Hugging Face's logo

RavingRabbit
/
eformConsult

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Metrics Community
RavingRabbit commited on
Commit
5ac0c01
·
1 Parent(s): 1bdde1b

Training in progress, epoch 3

Browse files
Files changed (25) hide show
  1. model.safetensors +1 -1
  2. run-2/checkpoint-2138/config.json +25 -0
  3. run-2/checkpoint-2138/model.safetensors +3 -0
  4. run-2/checkpoint-2138/optimizer.pt +3 -0
  5. run-2/checkpoint-2138/rng_state.pth +3 -0
  6. run-2/checkpoint-2138/scheduler.pt +3 -0
  7. run-2/checkpoint-2138/special_tokens_map.json +7 -0
  8. run-2/checkpoint-2138/tokenizer.json +0 -0
  9. run-2/checkpoint-2138/tokenizer_config.json +55 -0
  10. run-2/checkpoint-2138/trainer_state.json +59 -0
  11. run-2/checkpoint-2138/training_args.bin +3 -0
  12. run-2/checkpoint-2138/vocab.txt +0 -0
  13. run-2/checkpoint-4276/config.json +25 -0
  14. run-2/checkpoint-4276/model.safetensors +3 -0
  15. run-2/checkpoint-4276/optimizer.pt +3 -0
  16. run-2/checkpoint-4276/rng_state.pth +3 -0
  17. run-2/checkpoint-4276/scheduler.pt +3 -0
  18. run-2/checkpoint-4276/special_tokens_map.json +7 -0
  19. run-2/checkpoint-4276/tokenizer.json +0 -0
  20. run-2/checkpoint-4276/tokenizer_config.json +55 -0
  21. run-2/checkpoint-4276/trainer_state.json +92 -0
  22. run-2/checkpoint-4276/training_args.bin +3 -0
  23. run-2/checkpoint-4276/vocab.txt +0 -0
  24. runs/Dec23_02-11-24_38c624d3e13b/events.out.tfevents.1703299364.38c624d3e13b.382.4 +3 -0
  25. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2c92881e353adce583369c730349621aafed388f473a2721a35d5ad5fb6bee2
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:808e0a246341a493e48c2982ca451e81f4531e05f3428ac49e8a2f00794fbdf9
3
  size 267832560
run-2/checkpoint-2138/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": "4.36.2",
24
+ "vocab_size": 30522
25
+ }
run-2/checkpoint-2138/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7322180f7242cff4edcaebe628d9084262ade51eecd3e3c78a4047f70378f65d
3
+ size 267832560
run-2/checkpoint-2138/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85f419d1f5fc93091e9600b6ab0336f393ae45b33008890c56cef5a0f16d30b7
3
+ size 535727290
run-2/checkpoint-2138/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16d397e91a8e27617cdc21beb7fc232f075b50df3e73f064c98f0b19870d0bd7
3
+ size 14308
run-2/checkpoint-2138/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3817bb4ed2051ff57b6b4fad9ed6de1e031c326af437005dc0047f61b9c64d91
3
+ size 1064
run-2/checkpoint-2138/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-2138/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-2138/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-2138/trainer_state.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-2138",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2138,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.23,
13
+ "learning_rate": 6.673421496233018e-05,
14
+ "loss": 0.6049,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.47,
19
+ "learning_rate": 6.259026222000962e-05,
20
+ "loss": 0.6341,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.7,
25
+ "learning_rate": 5.844630947768907e-05,
26
+ "loss": 0.6276,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.94,
31
+ "learning_rate": 5.4302356735368516e-05,
32
+ "loss": 0.614,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.0,
37
+ "eval_loss": 0.619145393371582,
38
+ "eval_matthews_correlation": 0.0,
39
+ "eval_runtime": 0.7293,
40
+ "eval_samples_per_second": 1430.082,
41
+ "eval_steps_per_second": 90.494,
42
+ "step": 2138
43
+ }
44
+ ],
45
+ "logging_steps": 500,
46
+ "max_steps": 8552,
47
+ "num_input_tokens_seen": 0,
48
+ "num_train_epochs": 4,
49
+ "save_steps": 500,
50
+ "total_flos": 32649074162496.0,
51
+ "train_batch_size": 4,
52
+ "trial_name": null,
53
+ "trial_params": {
54
+ "learning_rate": 7.087816770465073e-05,
55
+ "num_train_epochs": 4,
56
