Hugging Face's logo

Ethan615
/
try

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Metrics Community
Ethan615 commited on
Commit
00259b7
·
1 Parent(s): 0b33137

Training in progress, epoch 2

Browse files
Files changed (25) hide show
  1. model.safetensors +1 -1
  2. run-3/checkpoint-2138/config.json +25 -0
  3. run-3/checkpoint-2138/model.safetensors +3 -0
  4. run-3/checkpoint-2138/optimizer.pt +3 -0
  5. run-3/checkpoint-2138/rng_state.pth +3 -0
  6. run-3/checkpoint-2138/scheduler.pt +3 -0
  7. run-3/checkpoint-2138/special_tokens_map.json +7 -0
  8. run-3/checkpoint-2138/tokenizer.json +0 -0
  9. run-3/checkpoint-2138/tokenizer_config.json +55 -0
  10. run-3/checkpoint-2138/trainer_state.json +59 -0
  11. run-3/checkpoint-2138/training_args.bin +3 -0
  12. run-3/checkpoint-2138/vocab.txt +0 -0
  13. run-3/checkpoint-4276/config.json +25 -0
  14. run-3/checkpoint-4276/model.safetensors +3 -0
  15. run-3/checkpoint-4276/optimizer.pt +3 -0
  16. run-3/checkpoint-4276/rng_state.pth +3 -0
  17. run-3/checkpoint-4276/scheduler.pt +3 -0
  18. run-3/checkpoint-4276/special_tokens_map.json +7 -0
  19. run-3/checkpoint-4276/tokenizer.json +0 -0
  20. run-3/checkpoint-4276/tokenizer_config.json +55 -0
  21. run-3/checkpoint-4276/trainer_state.json +92 -0
  22. run-3/checkpoint-4276/training_args.bin +3 -0
  23. run-3/checkpoint-4276/vocab.txt +0 -0
  24. runs/Dec22_07-12-50_84c4b1f8dc6c/events.out.tfevents.1703230002.84c4b1f8dc6c.518.5 +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 sha256:6cac33cf1f66d6bc87830dd38d64218afdf90251c418d1ef12a8b230da5f1de5
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d07018f8d8711ff007d435c37d6370c998099d5da175275fb842585fb0318b5
3
  size 267832560
run-3/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-3/checkpoint-2138/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80f2c334ed4f1f294a2f916451cea250a4cfa86cd9c6ec539ac77b6e87747ee5
3
+ size 267832560
run-3/checkpoint-2138/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5e39aab0ba5776938cf76f475fbe95fc4816348d471338d1eda66c42a7f697
3
+ size 535727290
run-3/checkpoint-2138/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d076be17692cfa345b0f1981db591dc8bcdd0b29c1b64b0637d37bb7f8ea4265
3
+ size 14244
run-3/checkpoint-2138/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f78ca8dc6a7929f80c42b973d6b726c0c10724f3fabc46b62fb266e16c4fb748
3
+ size 1064
run-3/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-3/checkpoint-2138/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/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-3/checkpoint-2138/trainer_state.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3194134442722084,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/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": 2.109376138070761e-06,
14
+ "loss": 0.5971,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.47,
19
+ "learning_rate": 1.8300625604660523e-06,
20
+ "loss": 0.575,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.7,
25
+ "learning_rate": 1.5507489828613434e-06,
26
+ "loss": 0.5345,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.94,
31
+ "learning_rate": 1.2714354052566345e-06,
32
+ "loss": 0.5352,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.0,
37
+ "eval_loss": 0.5899004936218262,
38
+ "eval_matthews_correlation": 0.3194134442722084,
39
+ "eval_runtime": 0.7491,
40
+ "eval_samples_per_second": 1392.35,
41
+ "eval_steps_per_second": 88.107,
42
+ "step": 2138
43
+ }
44
+ ],
45
+ "logging_steps": 500,
46
+ "max_steps": 4276,
47
+ "num_input_tokens_seen": 0,
48
+ "num_train_epochs": 2,
49
+ "save_steps": 500,
50
+ "total_flos": 32608713001968.0,
51
+ "train_batch_size": 4,
52
+ "trial_name": null,
53
+ "trial_params": {
54
+ "learning_rate": 2.38868971567547e-06,
55
+ "num_train_epochs": 2,
56
+ "per_device_train_batch_size": 4,
