Hugging Face's logo

Yihsiu
/
hw-01

Text Generation
Transformers
TensorBoard
Safetensors
llama
Generated from Trainer
trl
sft
conversational
text-generation-inference
Inference Endpoints
8-bit precision
bitsandbytes
Model card Files Metrics Community
Yihsiu commited on
Commit
eb8ec8a
·
1 Parent(s): b70ddc6

Training in progress, epoch 1

Browse files
Files changed (41) hide show
  1. model.safetensors +1 -1
  2. run-4/checkpoint-4276/config.json +25 -0
  3. run-4/checkpoint-4276/model.safetensors +3 -0
  4. run-4/checkpoint-4276/optimizer.pt +3 -0
  5. run-4/checkpoint-4276/rng_state.pth +3 -0
  6. run-4/checkpoint-4276/scheduler.pt +3 -0
  7. run-4/checkpoint-4276/special_tokens_map.json +7 -0
  8. run-4/checkpoint-4276/tokenizer.json +0 -0
  9. run-4/checkpoint-4276/tokenizer_config.json +55 -0
  10. run-4/checkpoint-4276/trainer_state.json +92 -0
  11. run-4/checkpoint-4276/training_args.bin +3 -0
  12. run-4/checkpoint-4276/vocab.txt +0 -0
  13. run-8/checkpoint-2138/config.json +25 -0
  14. run-8/checkpoint-2138/model.safetensors +3 -0
  15. run-8/checkpoint-2138/optimizer.pt +3 -0
  16. run-8/checkpoint-2138/rng_state.pth +3 -0
  17. run-8/checkpoint-2138/scheduler.pt +3 -0
  18. run-8/checkpoint-2138/special_tokens_map.json +7 -0
  19. run-8/checkpoint-2138/tokenizer.json +0 -0
  20. run-8/checkpoint-2138/tokenizer_config.json +55 -0
  21. run-8/checkpoint-2138/trainer_state.json +59 -0
  22. run-8/checkpoint-2138/training_args.bin +3 -0
  23. run-8/checkpoint-2138/vocab.txt +0 -0
  24. run-9/checkpoint-268/config.json +25 -0
  25. run-9/checkpoint-268/model.safetensors +3 -0
  26. run-9/checkpoint-268/optimizer.pt +3 -0
  27. run-9/checkpoint-268/rng_state.pth +3 -0
  28. run-9/checkpoint-268/scheduler.pt +3 -0
  29. run-9/checkpoint-268/special_tokens_map.json +7 -0
  30. run-9/checkpoint-268/tokenizer.json +0 -0
  31. run-9/checkpoint-268/tokenizer_config.json +55 -0
  32. run-9/checkpoint-268/trainer_state.json +35 -0
  33. run-9/checkpoint-268/training_args.bin +3 -0
  34. run-9/checkpoint-268/vocab.txt +0 -0
  35. runs/Dec23_02-07-05_42b18358a534/events.out.tfevents.1703298865.42b18358a534.403.6 +2 -2
  36. runs/Dec23_02-07-05_42b18358a534/events.out.tfevents.1703299135.42b18358a534.403.7 +3 -0
  37. runs/Dec23_02-07-05_42b18358a534/events.out.tfevents.1703299234.42b18358a534.403.8 +3 -0
  38. runs/Dec23_02-07-05_42b18358a534/events.out.tfevents.1703299256.42b18358a534.403.9 +3 -0
  39. runs/Dec23_02-07-05_42b18358a534/events.out.tfevents.1703299306.42b18358a534.403.10 +3 -0
  40. runs/Dec23_02-07-05_42b18358a534/events.out.tfevents.1703299460.42b18358a534.403.11 +3 -0
  41. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:816fc21de83b79d724852cb4293f1295d3a8997517ca87d89218d6a82c33d454
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e751e500ef4facc9a2ff8cb8866b7ddbc9c4153bac41aaf2e9e8891d1b708736
3
  size 267832560
run-4/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-4/checkpoint-4276/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:feb9bdd5a7f4e6fdb7d2f9e0382e5912da999dc89420cc91b2f464d53fb54e6f
3
+ size 267832560
run-4/checkpoint-4276/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:509ebf6debe3abb1e32a9d32391ee752c58e3788e4e682cec29570e18e9e3ab6
3
+ size 535727290
run-4/checkpoint-4276/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f48499f343d9f47fec47b3a3efdd0d4cffdef9ea33650063c93199887fdf4c53
3
+ size 14308
run-4/checkpoint-4276/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da1c3e633749fa3826f25a26e3e87ecaebb21e6589bed428ef8fd4e6e2d7f2bb
3
+ size 1064
run-4/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-4/checkpoint-4276/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/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-4/checkpoint-4276/trainer_state.json ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "hw-01-finetuned-cola/run-4/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": 6.743225819833664e-05,
