Hugging Face's logo

Tech-oriented
/
bert-base-uncased-finetuned-sst2

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Tech-oriented commited on
Commit
f79ee64
·
verified ·
1 Parent(s): 866bb22

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. model.safetensors +1 -1
  2. run-4/checkpoint-422/config.json +27 -0
  3. run-4/checkpoint-422/model.safetensors +3 -0
  4. run-4/checkpoint-422/optimizer.pt +3 -0
  5. run-4/checkpoint-422/rng_state.pth +3 -0
  6. run-4/checkpoint-422/scheduler.pt +3 -0
  7. run-4/checkpoint-422/special_tokens_map.json +7 -0
  8. run-4/checkpoint-422/tokenizer.json +0 -0
  9. run-4/checkpoint-422/tokenizer_config.json +55 -0
  10. run-4/checkpoint-422/trainer_state.json +44 -0
  11. run-4/checkpoint-422/training_args.bin +3 -0
  12. run-4/checkpoint-422/vocab.txt +0 -0
  13. run-4/checkpoint-633/config.json +27 -0
  14. run-4/checkpoint-633/model.safetensors +3 -0
  15. run-4/checkpoint-633/optimizer.pt +3 -0
  16. run-4/checkpoint-633/rng_state.pth +3 -0
  17. run-4/checkpoint-633/scheduler.pt +3 -0
  18. run-4/checkpoint-633/special_tokens_map.json +7 -0
  19. run-4/checkpoint-633/tokenizer.json +0 -0
  20. run-4/checkpoint-633/tokenizer_config.json +55 -0
  21. run-4/checkpoint-633/trainer_state.json +60 -0
  22. run-4/checkpoint-633/training_args.bin +3 -0
  23. run-4/checkpoint-633/vocab.txt +0 -0
  24. run-6/checkpoint-211/config.json +27 -0
  25. run-6/checkpoint-211/model.safetensors +3 -0
  26. run-6/checkpoint-211/optimizer.pt +3 -0
  27. run-6/checkpoint-211/rng_state.pth +3 -0
  28. run-6/checkpoint-211/scheduler.pt +3 -0
  29. run-6/checkpoint-211/special_tokens_map.json +7 -0
  30. run-6/checkpoint-211/tokenizer.json +0 -0
  31. run-6/checkpoint-211/tokenizer_config.json +55 -0
  32. run-6/checkpoint-211/trainer_state.json +35 -0
  33. run-6/checkpoint-211/training_args.bin +3 -0
  34. run-6/checkpoint-211/vocab.txt +0 -0
  35. runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709498805.90708aaa767a.21824.23 +3 -0
  36. runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709498861.90708aaa767a.21824.24 +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 sha256:118f4c78444f2940718c0d3597e86c36a7be25347afc99e94cb1ffc468b6595b
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:082851f9b957d055fcbe72ca5eb1742411ab7792a974452628f63518027d3faa
3
  size 437958648
run-4/checkpoint-422/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "problem_type": "single_label_classification",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.2",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
+ }
run-4/checkpoint-422/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be87332a226bdfe66aa8aec5b3c4c5ce71f5fe13479a7e7d851752724af97e82
3
+ size 437958648
run-4/checkpoint-422/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5456fab877e4b2c6a94508dda4269de32dd3062a2f02acf8d95d055c33ea13bc
3
+ size 876038394
run-4/checkpoint-422/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8324adba996a07dd80a2fbe3370e0b9101fd8d3723fcdc8d978f6446264fb6af
3
+ size 14244
run-4/checkpoint-422/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e76b771517a69c80a5d6954ae839c678665ca8f0a7c989e2c71aa59c056712d8
3
+ size 1064
run-4/checkpoint-422/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-422/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-422/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": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-4/checkpoint-422/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9025229357798165,
3
+ "best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-4/checkpoint-422",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 422,
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_accuracy": 0.8807339449541285,
14
+ "eval_loss": 0.2860465347766876,
15
+ "eval_runtime": 2.3416,
16
+ "eval_samples_per_second": 372.397,
17
+ "eval_steps_per_second": 23.488,
18
+ "step": 211
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.9025229357798165,
23
+ "eval_loss": 0.30859723687171936,
24
+ "eval_runtime": 2.3653,
25
+ "eval_samples_per_second": 368.662,
26
+ "eval_steps_per_second": 23.253,
27
+ "step": 422
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 633,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 3,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 32,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 5.23140217513524e-05,
40
+ "num_train_epochs": 3,
41
+ "per_device_train_batch_size": 32,
42
+ "seed": 3
43
+ }
44
+ }
run-4/checkpoint-422/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a14303b760ee151020909efbf06b2a21d25b83f2f033203b97ca6e7e040da154
3
+ size 4920
run-4/checkpoint-422/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-633/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "problem_type": "single_label_classification",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.2",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
+ }
run-4/checkpoint-633/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea87df5170b05db6222d9bea54eaeb38439d1704bc42d875e45d666a797c9f39
3
+ size 437958648
