Hugging Face's logo

flyingswan3000
/
HW01

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
flyingswan3000 commited on
Commit
81ff745
·
1 Parent(s): 2ac8c9c

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. model.safetensors +1 -1
  2. run-4/checkpoint-1070/config.json +25 -0
  3. run-4/checkpoint-1070/model.safetensors +3 -0
  4. run-4/checkpoint-1070/optimizer.pt +3 -0
  5. run-4/checkpoint-1070/rng_state.pth +3 -0
  6. run-4/checkpoint-1070/scheduler.pt +3 -0
  7. run-4/checkpoint-1070/special_tokens_map.json +7 -0
  8. run-4/checkpoint-1070/tokenizer.json +0 -0
  9. run-4/checkpoint-1070/tokenizer_config.json +55 -0
  10. run-4/checkpoint-1070/trainer_state.json +56 -0
  11. run-4/checkpoint-1070/training_args.bin +3 -0
  12. run-4/checkpoint-1070/vocab.txt +0 -0
  13. run-4/checkpoint-1605/config.json +25 -0
  14. run-4/checkpoint-1605/model.safetensors +3 -0
  15. run-4/checkpoint-1605/optimizer.pt +3 -0
  16. run-4/checkpoint-1605/rng_state.pth +3 -0
  17. run-4/checkpoint-1605/scheduler.pt +3 -0
  18. run-4/checkpoint-1605/special_tokens_map.json +7 -0
  19. run-4/checkpoint-1605/tokenizer.json +0 -0
  20. run-4/checkpoint-1605/tokenizer_config.json +55 -0
  21. run-4/checkpoint-1605/trainer_state.json +71 -0
  22. run-4/checkpoint-1605/training_args.bin +3 -0
  23. run-4/checkpoint-1605/vocab.txt +0 -0
  24. run-6/checkpoint-134/config.json +25 -0
  25. run-6/checkpoint-134/model.safetensors +3 -0
  26. run-6/checkpoint-134/optimizer.pt +3 -0
  27. run-6/checkpoint-134/rng_state.pth +3 -0
  28. run-6/checkpoint-134/scheduler.pt +3 -0
  29. run-6/checkpoint-134/special_tokens_map.json +7 -0
  30. run-6/checkpoint-134/tokenizer.json +0 -0
  31. run-6/checkpoint-134/tokenizer_config.json +55 -0
  32. run-6/checkpoint-134/trainer_state.json +35 -0
  33. run-6/checkpoint-134/training_args.bin +3 -0
  34. run-6/checkpoint-134/vocab.txt +0 -0
  35. runs/Dec23_02-10-25_786cd877caf6/events.out.tfevents.1703298817.786cd877caf6.1133.7 +3 -0
  36. runs/Dec23_02-10-25_786cd877caf6/events.out.tfevents.1703298840.786cd877caf6.1133.8 +3 -0
  37. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bbf740ab6a03e4c605f40b439e92c140421640587af55dca187ff604838c7a9
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31d7b9569e1812a35365a6f1e06e72d9c90ab391e407fa76863959efda212512
3
  size 267832560
run-4/checkpoint-1070/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-4/checkpoint-1070/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58b712a45039b355f295cba5d4c1e4d5f6ce8534d1145804fbebcf771c4c7f2d
3
+ size 267832560
run-4/checkpoint-1070/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2818d25b0a6435401a0ff12ad724d7b6ab87a571ee9e947552df9373528219c9
3
+ size 535727290
run-4/checkpoint-1070/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:735953fa6cd11e734791dd5c81df81ae523716b7a8b84ab1913e5a1d4b7503d1
3
+ size 14308
run-4/checkpoint-1070/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ebd44d1fa5aaf014506d13de0595b121b808f119bd4e39c3137cdf835d90533
3
+ size 1064
run-4/checkpoint-1070/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-4/checkpoint-1070/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-1070/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-4/checkpoint-1070/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.39164945782890503,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola-hw01/run-4/checkpoint-1070",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1070,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.93,
13
+ "learning_rate": 3.15241497319162e-06,
14
+ "loss": 0.5747,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_loss": 0.5329746603965759,
20
+ "eval_matthews_correlation": 0.35188947328821835,
21
+ "eval_runtime": 0.7836,
22
+ "eval_samples_per_second": 1331.039,
23
+ "eval_steps_per_second": 84.227,
24
+ "step": 535
25
+ },
26
+ {
27
+ "epoch": 1.87,
28
+ "learning_rate": 1.7259828586252763e-06,
29
+ "loss": 0.4857,
30
+ "step": 1000
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_loss": 0.5231956839561462,
35
+ "eval_matthews_correlation": 0.39164945782890503,
36
+ "eval_runtime": 0.8685,
37
+ "eval_samples_per_second": 1200.886,
38
+ "eval_steps_per_second": 75.991,
39
+ "step": 1070
40
+ }
41
+ ],
42
+ "logging_steps": 500,
43
+ "max_steps": 1605,
44
+ "num_input_tokens_seen": 0,
45
+ "num_train_epochs": 3,
46
+ "save_steps": 500,
47
+ "total_flos": 85414564692768.0,
48
+ "train_batch_size": 16,
49
+ "trial_name": null,
50
+ "trial_params": {
51
+ "learning_rate": 4.578847087757964e-06,
52
+ "num_train_epochs": 3,
53
+ "per_device_train_batch_size": 16,
54
+ "seed": 33
55
+ }
56
+ }
run-4/checkpoint-1070/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b665387d26d417cb642ca9b275e154ce9b15d307b3961a8743c1dc43efa7e91
3
+ size 4792
run-4/checkpoint-1070/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-1605/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-4/checkpoint-1605/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57c7c6ed28439d870bdbca224030c03f28ff7a8f5e1f9766abbc169e7ff54f19
3
+ size 267832560
run-4/checkpoint-1605/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba0e34e4040fc92754e4d7fd159beb2665cd49090bdc974e3a788f530587cc4c
