anamelchor commited on
Commit
9c9558c
·
verified ·
1 Parent(s): 83f8050

Training in progress, epoch 4

Browse files
Files changed (35) hide show
  1. model.safetensors +1 -1
  2. run-1/checkpoint-268/config.json +25 -0
  3. run-1/checkpoint-268/model.safetensors +3 -0
  4. run-1/checkpoint-268/optimizer.pt +3 -0
  5. run-1/checkpoint-268/rng_state.pth +3 -0
  6. run-1/checkpoint-268/scheduler.pt +3 -0
  7. run-1/checkpoint-268/special_tokens_map.json +7 -0
  8. run-1/checkpoint-268/tokenizer.json +0 -0
  9. run-1/checkpoint-268/tokenizer_config.json +55 -0
  10. run-1/checkpoint-268/trainer_state.json +44 -0
  11. run-1/checkpoint-268/training_args.bin +3 -0
  12. run-1/checkpoint-268/vocab.txt +0 -0
  13. run-1/checkpoint-402/config.json +25 -0
  14. run-1/checkpoint-402/model.safetensors +3 -0
  15. run-1/checkpoint-402/optimizer.pt +3 -0
  16. run-1/checkpoint-402/rng_state.pth +3 -0
  17. run-1/checkpoint-402/scheduler.pt +3 -0
  18. run-1/checkpoint-402/special_tokens_map.json +7 -0
  19. run-1/checkpoint-402/tokenizer.json +0 -0
  20. run-1/checkpoint-402/tokenizer_config.json +55 -0
  21. run-1/checkpoint-402/trainer_state.json +53 -0
  22. run-1/checkpoint-402/training_args.bin +3 -0
  23. run-1/checkpoint-402/vocab.txt +0 -0
  24. run-1/checkpoint-536/config.json +25 -0
  25. run-1/checkpoint-536/model.safetensors +3 -0
  26. run-1/checkpoint-536/optimizer.pt +3 -0
  27. run-1/checkpoint-536/rng_state.pth +3 -0
  28. run-1/checkpoint-536/scheduler.pt +3 -0
  29. run-1/checkpoint-536/special_tokens_map.json +7 -0
  30. run-1/checkpoint-536/tokenizer.json +0 -0
  31. run-1/checkpoint-536/tokenizer_config.json +55 -0
  32. run-1/checkpoint-536/trainer_state.json +69 -0
  33. run-1/checkpoint-536/training_args.bin +3 -0
  34. run-1/checkpoint-536/vocab.txt +0 -0
  35. runs/Mar03_19-18-26_abc5bcbabcce/events.out.tfevents.1709493714.abc5bcbabcce.1176.30 +2 -2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:965ccdb2fdbba772a63458d46de224adb46912122f2e5209bed078a223778be4
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a89d05202561f88efc8b74831bae197cf4ab182b1b67d59bd72b887b89dd9e0f
3
  size 267832560
run-1/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": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-1/checkpoint-268/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49d6b5959dd2a0ea0667c59e6f3283d1752b1e703475defb4ef0a4948a79e5f4
3
+ size 267832560
run-1/checkpoint-268/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4ecc7b226804a86dfc011ca9abce7863dc6fc33990ecd067abd96016b0f8c04
3
+ size 535727290
run-1/checkpoint-268/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a387a70985a9d5ddb23665a6eba8dcab8fe97931f627799da68ebbabc1450185
3
+ size 14244
run-1/checkpoint-268/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a44c54c646bb9011d05d52c0355c58b8bc9f1d8203e9dd5bc3ce2ddaddd3d27
3
+ size 1064
run-1/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-1/checkpoint-268/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/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-1/checkpoint-268/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5008706778439593,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/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": 0.5111436247825623,
14
+ "eval_matthews_correlation": 0.3704165163359662,
15
+ "eval_runtime": 0.7196,
16
+ "eval_samples_per_second": 1449.402,
17
+ "eval_steps_per_second": 91.717,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.458956778049469,
23
+ "eval_matthews_correlation": 0.5008706778439593,
24
+ "eval_runtime": 0.7749,
25
+ "eval_samples_per_second": 1345.924,
26
+ "eval_steps_per_second": 85.169,
27
+ "step": 268
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 670,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 5,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 64,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 1.7742116118117113e-05,
40
+ "num_train_epochs": 5,
41
+ "per_device_train_batch_size": 64,
42
+ "seed": 5
43
+ }
44
+ }
run-1/checkpoint-268/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e85813f8f9164f9360ce3af56ab636de97835d2f503c2f4e4acad37565e88656
3
+ size 4984
run-1/checkpoint-268/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/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": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-1/checkpoint-402/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:636efbeb70e7d77ac2aea7216e9c65804d8519f68dc7e78ec66d9b47dc5dcc4a
3
+ size 267832560
run-1/checkpoint-402/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fd0ea0c4f9ad94e9b5119b0b52addc779e71a2645e40d8c93b5d4e17c8b9ebb
3
+ size 535727290
run-1/checkpoint-402/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b5a91da2ec62e9093ed73096c4ec63492bdaa76e06a9bb581abfa43f9b87be0
3
+ size 14244
