DOYLE": 2
21
+ },
22
+ "max_position_embeddings": 512,
23
+ "model_type": "distilbert",
24
+ "n_heads": 12,
25
+ "n_layers": 6,
26
+ "pad_token_id": 0,
27
+ "problem_type": "single_label_classification",
28
+ "qa_dropout": 0.1,
29
+ "seq_classif_dropout": 0.2,
30
+ "sinusoidal_pos_embds": false,
31
+ "tie_weights_": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.35.2",
34
+ "vocab_size": 30522
35
+ }
run-1/checkpoint-40/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6594a3acb5c83556b6b4b07c0671cb392f3fb9a62029410a5862da303023fd80
3
+ size 267835644
run-1/checkpoint-40/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:685bd933870ea910231d27235ab4c47dbf248959759710ec58886d51233a40a7
3
+ size 535733434
run-1/checkpoint-40/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5416a35b5b89efbb1d3f602afb2f34293d6d4ef3b470f6de361e68843441b798
3
+ size 14308
run-1/checkpoint-40/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66252c69e737d8f83316524d1c167d493efb75b78f55928b24706156215daff9
3
+ size 1064
run-1/checkpoint-40/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
+ }
run-1/checkpoint-40/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-40/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": true,
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
+ }
run-1/checkpoint-40/trainer_state.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.0113459825515747,
3
+ "best_model_checkpoint": "DistilBERT-PD_Books/run-1/checkpoint-40",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 40,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.6246851385390428,
14
+ "eval_loss": 1.0437079668045044,
15
+ "eval_macro-f1": 0.4250961051798347,
16
+ "eval_macro-precision": 0.4049519842647229,
17
+ "eval_macro-recall": 0.44806754834044743,
18
+ "eval_micro-f1": 0.6246851385390428,
19
+ "eval_micro-precision": 0.6246851385390428,
20
+ "eval_micro-recall": 0.6246851385390428,
21
+ "eval_runtime": 15.1824,
22
+ "eval_samples_per_second": 52.297,
23
+ "eval_steps_per_second": 3.293,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_accuracy": 0.6360201511335013,
29
+ "eval_loss": 1.0257869958877563,
30
+ "eval_macro-f1": 0.36366715571736496,
31
+ "eval_macro-precision": 0.48950953678474113,
32
+ "eval_macro-recall": 0.39682025983719355,
33
+ "eval_micro-f1": 0.6360201511335013,
34
+ "eval_micro-precision": 0.6360201511335013,
35
+ "eval_micro-recall": 0.6360201511335013,
36
+ "eval_runtime": 16.6991,
37
+ "eval_samples_per_second": 47.547,
38
+ "eval_steps_per_second": 2.994,
39
+ "step": 20
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "eval_accuracy": 0.5994962216624685,
44
+ "eval_loss": 1.0149487257003784,
45
+ "eval_macro-f1": 0.2880622522817352,
46
+ "eval_macro-precision": 0.47855121675155626,
47
+ "eval_macro-recall": 0.35411564387843164,
48
+ "eval_micro-f1": 0.5994962216624685,
49
+ "eval_micro-precision": 0.5994962216624685,
50
+ "eval_micro-recall": 0.5994962216624685,
51
+ "eval_runtime": 15.8836,
52
+ "eval_samples_per_second": 49.989,
53
+ "eval_steps_per_second": 3.148,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "eval_accuracy": 0.593198992443325,
59
+ "eval_loss": 1.0113459825515747,
60
+ "eval_macro-f1": 0.2751023655305477,
61
+ "eval_macro-precision": 0.45848595848595847,
62
+ "eval_macro-recall": 0.3473952137709048,
63
+ "eval_micro-f1": 0.593198992443325,
64
+ "eval_micro-precision": 0.593198992443325,
65
+ "eval_micro-recall": 0.593198992443325,
66
+ "eval_runtime": 16.4725,
67
+ "eval_samples_per_second": 48.202,
68
+ "eval_steps_per_second": 3.035,
69
+ "step": 40
70
+ }
71
+ ],
72
+ "logging_steps": 500,
73
+ "max_steps": 40,
74
+ "num_train_epochs": 4,
75
+ "save_steps": 500,
76
+ "total_flos": 0,
77
+ "trial_name": null,
78
+ "trial_params": {
79
+ "learning_rate": 2.056719275757213e-06,
80
+ "num_train_epochs": 4,
81
+ "per_device_train_batch_size": 32,