3
+ size 535727290
run-4/checkpoint-1605/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91a91f1a98bda2b082e23bdcd79fbd560eefc1ce2dee625d84366005a52e9ec8
3
+ size 14308
run-4/checkpoint-1605/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b483da75bac2e1686b423d1b27da5b1dece0c9d669842205d41171cdb32e6326
3
+ size 1064
run-4/checkpoint-1605/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-4/checkpoint-1605/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-1605/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-4/checkpoint-1605/trainer_state.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4197669868187074,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola-hw01/run-4/checkpoint-1605",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1605,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.93,
13
+ "learning_rate": 3.15241497319162e-06,
14
+ "loss": 0.5747,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_loss": 0.5329746603965759,
20
+ "eval_matthews_correlation": 0.35188947328821835,
21
+ "eval_runtime": 0.7836,
22
+ "eval_samples_per_second": 1331.039,
23
+ "eval_steps_per_second": 84.227,
24
+ "step": 535
25
+ },
26
+ {
27
+ "epoch": 1.87,
28
+ "learning_rate": 1.7259828586252763e-06,
29
+ "loss": 0.4857,
30
+ "step": 1000
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_loss": 0.5231956839561462,
35
+ "eval_matthews_correlation": 0.39164945782890503,
36
+ "eval_runtime": 0.8685,
37
+ "eval_samples_per_second": 1200.886,
38
+ "eval_steps_per_second": 75.991,
39
+ "step": 1070
40
+ },
41
+ {
42
+ "epoch": 2.8,
43
+ "learning_rate": 2.995507440589322e-07,
44
+ "loss": 0.4328,
45
+ "step": 1500
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_loss": 0.5138571858406067,
50
+ "eval_matthews_correlation": 0.4197669868187074,
51
+ "eval_runtime": 0.8469,
52
+ "eval_samples_per_second": 1231.48,
53
+ "eval_steps_per_second": 77.927,
54
+ "step": 1605
55
+ }
56
+ ],
57
+ "logging_steps": 500,
58
+ "max_steps": 1605,
59
+ "num_input_tokens_seen": 0,
60
+ "num_train_epochs": 3,
61
+ "save_steps": 500,
62
+ "total_flos": 128609026944756.0,
63
+ "train_batch_size": 16,
64
+ "trial_name": null,
65
+ "trial_params": {
66
+ "learning_rate": 4.578847087757964e-06,
67
+ "num_train_epochs": 3,
68
+ "per_device_train_batch_size": 16,
69
+ "seed": 33
70
+ }
71
+ }
run-4/checkpoint-1605/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b665387d26d417cb642ca9b275e154ce9b15d307b3961a8743c1dc43efa7e91
3
+ size 4792
run-4/checkpoint-1605/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-134/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-6/checkpoint-134/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31d7b9569e1812a35365a6f1e06e72d9c90ab391e407fa76863959efda212512
3
+ size 267832560
run-6/checkpoint-134/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:976b0e55e4c2e37d2c58e85fcba6805ebda83fa6d5cc0db09b9dc8983dfaa1be
3
+ size 535727290
run-6/checkpoint-134/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67de1495d89bad1bf433ea074faeed5cad69203839c69144ec9b9dd8e5891ce0
3
+ size 14244
run-6/checkpoint-134/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7f58550926466fc472f81577d903e093c831f0587d51a0bab98942a31135fa2
3
+ size 1064
run-6/checkpoint-134/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-6/checkpoint-134/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-134/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-6/checkpoint-134/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.42688451387061943,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola-hw01/run-6/checkpoint-134",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 134,
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_loss": 0.4709751605987549,
14
+ "eval_matthews_correlation": 0.42688451387061943,
15
+ "eval_runtime": 1.0375,
16
+ "eval_samples_per_second": 1005.269,
17
+ "eval_steps_per_second": 63.612,
18
+ "step": 134
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 402,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 3,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 64,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 5.0568164357979843e-05,
31
+ "num_train_epochs": 3,
32
+ "per_device_train_batch_size": 64,
33
+ "seed": 16
34
+ }
35
+ }
run-6/checkpoint-134/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:349eb54dfb356b807b426134ae60f49a653b5a3e87b92d9c01d994d673f65149
3
+ size 4792
run-6/checkpoint-134/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec23_02-10-25_786cd877caf6/events.out.tfevents.1703298817.786cd877caf6.1133.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:445ea1fb144b727982df66c693718ec6760762507d98d8728f11ecfd626e531b
3
+ size 4699
runs/Dec23_02-10-25_786cd877caf6/events.out.tfevents.1703298840.786cd877caf6.1133.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f114c296374d408bcb11840d2530aba76753723c6ed0fabc7c71ace13cb121ef
3
+ size 5723
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b665387d26d417cb642ca9b275e154ce9b15d307b3961a8743c1dc43efa7e91
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:349eb54dfb356b807b426134ae60f49a653b5a3e87b92d9c01d994d673f65149
3
  size 4792