Hugging Face's logo

anamelchor
/
distilbert-base-uncased-finetuned-cola

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
anamelchor commited on
Commit
04939b5
·
verified ·
1 Parent(s): aaa50b7

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. model.safetensors +1 -1
  2. run-4/checkpoint-428/config.json +25 -0
  3. run-4/checkpoint-428/model.safetensors +3 -0
  4. run-4/checkpoint-428/optimizer.pt +3 -0
  5. run-4/checkpoint-428/rng_state.pth +3 -0
  6. run-4/checkpoint-428/scheduler.pt +3 -0
  7. run-4/checkpoint-428/special_tokens_map.json +7 -0
  8. run-4/checkpoint-428/tokenizer.json +0 -0
  9. run-4/checkpoint-428/tokenizer_config.json +55 -0
  10. run-4/checkpoint-428/trainer_state.json +44 -0
  11. run-4/checkpoint-428/training_args.bin +3 -0
  12. run-4/checkpoint-428/vocab.txt +0 -0
  13. run-4/checkpoint-642/config.json +25 -0
  14. run-4/checkpoint-642/model.safetensors +3 -0
  15. run-4/checkpoint-642/optimizer.pt +3 -0
  16. run-4/checkpoint-642/rng_state.pth +3 -0
  17. run-4/checkpoint-642/scheduler.pt +3 -0
  18. run-4/checkpoint-642/special_tokens_map.json +7 -0
  19. run-4/checkpoint-642/tokenizer.json +0 -0
  20. run-4/checkpoint-642/tokenizer_config.json +55 -0
  21. run-4/checkpoint-642/trainer_state.json +60 -0
  22. run-4/checkpoint-642/training_args.bin +3 -0
  23. run-4/checkpoint-642/vocab.txt +0 -0
  24. run-6/checkpoint-14/config.json +25 -0
  25. run-6/checkpoint-14/model.safetensors +3 -0
  26. run-6/checkpoint-14/optimizer.pt +3 -0
  27. run-6/checkpoint-14/rng_state.pth +3 -0
  28. run-6/checkpoint-14/scheduler.pt +3 -0
  29. run-6/checkpoint-14/special_tokens_map.json +7 -0
  30. run-6/checkpoint-14/tokenizer.json +0 -0
  31. run-6/checkpoint-14/tokenizer_config.json +55 -0
  32. run-6/checkpoint-14/trainer_state.json +35 -0
  33. run-6/checkpoint-14/training_args.bin +3 -0
  34. run-6/checkpoint-14/vocab.txt +0 -0
  35. runs/Feb27_17-28-42_b3bc3fede2ea/events.out.tfevents.1709056297.b3bc3fede2ea.5958.20 +3 -0
  36. runs/Feb27_17-28-42_b3bc3fede2ea/events.out.tfevents.1709056309.b3bc3fede2ea.5958.21 +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 sha256:79865c33c7bf98d3964f5869bc9be96a1a7692de8cbdd2aba029b7fbe1cb6e07
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:011028a9801a722058faf4f514b85242abe490577610f4c4d5c0c45055172d32
3
  size 267832560
run-4/checkpoint-428/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": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-4/checkpoint-428/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de4635afdbfc393071a0f639351134660828c1a525b8c750317e6ed999952d1e
3
+ size 267832560
run-4/checkpoint-428/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f52810d262059d699101839d263346170bec919ce721805528411da5af2226f
3
+ size 535727290
run-4/checkpoint-428/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ec30084ded4fa0652dc768e0973cbcfe83e36ae34120d32b70abdc577e58816
3
+ size 14244
run-4/checkpoint-428/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bc7dada64b6e4976f12d172fc581c34413630d1bd373dba1d9713460f45c1a6
3
+ size 1064
run-4/checkpoint-428/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-428/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-428/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-4/checkpoint-428/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.1503623456988113,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-428",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 428,
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": 0.6031935214996338,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7575,
16
+ "eval_samples_per_second": 1376.897,
17
+ "eval_steps_per_second": 87.129,
18
+ "step": 214
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.7723499536514282,
23
+ "eval_matthews_correlation": 0.1503623456988113,
24
+ "eval_runtime": 1.0694,
25
+ "eval_samples_per_second": 975.303,