82
+ "seed": 37
83
+ }
84
+ }
run-1/checkpoint-40/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6979160f04a8c400b011acf29c779deb101dc33edcd8024742710578175447af
3
+ size 4600
run-1/checkpoint-40/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-5/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "id2label": {
12
+ "0": "CAROLL",
13
+ "1": "DICKENS",
14
+ "2": "DOYLE"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "CAROLL": 0,
19
+ "DICKENS": 1,
20
+ "DOYLE": 2
21
+ },
22
+ "max_position_embeddings": 512,
23
+ "model_type": "distilbert",
24
+ "n_heads": 12,
25
+ "n_layers": 6,
26
+ "pad_token_id": 0,
27
+ "problem_type": "single_label_classification",
28
+ "qa_dropout": 0.1,
29
+ "seq_classif_dropout": 0.2,
30
+ "sinusoidal_pos_embds": false,
31
+ "tie_weights_": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.35.2",
34
+ "vocab_size": 30522
35
+ }
run-2/checkpoint-5/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98d9f241fe83935d68f18735b6668d5492714595cc5df686be3ec3dc4b4a974f
3
+ size 267835644
run-2/checkpoint-5/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:552b4c1a1002e85e779e1a51d1a0a99897e3916dfb1bdf05157622ffa60cb673
3
+ size 535733434
run-2/checkpoint-5/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c9a81410d1f152bdd2a33e7526ffa53899795a1da9e1f95160ae799c9791344
3
+ size 14244
run-2/checkpoint-5/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f47ceac44283ffb3b4c4a50804fa1b68cca1f348343917c8be83e3599f79f1b5
3
+ size 1064
run-2/checkpoint-5/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
+ }
run-2/checkpoint-5/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-5/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": true,
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
+ }
run-2/checkpoint-5/trainer_state.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.0914820432662964,
3
+ "best_model_checkpoint": "DistilBERT-PD_Books/run-2/checkpoint-5",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 5,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.4420654911838791,
14
+ "eval_loss": 1.0914820432662964,
15
+ "eval_macro-f1": 0.31642606581662175,
16
+ "eval_macro-precision": 0.2814161330151683,
17
+ "eval_macro-recall": 0.48728680192250434,
18
+ "eval_micro-f1": 0.44206549118387917,
19
+ "eval_micro-precision": 0.4420654911838791,
20
+ "eval_micro-recall": 0.4420654911838791,
21
+ "eval_runtime": 15.4707,
22
+ "eval_samples_per_second": 51.323,
23
+ "eval_steps_per_second": 3.232,
24
+ "step": 5
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 5,
29
+ "num_train_epochs": 1,
30
+ "save_steps": 500,
31
+ "total_flos": 0,
32
+ "trial_name": null,
33
+ "trial_params": {
34
+ "learning_rate": 4.240056951299604e-06,
35
+ "num_train_epochs": 1,
36
+ "per_device_train_batch_size": 64,
37
+ "seed": 40
38
+ }
39
+ }
run-2/checkpoint-5/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00b6b22867f93d7846ca52745a5338d90652270692f2e223ce0a5c07a5f28bdb
3
+ size 4600
run-2/checkpoint-5/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Nov29_01-02-41_37a4be0f03a9/events.out.tfevents.1701220519.37a4be0f03a9.346.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca6d201e6990fde0b8536039d3d291eaa4919b729d59f2eb259cca120cfa8bd8
3
- size 4911
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f97a2ae972612f27f3d3a4bc03f1ca31b13ff3d806f674d5bd809158fa1f962e
3
+ size 7194
runs/Nov29_01-02-41_37a4be0f03a9/events.out.tfevents.1701220660.37a4be0f03a9.346.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87cfa3074b670a25cfa7574bf4a6300546428272bc1f80c7febe9ca50e02586e
3
+ size 5259
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6979160f04a8c400b011acf29c779deb101dc33edcd8024742710578175447af
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00b6b22867f93d7846ca52745a5338d90652270692f2e223ce0a5c07a5f28bdb
3
  size 4600