Hugging Face's logo

LiamLi1991
/
HW01

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Metrics Community
LiamLi1991 commited on
Commit
9cd6d86
·
1 Parent(s): 159ee05

Training in progress, epoch 4

Browse files
Files changed (36) 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-0/checkpoint-402/config.json +25 -0
  14. run-0/checkpoint-402/model.safetensors +3 -0
  15. run-0/checkpoint-402/optimizer.pt +3 -0
  16. run-0/checkpoint-402/rng_state.pth +3 -0
  17. run-0/checkpoint-402/scheduler.pt +3 -0
  18. run-0/checkpoint-402/special_tokens_map.json +7 -0
  19. run-0/checkpoint-402/tokenizer.json +0 -0
  20. run-0/checkpoint-402/tokenizer_config.json +55 -0
  21. run-0/checkpoint-402/trainer_state.json +53 -0
  22. run-0/checkpoint-402/training_args.bin +3 -0
  23. run-0/checkpoint-402/vocab.txt +0 -0
  24. run-0/checkpoint-536/config.json +25 -0
  25. run-0/checkpoint-536/model.safetensors +3 -0
  26. run-0/checkpoint-536/optimizer.pt +3 -0
  27. run-0/checkpoint-536/rng_state.pth +3 -0
  28. run-0/checkpoint-536/scheduler.pt +3 -0
  29. run-0/checkpoint-536/special_tokens_map.json +7 -0
  30. run-0/checkpoint-536/tokenizer.json +0 -0
  31. run-0/checkpoint-536/tokenizer_config.json +55 -0
  32. run-0/checkpoint-536/trainer_state.json +68 -0
  33. run-0/checkpoint-536/training_args.bin +3 -0
  34. run-0/checkpoint-536/vocab.txt +0 -0
  35. runs/Dec23_04-48-26_eb0969bbe4e6/events.out.tfevents.1703306979.eb0969bbe4e6.378.0 +2 -2
  36. runs/Dec23_04-48-26_eb0969bbe4e6/events.out.tfevents.1703307020.eb0969bbe4e6.378.1 +2 -2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f16783a7ae4678093b460066fd39d837988729ba56d7e0e42fb0a5b98afb07b
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac48a0b0b57e2410d85f3d1352e709674d59974b677c2e447f67ee8131999ca6
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:fadb4e17036ae30a672296d68b0d899455b2837dd114d0e61afbb3f513ada3ea
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:c594f301218c2fd750f57dc03a7d503eac9170e1447e9603e6a58d448adaf208
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:ed4de1830cbc656e834d77b75444f9511cb6f78507e6fcda7b1b5f506b7b2a5b
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 sha256:8b37b2bc2f6d0f7b7ee0cbb570e5dd6944b7a5624a1fc6e39e8bc1748cac7b6f
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": 0.44417673863908563,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/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": 0.5199057459831238,
14
+ "eval_matthews_correlation": 0.3698827174375846,
15
+ "eval_runtime": 0.8936,
16
+ "eval_samples_per_second": 1167.235,
17
+ "eval_steps_per_second": 73.861,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.491267591714859,
23
+ "eval_matthews_correlation": 0.44417673863908563,
24
+ "eval_runtime": 0.7468,
25
+ "eval_samples_per_second": 1396.564,
26
+ "eval_steps_per_second": 88.373,
27
+ "step": 268
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 536,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 4,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 64,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 1.59980677722973e-05,
40
+ "num_train_epochs": 4,
41
+ "per_device_train_batch_size": 64,
42
+ "seed": 18
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 sha256:6b95dd210fa74b759d650b3c95a9236cce725060761a8143e7ac42594dc1f1fb
3
+ size 4792
run-0/checkpoint-268/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-402/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-402/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a2389febcf461b93a78a6ad3f5f7ca9d3fdfb599a5028126d447e4b6bf4baaa
3
+ size 267832560
run-0/checkpoint-402/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6505ee1eed732de90a81bd27b3907cba8003926035bde7d602cfd1951bf11a02
3
+ size 535727290
run-0/checkpoint-402/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab34df0ccec816ba72634276ef96767d592a4fad76039b87f18ab7f6f1cdeb38
3
+ size 14244
run-0/checkpoint-402/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24ba9832c2d5781b5432e9756a62c324ba6cbb94a6d3000b649abfeeaecc4de7
3
+ size 1064
run-0/checkpoint-402/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-402/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-402/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-402/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.46458665505165037,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-402",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 402,
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": 0.5199057459831238,
14
+ "eval_matthews_correlation": 0.3698827174375846,
15
+ "eval_runtime": 0.8936,