57
+ "seed": 28
58
+ }
59
+ }
run-3/checkpoint-2138/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58fae703abd28cb0ab5528ac939f06e8a9578110f6c6558da0b2c2f9c2704502
3
+ size 4792
run-3/checkpoint-2138/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/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-3/checkpoint-4276/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d07018f8d8711ff007d435c37d6370c998099d5da175275fb842585fb0318b5
3
+ size 267832560
run-3/checkpoint-4276/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfa4633d55816cfe6eca7524f8815fa881fc69129cd7c1f7abc6d16346f4722b
3
+ size 535727290
run-3/checkpoint-4276/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86e67acc8c695dd03f71ec0d0b05d2661de64c22350ea274426e0f5c6f15576e
3
+ size 14244
run-3/checkpoint-4276/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3788bef18ab31e49053128984c1d7f892c3b1ad9a0367cbb365fddddc8b3336b
3
+ size 1064
run-3/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-3/checkpoint-4276/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/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-3/checkpoint-4276/trainer_state.json ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4174403779614697,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-4276",
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": 2.109376138070761e-06,
14
+ "loss": 0.5971,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.47,
19
+ "learning_rate": 1.8300625604660523e-06,
20
+ "loss": 0.575,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.7,
25
+ "learning_rate": 1.5507489828613434e-06,
26
+ "loss": 0.5345,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.94,
31
+ "learning_rate": 1.2714354052566345e-06,
32
+ "loss": 0.5352,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.0,
37
+ "eval_loss": 0.5899004936218262,
38
+ "eval_matthews_correlation": 0.3194134442722084,
39
+ "eval_runtime": 0.7491,
40
+ "eval_samples_per_second": 1392.35,
41
+ "eval_steps_per_second": 88.107,
42
+ "step": 2138
43
+ },
44
+ {
45
+ "epoch": 1.17,
46
+ "learning_rate": 9.921218276519258e-07,
47
+ "loss": 0.4939,
48
+ "step": 2500
49
+ },
50
+ {
51
+ "epoch": 1.4,
52
+ "learning_rate": 7.128082500472169e-07,
53
+ "loss": 0.4899,
54
+ "step": 3000
55
+ },
56
+ {
57
+ "epoch": 1.64,
58
+ "learning_rate": 4.3349467244250807e-07,
59
+ "loss": 0.4685,
60
+ "step": 3500
61
+ },
62
+ {
63
+ "epoch": 1.87,
64
+ "learning_rate": 1.5418109483779928e-07,
65
+ "loss": 0.4906,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 2.0,
70
+ "eval_loss": 0.5730822682380676,
71
+ "eval_matthews_correlation": 0.4174403779614697,
72
+ "eval_runtime": 0.7482,
73
+ "eval_samples_per_second": 1394.024,
74
+ "eval_steps_per_second": 88.212,
75
+ "step": 4276
76
+ }
77
+ ],
78
+ "logging_steps": 500,
79
+ "max_steps": 4276,
80
+ "num_input_tokens_seen": 0,
81
+ "num_train_epochs": 2,
82
+ "save_steps": 500,
83
+ "total_flos": 65347823599488.0,
84
+ "train_batch_size": 4,
85
+ "trial_name": null,
86
+ "trial_params": {
87
+ "learning_rate": 2.38868971567547e-06,
88
+ "num_train_epochs": 2,
89
+ "per_device_train_batch_size": 4,
90
+ "seed": 28
91
+ }
92
+ }
run-3/checkpoint-4276/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58fae703abd28cb0ab5528ac939f06e8a9578110f6c6558da0b2c2f9c2704502
3
+ size 4792
run-3/checkpoint-4276/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec22_07-12-50_84c4b1f8dc6c/events.out.tfevents.1703230002.84c4b1f8dc6c.518.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa6ccc86e31623587f7430b103fc16505904003c2ab226ea5a41c2cdcb21702d
3
+ size 6619
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d422aeda2732c1b38205a36cc73dce73117c13e544bca80029f20a7b3098544a
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58fae703abd28cb0ab5528ac939f06e8a9578110f6c6558da0b2c2f9c2704502
3
  size 4792