+ "per_device_train_batch_size": 4,
57
+ "seed": 26
58
+ }
59
+ }
run-2/checkpoint-2138/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:229096f3c02d1f39e318a3c8267e4a335369e6543c5689f448d17d69600fc193
3
+ size 4792
run-2/checkpoint-2138/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-4276/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": "4.36.2",
24
+ "vocab_size": 30522
25
+ }
run-2/checkpoint-4276/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbf1ae9f95a524ddeae95effb3b0b79de7266d64d60d9a4ca9966f10dcdc2d03
3
+ size 267832560
run-2/checkpoint-4276/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b9aa091d09dcb304fdc009fcc9dcb3649285fc0f65e2bc5f90764f5466b83f7
3
+ size 535727290
run-2/checkpoint-4276/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a671fb0f280894a47ad3fa3f40448e902a5016ade3b8ae8c284c6f3a658d2b0
3
+ size 14308
run-2/checkpoint-4276/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db060b890a27c8f7bd1e146b036857ac0ea503e49e2473bba56a49e585bb1627
3
+ size 1064
run-2/checkpoint-4276/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-4276/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-4276/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-4276/trainer_state.json ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-2138",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4276,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.23,
13
+ "learning_rate": 6.673421496233018e-05,
14
+ "loss": 0.6049,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.47,
19
+ "learning_rate": 6.259026222000962e-05,
20
+ "loss": 0.6341,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.7,
25
+ "learning_rate": 5.844630947768907e-05,
26
+ "loss": 0.6276,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.94,
31
+ "learning_rate": 5.4302356735368516e-05,
32
+ "loss": 0.614,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.0,
37
+ "eval_loss": 0.619145393371582,
38
+ "eval_matthews_correlation": 0.0,
39
+ "eval_runtime": 0.7293,
40
+ "eval_samples_per_second": 1430.082,
41
+ "eval_steps_per_second": 90.494,
42
+ "step": 2138
43
+ },
44
+ {
45
+ "epoch": 1.17,
46
+ "learning_rate": 5.015840399304796e-05,
47
+ "loss": 0.6223,
48
+ "step": 2500
49
+ },
50
+ {
51
+ "epoch": 1.4,
52
+ "learning_rate": 4.601445125072741e-05,
53
+ "loss": 0.6101,
54
+ "step": 3000
55
+ },
56
+ {
57
+ "epoch": 1.64,
58
+ "learning_rate": 4.187049850840686e-05,
59
+ "loss": 0.6246,
60
+ "step": 3500
61
+ },
62
+ {
63
+ "epoch": 1.87,
64
+ "learning_rate": 3.7726545766086306e-05,
65
+ "loss": 0.603,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 2.0,
70
+ "eval_loss": 0.6236200332641602,
71
+ "eval_matthews_correlation": 0.0,
72
+ "eval_runtime": 0.7355,
73
+ "eval_samples_per_second": 1418.007,
74
+ "eval_steps_per_second": 89.73,
75
+ "step": 4276
76
+ }
77
+ ],
78
+ "logging_steps": 500,
79
+ "max_steps": 8552,
80
+ "num_input_tokens_seen": 0,
81
+ "num_train_epochs": 4,
82
+ "save_steps": 500,
83
+ "total_flos": 65202419931432.0,
84
+ "train_batch_size": 4,
85
+ "trial_name": null,
86
+ "trial_params": {
87
+ "learning_rate": 7.087816770465073e-05,
88
+ "num_train_epochs": 4,
89
+ "per_device_train_batch_size": 4,
90
+ "seed": 26
91
+ }
92
+ }
run-2/checkpoint-4276/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:229096f3c02d1f39e318a3c8267e4a335369e6543c5689f448d17d69600fc193
3
+ size 4792
run-2/checkpoint-4276/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec23_02-11-24_38c624d3e13b/events.out.tfevents.1703299364.38c624d3e13b.382.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a7bb4cf11262487b9290e25bcd7ef950208b415f9c88f91813b7b627da52b76
3
+ size 7556
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f0c50ea7fa32747038fcc8eacd8e23a4a64c7c127a347db2073e7058baef7a9
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:229096f3c02d1f39e318a3c8267e4a335369e6543c5689f448d17d69600fc193
3
  size 4792