Hugging Face's logo

AilingDAI
/
HM_1

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Metrics Community
AilingDAI commited on
Commit
2a0bcfa
·
verified ·
1 Parent(s): 5dcbd7a

Training in progress, epoch 2

Browse files
Files changed (37) hide show
  1. model.safetensors +1 -1
  2. run-0/checkpoint-804/config.json +25 -0
  3. run-0/checkpoint-804/model.safetensors +3 -0
  4. run-0/checkpoint-804/optimizer.pt +3 -0
  5. run-0/checkpoint-804/rng_state.pth +3 -0
  6. run-0/checkpoint-804/scheduler.pt +3 -0
  7. run-0/checkpoint-804/special_tokens_map.json +7 -0
  8. run-0/checkpoint-804/tokenizer.json +0 -0
  9. run-0/checkpoint-804/tokenizer_config.json +55 -0
  10. run-0/checkpoint-804/trainer_state.json +60 -0
  11. run-0/checkpoint-804/training_args.bin +3 -0
  12. run-0/checkpoint-804/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 +49 -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 +72 -0
  33. run-1/checkpoint-2138/training_args.bin +3 -0
  34. run-1/checkpoint-2138/vocab.txt +0 -0
  35. runs/Mar23_02-10-25_52e0cb6c1736/events.out.tfevents.1711160300.52e0cb6c1736.459.2 +2 -2
  36. runs/Mar23_02-10-25_52e0cb6c1736/events.out.tfevents.1711160395.52e0cb6c1736.459.3 +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:b81d1cde9ce9fa79f45b951a8bc435cc75ed206aab0999ba52f97181882307c8
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b56433d425c1c5233d43980b8cacc41ea7ffd6169e01838e3d9d0e5d2067a8ca
3
  size 267832560
run-0/checkpoint-804/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": "4.39.1",
24
+ "vocab_size": 30522
25
+ }
run-0/checkpoint-804/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd783a99ed6464cfae22dbd200c939e607cd8b3b6a834f56d1cab1d5d1878a5f
3
+ size 267832560
run-0/checkpoint-804/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76d1f1ca083bcc044716358169f1137bbf2aacb695b1421a4d1dcb3e26cb85e5
3
+ size 535727290
run-0/checkpoint-804/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efc02031fa2486ef1ec8588df415ec695bf5a210a41d4a8d69069bcac08e2449
3
+ size 14244
run-0/checkpoint-804/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b81302d458daf40eed105317a99b917ac25e6b3915046c072db01f8c57c37dc
3
+ size 1064
run-0/checkpoint-804/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-804/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-804/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-804/trainer_state.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.40932957628357974,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-804",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 804,
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": 0.5428110361099243,
14
+ "eval_matthews_correlation": 0.16816948860566025,
15
+ "eval_runtime": 0.759,
16
+ "eval_samples_per_second": 1374.206,
17
+ "eval_steps_per_second": 86.958,
18
+ "step": 268
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "grad_norm": 3.443307876586914,
23
+ "learning_rate": 1.5262367752217109e-06,
24
+ "loss": 0.5463,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_loss": 0.5213160514831543,
30
+ "eval_matthews_correlation": 0.402173248634525,
31
+ "eval_runtime": 0.7335,
32
+ "eval_samples_per_second": 1421.887,
33
+ "eval_steps_per_second": 89.976,
34
+ "step": 536
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "eval_loss": 0.5190894603729248,
39
+ "eval_matthews_correlation": 0.40932957628357974,
40
+ "eval_runtime": 0.8161,
41
+ "eval_samples_per_second": 1278.032,
42
+ "eval_steps_per_second": 80.873,
43
+ "step": 804
44
+ }
45
+ ],
46
+ "logging_steps": 500,
47
+ "max_steps": 804,
48
+ "num_input_tokens_seen": 0,
49
+ "num_train_epochs": 3,
50
+ "save_steps": 500,
51
+ "total_flos": 95368506545292.0,
52
+ "train_batch_size": 32,
53
+ "trial_name": null,
54
+ "trial_params": {
55
+ "learning_rate": 4.036494629204788e-06,
56
+ "num_train_epochs": 3,
57
+ "per_device_train_batch_size": 32,
58
+ "seed": 23
59
+ }
60
+ }
run-0/checkpoint-804/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcf874ce22791d9f1993c027b375528da647df85379a06a734ed6731c3d7f669
3
+ size 4984
run-0/checkpoint-804/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": "4.39.1",
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 sha256:9cbe7d2a14d6c44e5965fe559f39ae001a0bec212d55ae76ee74d6f78a5cb3ab
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:fa0df246bbb8e447782f3bd52ffc79458807165381545d1ccf9415174725bc38
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 sha256:4f18cb1de77646dd1e41247a6a86126ab4dfb25778817b59557f803bfafff73b
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:edaa6b45c81b03207d6917fd9a501e7e72636579f4d88b4600cebfdd3d30e140