run-4/checkpoint-633/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b2ee29fb0bcbe03cd770b808f5e0e6ae8e5a2b23337bab1a0358f0b381bb5c7
3
+ size 876038394
run-4/checkpoint-633/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81e8565db30a703f5c2f9475899f346f78916c8eaa6d04f79f0e14e37860b035
3
+ size 14244
run-4/checkpoint-633/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcba1f6611db8ef90ba214ab57d4faacd81dde5fd3142c9b94469fd689ac35f5
3
+ size 1064
run-4/checkpoint-633/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-633/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-633/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": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-4/checkpoint-633/trainer_state.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.930045871559633,
3
+ "best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-4/checkpoint-633",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 633,
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_accuracy": 0.8807339449541285,
14
+ "eval_loss": 0.2860465347766876,
15
+ "eval_runtime": 2.3416,
16
+ "eval_samples_per_second": 372.397,
17
+ "eval_steps_per_second": 23.488,
18
+ "step": 211
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.9025229357798165,
23
+ "eval_loss": 0.30859723687171936,
24
+ "eval_runtime": 2.3653,
25
+ "eval_samples_per_second": 368.662,
26
+ "eval_steps_per_second": 23.253,
27
+ "step": 422
28
+ },
29
+ {
30
+ "epoch": 2.37,
31
+ "grad_norm": 0.23388604819774628,
32
+ "learning_rate": 1.099172968867278e-05,
33
+ "loss": 0.2134,
34
+ "step": 500
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "eval_accuracy": 0.930045871559633,
39
+ "eval_loss": 0.3024921715259552,
40
+ "eval_runtime": 2.3782,
41
+ "eval_samples_per_second": 366.664,
42
+ "eval_steps_per_second": 23.127,
43
+ "step": 633
44
+ }
45
+ ],
46
+ "logging_steps": 500,
47
+ "max_steps": 633,
48
+ "num_input_tokens_seen": 0,
49
+ "num_train_epochs": 3,
50
+ "save_steps": 500,
51
+ "total_flos": 336939914716260.0,
52
+ "train_batch_size": 32,
53
+ "trial_name": null,
54
+ "trial_params": {
55
+ "learning_rate": 5.23140217513524e-05,
56
+ "num_train_epochs": 3,
57
+ "per_device_train_batch_size": 32,
58
+ "seed": 3
59
+ }
60
+ }
run-4/checkpoint-633/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a14303b760ee151020909efbf06b2a21d25b83f2f033203b97ca6e7e040da154
3
+ size 4920
run-4/checkpoint-633/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-211/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "problem_type": "single_label_classification",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.2",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
+ }
run-6/checkpoint-211/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:082851f9b957d055fcbe72ca5eb1742411ab7792a974452628f63518027d3faa
3
+ size 437958648
run-6/checkpoint-211/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5358e335fe4a6e2a90f13e1851e11970ff89f9c2f8485cbbceb27ba65dfcf36f
3
+ size 876038394
run-6/checkpoint-211/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cb0dd1e13d8982c379f0b9f7b5eae142e6fc1e95814de9534e6934bfd6b9901
3
+ size 14244
run-6/checkpoint-211/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b946968aa62512174a8870dbc957de17026ccd8274e830f9fb1213ff87e3083
3
+ size 1064
run-6/checkpoint-211/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-6/checkpoint-211/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-211/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": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-6/checkpoint-211/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8979357798165137,
3
+ "best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-6/checkpoint-211",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 211,
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_accuracy": 0.8979357798165137,
14
+ "eval_loss": 0.2530447840690613,
15
+ "eval_runtime": 2.3384,
16
+ "eval_samples_per_second": 372.905,
17
+ "eval_steps_per_second": 23.52,
18
+ "step": 211
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 633,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 3,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 32,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 7.307031523207379e-05,
31
+ "num_train_epochs": 3,
32
+ "per_device_train_batch_size": 32,
33
+ "seed": 7
34
+ }
35
+ }
run-6/checkpoint-211/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70c7a28fe6d13e844ab8327d52bfc6c2fe84c82ef54748b5d8eb295117237ac1
3
+ size 4920
run-6/checkpoint-211/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709498805.90708aaa767a.21824.23 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ea976baa562f07c06c85a6d38b42c07765a85d3eb9ee59861fa2233164bbf14
3
+ size 4946
runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709498861.90708aaa767a.21824.24 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1ea2b5cb8053c1f6dd1f7e04f02988472fcc9e6b707ebaf5078f7e09d533af2
3
+ size 5269
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a14303b760ee151020909efbf06b2a21d25b83f2f033203b97ca6e7e040da154
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70c7a28fe6d13e844ab8327d52bfc6c2fe84c82ef54748b5d8eb295117237ac1
3
  size 4920