14
+ "loss": 0.6241,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.47,
19
+ "learning_rate": 5.850319858520944e-05,
20
+ "loss": 0.6246,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.7,
25
+ "learning_rate": 4.957413897208223e-05,
26
+ "loss": 0.6043,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.94,
31
+ "learning_rate": 4.0645079358955023e-05,
32
+ "loss": 0.6273,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.0,
37
+ "eval_loss": 0.6193726062774658,
38
+ "eval_matthews_correlation": 0.0,
39
+ "eval_runtime": 0.7486,
40
+ "eval_samples_per_second": 1393.202,
41
+ "eval_steps_per_second": 88.16,
42
+ "step": 2138
43
+ },
44
+ {
45
+ "epoch": 1.17,
46
+ "learning_rate": 3.171601974582783e-05,
47
+ "loss": 0.6217,
48
+ "step": 2500
49
+ },
50
+ {
51
+ "epoch": 1.4,
52
+ "learning_rate": 2.278696013270062e-05,
53
+ "loss": 0.619,
54
+ "step": 3000
55
+ },
56
+ {
57
+ "epoch": 1.64,
58
+ "learning_rate": 1.3857900519573418e-05,
59
+ "loss": 0.608,
60
+ "step": 3500
61
+ },
62
+ {
63
+ "epoch": 1.87,
64
+ "learning_rate": 4.928840906446216e-06,
65
+ "loss": 0.6039,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 2.0,
70
+ "eval_loss": 0.6199201941490173,
71
+ "eval_matthews_correlation": 0.0,
72
+ "eval_runtime": 0.7351,
73
+ "eval_samples_per_second": 1418.93,
74
+ "eval_steps_per_second": 89.788,
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": 65246403247392.0,
84
+ "train_batch_size": 4,
85
+ "trial_name": null,
86
+ "trial_params": {
87
+ "learning_rate": 7.636131781146384e-05,
88
+ "num_train_epochs": 2,
89
+ "per_device_train_batch_size": 4,
90
+ "seed": 33
91
+ }
92
+ }
run-4/checkpoint-4276/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ee357e41690d89a0afb5eaa03cca4783909127dc28f909367b040c73e17674b
3
+ size 4728
run-4/checkpoint-4276/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-8/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-8/checkpoint-2138/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cba5c257dda4e5b1d384dcc11946f8d4fac672b50b40cfb04fc8349a06bf840f
3
+ size 267832560
run-8/checkpoint-2138/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:852d48c57b21dd221c796c15901a8d6ab4ca81ad65530308e645c01b255b97a6
3
+ size 535727290
run-8/checkpoint-2138/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a1d34d8c66debf8d31f2b8edc92db8048a10207e2dc6a5cfef15845cb45e1e3
3
+ size 14244
run-8/checkpoint-2138/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6bfea906ebbba7165e905a600317d2f5c7188400d293225bfaf20f7ff43f181
3
+ size 1064
run-8/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-8/checkpoint-2138/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/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-8/checkpoint-2138/trainer_state.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4614924196768819,
3
+ "best_model_checkpoint": "hw-01-finetuned-cola/run-8/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": 1.0132397761685032e-05,
14
+ "loss": 0.5643,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.47,
19
+ "learning_rate": 7.039480252013165e-06,
20
+ "loss": 0.56,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.7,
25
+ "learning_rate": 3.946562742341299e-06,
26
+ "loss": 0.5342,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.94,
31
+ "learning_rate": 8.536452326694348e-07,
32
+ "loss": 0.5185,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.0,
37
+ "eval_loss": 0.5394960045814514,
38
+ "eval_matthews_correlation": 0.4614924196768819,
39
+ "eval_runtime": 0.7515,
40
+ "eval_samples_per_second": 1387.911,
41
+ "eval_steps_per_second": 87.826,
42
+ "step": 2138
43
+ }
44
+ ],
45
+ "logging_steps": 500,
46
+ "max_steps": 2138,
47
+ "num_input_tokens_seen": 0,
48
+ "num_train_epochs": 1,
49
+ "save_steps": 500,
50
+ "total_flos": 35113692208584.0,
51
+ "train_batch_size": 4,
52
+ "trial_name": null,
53
+ "trial_params": {
54