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 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.17287049484713765,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/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
+ "grad_norm": 3.3132574558258057,
14
+ "learning_rate": 5.3487951435688824e-05,
15
+ "loss": 0.6128,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.94,
20
+ "grad_norm": 10.235213279724121,
21
+ "learning_rate": 4.360838892447921e-05,
22
+ "loss": 0.5719,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_loss": 0.6078479886054993,
28
+ "eval_matthews_correlation": 0.17287049484713765,
29
+ "eval_runtime": 0.8538,
30
+ "eval_samples_per_second": 1221.595,
31
+ "eval_steps_per_second": 77.301,
32
+ "step": 1069
33
+ }
34
+ ],
35
+ "logging_steps": 500,
36
+ "max_steps": 3207,
37
+ "num_input_tokens_seen": 0,
38
+ "num_train_epochs": 3,
39
+ "save_steps": 500,
40
+ "total_flos": 37581414959328.0,
41
+ "train_batch_size": 8,
42
+ "trial_name": null,
43
+ "trial_params": {
44
+ "learning_rate": 6.336751394689843e-05,
45
+ "num_train_epochs": 3,
46
+ "per_device_train_batch_size": 8,
47
+ "seed": 33
48
+ }
49
+ }
run-1/checkpoint-1069/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6767fea303015c1edac213c398e0894020cd1b6ef3eb74b74eb055ccb779eab2
3
+ size 4984
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": "4.39.1",
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:b56433d425c1c5233d43980b8cacc41ea7ffd6169e01838e3d9d0e5d2067a8ca
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 sha256:15410be3e26267250d618499743f093d3248defa3c1c30535474e1f591945bf9
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:d3e82e8e5c924089bf2d105c906ca0a273a99d7892d3964255fbc0c1f9f92600
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 sha256:1a6700fecdb3f18d11a7d7fe7ece7a1b609303538bb6035cd7cc1cacb18d4a78
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 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3237133903096396,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/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
+ "grad_norm": 3.3132574558258057,
14
+ "learning_rate": 5.3487951435688824e-05,
15
+ "loss": 0.6128,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.94,
20
+ "grad_norm": 10.235213279724121,
21
+ "learning_rate": 4.360838892447921e-05,
22
+ "loss": 0.5719,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_loss": 0.6078479886054993,
28
+ "eval_matthews_correlation": 0.17287049484713765,
29
+ "eval_runtime": 0.8538,
30
+ "eval_samples_per_second": 1221.595,
31
+ "eval_steps_per_second": 77.301,
32
+ "step": 1069
33
+ },
34
+ {
35
+ "epoch": 1.4,
36
+ "grad_norm": 9.716071128845215,
37
+ "learning_rate": 3.3728826413269603e-05,
38
+ "loss": 0.445,
39
+ "step": 1500
40
+ },
41
+ {
42
+ "epoch": 1.87,
43
+ "grad_norm": 7.158620834350586,
44
+ "learning_rate": 2.3849263902059996e-05,
45
+ "loss": 0.4148,
46
+ "step": 2000
47
+ },
48
+ {
49
+ "epoch": 2.0,
50
+ "eval_loss": 0.7100014090538025,
51
+ "eval_matthews_correlation": 0.3237133903096396,
52
+ "eval_runtime": 0.8592,
53
+ "eval_samples_per_second": 1213.872,
54
+ "eval_steps_per_second": 76.813,
55
+ "step": 2138
56
+ }
57
+ ],
58
+ "logging_steps": 500,
59
+ "max_steps": 3207,
60
+ "num_input_tokens_seen": 0,
61
+ "num_train_epochs": 3,
62
+ "save_steps": 500,
63
+ "total_flos": 75365670622848.0,
64
+ "train_batch_size": 8,
65
+ "trial_name": null,
66
+ "trial_params": {
67
+ "learning_rate": 6.336751394689843e-05,
68
+ "num_train_epochs": 3,
69
+ "per_device_train_batch_size": 8,
70
+ "seed": 33
71
+ }
72
+ }
run-1/checkpoint-2138/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6767fea303015c1edac213c398e0894020cd1b6ef3eb74b74eb055ccb779eab2
3
+ size 4984
run-1/checkpoint-2138/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar23_02-10-25_52e0cb6c1736/events.out.tfevents.1711160300.52e0cb6c1736.459.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a026122fa53a34719107c827ec166d87385f39d4e31da964ccdb2c8c12bc44be
3
- size 5467
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85a17ace3f46395086fc7f6219815027076153e905f5ef2aad4b47e9a22cdf3b
3
+ size 6156
runs/Mar23_02-10-25_52e0cb6c1736/events.out.tfevents.1711160395.52e0cb6c1736.459.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a8618eeb803809dbaf10d6fbbed664e4aa7417da4901061ffbbf6fd955a27c3
3
+ size 6310
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fcf874ce22791d9f1993c027b375528da647df85379a06a734ed6731c3d7f669
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6767fea303015c1edac213c398e0894020cd1b6ef3eb74b74eb055ccb779eab2
3
  size 4984