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
f8ec79e
·
1 Parent(s): 4ce588e

Training in progress, epoch 2

Browse files
Files changed (37) hide show
  1. model.safetensors +1 -1
  2. run-0/checkpoint-268/config.json +25 -0
  3. run-0/checkpoint-268/model.safetensors +3 -0
  4. run-0/checkpoint-268/optimizer.pt +3 -0
  5. run-0/checkpoint-268/rng_state.pth +3 -0
  6. run-0/checkpoint-268/scheduler.pt +3 -0
  7. run-0/checkpoint-268/special_tokens_map.json +7 -0
  8. run-0/checkpoint-268/tokenizer.json +0 -0
  9. run-0/checkpoint-268/tokenizer_config.json +55 -0
  10. run-0/checkpoint-268/trainer_state.json +44 -0
  11. run-0/checkpoint-268/training_args.bin +3 -0
  12. run-0/checkpoint-268/vocab.txt +0 -0
  13. run-1/checkpoint-1069/config.json +25 -0
  14. run-1/checkpoint-1069/model.safetensors +3 -0
  15. run-1/checkpoint-1069/optimizer.pt +3 -0
  16. run-1/checkpoint-1069/rng_state.pth +3 -0
  17. run-1/checkpoint-1069/scheduler.pt +3 -0
  18. run-1/checkpoint-1069/special_tokens_map.json +7 -0
  19. run-1/checkpoint-1069/tokenizer.json +0 -0
  20. run-1/checkpoint-1069/tokenizer_config.json +55 -0
  21. run-1/checkpoint-1069/trainer_state.json +47 -0
  22. run-1/checkpoint-1069/training_args.bin +3 -0
  23. run-1/checkpoint-1069/vocab.txt +0 -0
  24. run-1/checkpoint-2138/config.json +25 -0
  25. run-1/checkpoint-2138/model.safetensors +3 -0
  26. run-1/checkpoint-2138/optimizer.pt +3 -0
  27. run-1/checkpoint-2138/rng_state.pth +3 -0
  28. run-1/checkpoint-2138/scheduler.pt +3 -0
  29. run-1/checkpoint-2138/special_tokens_map.json +7 -0
  30. run-1/checkpoint-2138/tokenizer.json +0 -0
  31. run-1/checkpoint-2138/tokenizer_config.json +55 -0
  32. run-1/checkpoint-2138/trainer_state.json +68 -0
  33. run-1/checkpoint-2138/training_args.bin +3 -0
  34. run-1/checkpoint-2138/vocab.txt +0 -0
  35. runs/Dec23_02-10-25_786cd877caf6/events.out.tfevents.1703298014.786cd877caf6.1133.2 +2 -2
  36. runs/Dec23_02-10-25_786cd877caf6/events.out.tfevents.1703298068.786cd877caf6.1133.3 +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:ca4e995f9bb736bc5aec2bdd0a48a5ec229a8ec1a7904bd97a145283377b35d1
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c9051cbab86c238a882ead93602c3e9d1513511640bc300fa54d1cb9d0fdf08
3
  size 267832560
run-0/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-0/checkpoint-268/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b5f7d18ff287953bbb79b78daca4f8b0591bbbe780ddb356ec5ebb9ccf76e96
3
+ size 267832560
run-0/checkpoint-268/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e925e6c27ebb494e5520015410e1e7f4d079c900915b69ebe627f38f3beecef
3
+ size 535727290
run-0/checkpoint-268/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6173a9cefd06c9fa387eb88e05012ffeb0cf164c382b9573b07e37f9c2aabd6
3
+ size 14244
run-0/checkpoint-268/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4df240cb13bcc7ae863f367468717703e4ff4041547331e75918571f3b19176
3
+ size 1064
run-0/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-0/checkpoint-268/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/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-0/checkpoint-268/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3943819600110244,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola-hw01/run-0/checkpoint-268",
4
+ "epoch": 2.0,
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": 0.5262112021446228,
14
+ "eval_matthews_correlation": 0.3272948213494272,
15
+ "eval_runtime": 0.6979,
16
+ "eval_samples_per_second": 1494.519,
17
+ "eval_steps_per_second": 94.572,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5145078301429749,
23
+ "eval_matthews_correlation": 0.3943819600110244,
24
+ "eval_runtime": 0.7648,
25
+ "eval_samples_per_second": 1363.737,
26
+ "eval_steps_per_second": 86.296,
27
+ "step": 268
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 268,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 2,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 64,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 1.0554205202937232e-05,
40
+ "num_train_epochs": 2,
41
+ "per_device_train_batch_size": 64,
42
+ "seed": 9
43
+ }
44
+ }
run-0/checkpoint-268/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d44bcd9e6ff3e830e6cd21708452bf8e082dc2441ecccb5468b6800f652a3338
3
+ size 4792
run-0/checkpoint-268/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-1069/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-1/checkpoint-1069/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:807abdc230cfabccc655a43dabf295013039d4800041ab96efa72d7e5f02efd6
3
+ size 267832560
run-1/checkpoint-1069/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8213802bc1ece9fcbbeb11adb863c8891230b3e70dd7809af05e1c56e4ad69b6
3
+ size 535727290
run-1/checkpoint-1069/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0559252c669e30e932c5f9838e7e4093c78bd1b93862edbe7e0544db8e869b58
3
+ size 14308
run-1/checkpoint-1069/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:334fd733f390d80903a751cac08d1ad07d28e9698fc1069a9ee03bc0a20b00dc
3