16
+ "eval_samples_per_second": 1167.235,
17
+ "eval_steps_per_second": 73.861,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.491267591714859,
23
+ "eval_matthews_correlation": 0.44417673863908563,
24
+ "eval_runtime": 0.7468,
25
+ "eval_samples_per_second": 1396.564,
26
+ "eval_steps_per_second": 88.373,
27
+ "step": 268
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.5117157101631165,
32
+ "eval_matthews_correlation": 0.46458665505165037,
33
+ "eval_runtime": 0.8301,
34
+ "eval_samples_per_second": 1256.49,
35
+ "eval_steps_per_second": 79.509,
36
+ "step": 402
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 536,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 4,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 64,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 1.59980677722973e-05,
49
+ "num_train_epochs": 4,
50
+ "per_device_train_batch_size": 64,
51
+ "seed": 18
52
+ }
53
+ }
run-0/checkpoint-402/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b95dd210fa74b759d650b3c95a9236cce725060761a8143e7ac42594dc1f1fb
3
+ size 4792
run-0/checkpoint-402/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-536/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-536/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac48a0b0b57e2410d85f3d1352e709674d59974b677c2e447f67ee8131999ca6
3
+ size 267832560
run-0/checkpoint-536/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8442081693f4de1912fb3c0ab2437a2ca8040547923842be964c330f9e62aba
3
+ size 535727290
run-0/checkpoint-536/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7aa6f4fb7e7d09863ac4522aa0732f74658b87001599422289d36e7259a6203
3
+ size 14244
run-0/checkpoint-536/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:957fdca4bcbe5ba745cad262ec1732c87403d27193d8bfecb86798a2a2fa4c16
3
+ size 1064
run-0/checkpoint-536/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-536/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-536/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-536/trainer_state.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.46882316714116756,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-536",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 536,
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": 0.5199057459831238,
14
+ "eval_matthews_correlation": 0.3698827174375846,
15
+ "eval_runtime": 0.8936,
16
+ "eval_samples_per_second": 1167.235,
17
+ "eval_steps_per_second": 73.861,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.491267591714859,
23
+ "eval_matthews_correlation": 0.44417673863908563,
24
+ "eval_runtime": 0.7468,
25
+ "eval_samples_per_second": 1396.564,
26
+ "eval_steps_per_second": 88.373,
27
+ "step": 268
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.5117157101631165,
32
+ "eval_matthews_correlation": 0.46458665505165037,
33
+ "eval_runtime": 0.8301,
34
+ "eval_samples_per_second": 1256.49,
35
+ "eval_steps_per_second": 79.509,
36
+ "step": 402
37
+ },
38
+ {
39
+ "epoch": 3.73,
40
+ "learning_rate": 1.074497089184147e-06,
41
+ "loss": 0.4112,
42
+ "step": 500
43
+ },
44
+ {
45
+ "epoch": 4.0,
46
+ "eval_loss": 0.5207866430282593,
47
+ "eval_matthews_correlation": 0.46882316714116756,
48
+ "eval_runtime": 0.7702,
49
+ "eval_samples_per_second": 1354.203,
50
+ "eval_steps_per_second": 85.693,
51
+ "step": 536
52
+ }
53
+ ],
54
+ "logging_steps": 500,
55
+ "max_steps": 536,
56
+ "num_input_tokens_seen": 0,
57
+ "num_train_epochs": 4,
58
+ "save_steps": 500,
59
+ "total_flos": 210553308008280.0,
60
+ "train_batch_size": 64,
61
+ "trial_name": null,
62
+ "trial_params": {
63
+ "learning_rate": 1.59980677722973e-05,
64
+ "num_train_epochs": 4,
65
+ "per_device_train_batch_size": 64,
66
+ "seed": 18
67
+ }
68
+ }
run-0/checkpoint-536/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b95dd210fa74b759d650b3c95a9236cce725060761a8143e7ac42594dc1f1fb
3
+ size 4792
run-0/checkpoint-536/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec23_04-48-26_eb0969bbe4e6/events.out.tfevents.1703306979.eb0969bbe4e6.378.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2dfa013aa19764bfd29342c180ef397a238401561d3825495edd9d070e19e7a4
3
- size 4184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1e4231d3eb3572c48ba158b23d6073d1496cf38f1c4450e9eef8935de136822
3
+ size 4328
runs/Dec23_04-48-26_eb0969bbe4e6/events.out.tfevents.1703307020.eb0969bbe4e6.378.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7feffb1a3b0b6855ff47be6984118605030efde46a83c2ed3b514b20bdfdb7aa
3
- size 4678
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b57cb866808d7a3b463dee5e653c9527f1543ecdae1a73b743b0380da295839
3
+ size 6194