run-1/checkpoint-402/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f119c49098c568afd1409071f9eff47b15f7ca651fbd5894d37e482dfb7e242e
3
+ size 1064
run-1/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-1/checkpoint-402/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/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-1/checkpoint-402/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5108951669698317,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/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": 0.5111436247825623,
14
+ "eval_matthews_correlation": 0.3704165163359662,
15
+ "eval_runtime": 0.7196,
16
+ "eval_samples_per_second": 1449.402,
17
+ "eval_steps_per_second": 91.717,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.458956778049469,
23
+ "eval_matthews_correlation": 0.5008706778439593,
24
+ "eval_runtime": 0.7749,
25
+ "eval_samples_per_second": 1345.924,
26
+ "eval_steps_per_second": 85.169,
27
+ "step": 268
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.4913136959075928,
32
+ "eval_matthews_correlation": 0.5108951669698317,
33
+ "eval_runtime": 0.9439,
34
+ "eval_samples_per_second": 1104.949,
35
+ "eval_steps_per_second": 69.92,
36
+ "step": 402
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 670,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 5,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 64,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 1.7742116118117113e-05,
49
+ "num_train_epochs": 5,
50
+ "per_device_train_batch_size": 64,
51
+ "seed": 5
52
+ }
53
+ }
run-1/checkpoint-402/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e85813f8f9164f9360ce3af56ab636de97835d2f503c2f4e4acad37565e88656
3
+ size 4984
run-1/checkpoint-402/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/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": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-1/checkpoint-536/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a89d05202561f88efc8b74831bae197cf4ab182b1b67d59bd72b887b89dd9e0f
3
+ size 267832560
run-1/checkpoint-536/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6742cf9592b20703af78d9b8c04714a6999518190025d39bd7c03f5b5fa9612
3
+ size 535727290
run-1/checkpoint-536/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8005fd344a35973dde2a8fef759ea7142b3000c5e2337e569e2c0ea129208ad
3
+ size 14244
run-1/checkpoint-536/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69dbd3f7bf083aec61e72b09acbaf737f9d7da4f4f48b65c7b185f821b042b7
3
+ size 1064
run-1/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-1/checkpoint-536/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/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-1/checkpoint-536/trainer_state.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.520875943143754,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/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": 0.5111436247825623,
14
+ "eval_matthews_correlation": 0.3704165163359662,
15
+ "eval_runtime": 0.7196,
16
+ "eval_samples_per_second": 1449.402,
17
+ "eval_steps_per_second": 91.717,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.458956778049469,
23
+ "eval_matthews_correlation": 0.5008706778439593,
24
+ "eval_runtime": 0.7749,
25
+ "eval_samples_per_second": 1345.924,
26
+ "eval_steps_per_second": 85.169,
27
+ "step": 268
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.4913136959075928,
32
+ "eval_matthews_correlation": 0.5108951669698317,
33
+ "eval_runtime": 0.9439,
34
+ "eval_samples_per_second": 1104.949,
35
+ "eval_steps_per_second": 69.92,
36
+ "step": 402
37
+ },
38
+ {
39
+ "epoch": 3.73,
40
+ "grad_norm": 8.718708038330078,
41
+ "learning_rate": 4.5017309553431485e-06,
42
+ "loss": 0.3868,
43
+ "step": 500
44
+ },
45
+ {
46
+ "epoch": 4.0,
47
+ "eval_loss": 0.5247140526771545,
48
+ "eval_matthews_correlation": 0.520875943143754,
49
+ "eval_runtime": 0.7379,
50
+ "eval_samples_per_second": 1413.511,
51
+ "eval_steps_per_second": 89.446,
52
+ "step": 536
53
+ }
54
+ ],
55
+ "logging_steps": 500,
56
+ "max_steps": 670,
57
+ "num_input_tokens_seen": 0,
58
+ "num_train_epochs": 5,
59
+ "save_steps": 500,
60
+ "total_flos": 210564174474576.0,
61
+ "train_batch_size": 64,
62
+ "trial_name": null,
63
+ "trial_params": {
64
+ "learning_rate": 1.7742116118117113e-05,
65
+ "num_train_epochs": 5,
66
+ "per_device_train_batch_size": 64,
67
+ "seed": 5
68
+ }
69
+ }
run-1/checkpoint-536/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e85813f8f9164f9360ce3af56ab636de97835d2f503c2f4e4acad37565e88656
3
+ size 4984
run-1/checkpoint-536/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar03_19-18-26_abc5bcbabcce/events.out.tfevents.1709493714.abc5bcbabcce.1176.30 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64aebb4e12060b5f255f0777e35420a7f8016a4fe7682ab313287be4e09263a2
3
- size 5212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c78443bb69adb8ea218d45fe83188bcf757b079e975796fb66fc63f48135739
3
+ size 6782