+ size 1064
run-1/checkpoint-1069/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-1069/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-1069/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-1069/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.25695053268608636,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola-hw01/run-1/checkpoint-1069",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1069,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.47,
13
+ "learning_rate": 2.078291678610645e-06,
14
+ "loss": 0.6042,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.94,
19
+ "learning_rate": 1.8638136932019094e-06,
20
+ "loss": 0.5588,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 1.0,
25
+ "eval_loss": 0.5511462092399597,
26
+ "eval_matthews_correlation": 0.25695053268608636,
27
+ "eval_runtime": 0.7145,
28
+ "eval_samples_per_second": 1459.727,
29
+ "eval_steps_per_second": 92.37,
30
+ "step": 1069
31
+ }
32
+ ],
33
+ "logging_steps": 500,
34
+ "max_steps": 5345,
35
+ "num_input_tokens_seen": 0,
36
+ "num_train_epochs": 5,
37
+ "save_steps": 500,
38
+ "total_flos": 37856698772160.0,
39
+ "train_batch_size": 8,
40
+ "trial_name": null,
41
+ "trial_params": {
42
+ "learning_rate": 2.29276966401938e-06,
43
+ "num_train_epochs": 5,
44
+ "per_device_train_batch_size": 8,
45
+ "seed": 13
46
+ }
47
+ }
run-1/checkpoint-1069/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49a69489651161291c5d60c71fe0449b5d4a343856d5bdde066b2e1b8ad0ce6c
3
+ size 4792
run-1/checkpoint-1069/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/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-1/checkpoint-2138/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c9051cbab86c238a882ead93602c3e9d1513511640bc300fa54d1cb9d0fdf08
3
+ size 267832560
run-1/checkpoint-2138/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:565093ba5e7e427d2ec1f1e1eb94df7ffb4b5515058d602e4144f0a905886bc1
3
+ size 535727290
run-1/checkpoint-2138/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac9c8e5e8fb49e95050d2aa2f256ba0f70fdaf95fbc4a0b2f1e5cc7df7855730
3
+ size 14308
run-1/checkpoint-2138/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:962ebd715fd3444a3338e6d61a0dfe36d93c498b56a9f5c5ec7ac0a1aea4fa27
3
+ size 1064
run-1/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-1/checkpoint-2138/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/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-1/checkpoint-2138/trainer_state.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.37605227228925864,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola-hw01/run-1/checkpoint-2138",
4
+ "epoch": 2.0,
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": 0.47,
13
+ "learning_rate": 2.078291678610645e-06,
14
+ "loss": 0.6042,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.94,
19
+ "learning_rate": 1.8638136932019094e-06,
20
+ "loss": 0.5588,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 1.0,
25
+ "eval_loss": 0.5511462092399597,
26
+ "eval_matthews_correlation": 0.25695053268608636,
27
+ "eval_runtime": 0.7145,
28
+ "eval_samples_per_second": 1459.727,
29
+ "eval_steps_per_second": 92.37,
30
+ "step": 1069
31
+ },
32
+ {
33
+ "epoch": 1.4,
34
+ "learning_rate": 1.6493357077931742e-06,
35
+ "loss": 0.507,
36
+ "step": 1500
37
+ },
38
+ {
39
+ "epoch": 1.87,
40
+ "learning_rate": 1.4348577223844388e-06,
41
+ "loss": 0.4874,
42
+ "step": 2000
43
+ },
44
+ {
45
+ "epoch": 2.0,
46
+ "eval_loss": 0.5382365584373474,
47
+ "eval_matthews_correlation": 0.37605227228925864,
48
+ "eval_runtime": 0.8002,
49
+ "eval_samples_per_second": 1303.369,
50
+ "eval_steps_per_second": 82.476,
51
+ "step": 2138
52
+ }
53
+ ],
54
+ "logging_steps": 500,
55
+ "max_steps": 5345,
56
+ "num_input_tokens_seen": 0,
57
+ "num_train_epochs": 5,
58
+ "save_steps": 500,
59
+ "total_flos": 75521423306424.0,
60
+ "train_batch_size": 8,
61
+ "trial_name": null,
62
+ "trial_params": {
63
+ "learning_rate": 2.29276966401938e-06,
64
+ "num_train_epochs": 5,
65
+ "per_device_train_batch_size": 8,
66
+ "seed": 13
67
+ }
68
+ }
run-1/checkpoint-2138/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49a69489651161291c5d60c71fe0449b5d4a343856d5bdde066b2e1b8ad0ce6c
3
+ size 4792
run-1/checkpoint-2138/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.1703298014.786cd877caf6.1133.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fb3f7b8f933a69f003b465846ae66ff81abaf0589cfb1a706b6111b1b25a339
3
- size 4698
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6f21facfa207865428d2fb2d50f0c17dd1be2242ceadd9db52947a356d83ede
3
+ size 5387
runs/Dec23_02-10-25_786cd877caf6/events.out.tfevents.1703298068.786cd877caf6.1133.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86048fc16e3dbd5b0e0185c00d1d01c22b9583916a51250bf2f57db5a4effe8f
3
+ size 5659
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d44bcd9e6ff3e830e6cd21708452bf8e082dc2441ecccb5468b6800f652a3338
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49a69489651161291c5d60c71fe0449b5d4a343856d5bdde066b2e1b8ad0ce6c
3
  size 4792