+ "learning_rate": 1.3225315271356896e-05,
55
+ "num_train_epochs": 1,
56
+ "per_device_train_batch_size": 4,
57
+ "seed": 27
58
+ }
59
+ }
run-8/checkpoint-2138/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e099eb0b32b9af467fe8ab940f0392687ba3dfe1da130031b712568774aa7903
3
+ size 4728
run-8/checkpoint-2138/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-268/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-9/checkpoint-268/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e751e500ef4facc9a2ff8cb8866b7ddbc9c4153bac41aaf2e9e8891d1b708736
3
+ size 267832560
run-9/checkpoint-268/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a37c8464259a5a2977c54a6f849d7483383aa45003380d16d359737683938d4
3
+ size 535727290
run-9/checkpoint-268/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f3c6f33738840ae66d602ec44a31805c3c1244f220af1ccc8bbf30e6d301f82
3
+ size 14244
run-9/checkpoint-268/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cff16e74da8a654561909af5d2bb193c726e0ac32e6926922639fcf4eac27bd0
3
+ size 1064
run-9/checkpoint-268/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-9/checkpoint-268/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-268/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-9/checkpoint-268/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5078785333305506,
3
+ "best_model_checkpoint": "hw-01-finetuned-cola/run-9/checkpoint-268",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 268,
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": 0.47135576605796814,
14
+ "eval_matthews_correlation": 0.5078785333305506,
15
+ "eval_runtime": 0.755,
16
+ "eval_samples_per_second": 1381.448,
17
+ "eval_steps_per_second": 87.417,
18
+ "step": 268
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 536,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 2,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 32,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 2.1896399004105606e-05,
31
+ "num_train_epochs": 2,
32
+ "per_device_train_batch_size": 32,
33
+ "seed": 6
34
+ }
35
+ }
run-9/checkpoint-268/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be9d30924877c0415d0249046f79f42247a71e60666073775a01bb0a74541de4
3
+ size 4728
run-9/checkpoint-268/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec23_02-07-05_42b18358a534/events.out.tfevents.1703298865.42b18358a534.403.6 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee83bb6bfcbbda65e789b4497050adc86704898180293821d7681498bfa83148
3
- size 5720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a9eeba57a1fa1d4f1c765be236f635e071168f1eeef68a6dc1bfdafcb5d3833
3
+ size 6566
runs/Dec23_02-07-05_42b18358a534/events.out.tfevents.1703299135.42b18358a534.403.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ba7e50fd0fea0b8e71b22e97f6a94e118abe934d7cf354dea427b022278e3e7
3
+ size 5249
runs/Dec23_02-07-05_42b18358a534/events.out.tfevents.1703299234.42b18358a534.403.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e191b2af1fb30ee5d3c42e6c7331044ff3dcf05cb178745bce0f27c2528dfc8b
3
+ size 4622
runs/Dec23_02-07-05_42b18358a534/events.out.tfevents.1703299256.42b18358a534.403.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4d304e0605a8cc830bc32dcb2c77f194ebb251dc7d1f56db1a3758697018f23
3
+ size 4935
runs/Dec23_02-07-05_42b18358a534/events.out.tfevents.1703299306.42b18358a534.403.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa8d213082a2bde9832492f413303377a1e3f077c6a296d4a9a1161b9c6b530e
3
+ size 5604
runs/Dec23_02-07-05_42b18358a534/events.out.tfevents.1703299460.42b18358a534.403.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c743c31a6619a15f7492d6c48cee8c37586ba4a4b1a84aa78d418eba10c7661a
3
+ size 5468
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ee357e41690d89a0afb5eaa03cca4783909127dc28f909367b040c73e17674b
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be9d30924877c0415d0249046f79f42247a71e60666073775a01bb0a74541de4
3
  size 4728