26
+ "eval_steps_per_second": 61.716,
27
+ "step": 428
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 642,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 3,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 4,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 9.375493052500511e-05,
40
+ "num_train_epochs": 3,
41
+ "per_device_train_batch_size": 4,
42
+ "seed": 39
43
+ }
44
+ }
run-4/checkpoint-428/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96cdd25f5d049df8044e9c1301f4a9a4c9c9e52ba47ffe4bfc2f0bf462dee61d
3
+ size 4984
run-4/checkpoint-428/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-642/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": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-4/checkpoint-642/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a52cf04d17ac14316cfc3215dada5e0ebdceee094ff6e8554769ba219539ad0
3
+ size 267832560
run-4/checkpoint-642/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca0942713b35485042e5508865da82c5975e34d9affa592a990a4a50816c6254
3
+ size 535727290
run-4/checkpoint-642/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e95caafeeca6278437d103826252e39dc6555bd5c0a9081865e5bf8c551ef261
3
+ size 14244
run-4/checkpoint-642/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21a182fc8ccf03c107151e0a0bf5f5c573adab333ad30ab280466ea73c050398
3
+ size 1064
run-4/checkpoint-642/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-642/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-642/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-4/checkpoint-642/trainer_state.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.1802025287466822,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-642",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 642,
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": 0.6031935214996338,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7575,
16
+ "eval_samples_per_second": 1376.897,
17
+ "eval_steps_per_second": 87.129,
18
+ "step": 214
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.7723499536514282,
23
+ "eval_matthews_correlation": 0.1503623456988113,
24
+ "eval_runtime": 1.0694,
25
+ "eval_samples_per_second": 975.303,
26
+ "eval_steps_per_second": 61.716,
27
+ "step": 428
28
+ },
29
+ {
30
+ "epoch": 2.34,
31
+ "grad_norm": 0.33355072140693665,
32
+ "learning_rate": 2.0737071860670912e-05,
33
+ "loss": 0.5788,
34
+ "step": 500
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "eval_loss": 1.2426249980926514,
39
+ "eval_matthews_correlation": 0.1802025287466822,
40
+ "eval_runtime": 0.8186,
41
+ "eval_samples_per_second": 1274.176,
42
+ "eval_steps_per_second": 80.629,
43
+ "step": 642
44
+ }
45
+ ],
46
+ "logging_steps": 500,
47
+ "max_steps": 642,
48
+ "num_input_tokens_seen": 0,
49
+ "num_train_epochs": 3,
50
+ "save_steps": 500,
51
+ "total_flos": 8304050053248.0,
52
+ "train_batch_size": 4,
53
+ "trial_name": null,
54
+ "trial_params": {
55
+ "learning_rate": 9.375493052500511e-05,
56
+ "num_train_epochs": 3,
57
+ "per_device_train_batch_size": 4,
58
+ "seed": 39
59
+ }
60
+ }
run-4/checkpoint-642/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96cdd25f5d049df8044e9c1301f4a9a4c9c9e52ba47ffe4bfc2f0bf462dee61d
3
+ size 4984
run-4/checkpoint-642/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-14/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": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-6/checkpoint-14/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:011028a9801a722058faf4f514b85242abe490577610f4c4d5c0c45055172d32
3
+ size 267832560
run-6/checkpoint-14/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ffac2ef21599707c151368711a1433b846dac1ef8e9c6790356453575f09599
3
+ size 535727290
run-6/checkpoint-14/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:315f1501d8047fb3786e69054afb359f037e75c50e674eb9145d6fc0532700a3
3
+ size 14308
run-6/checkpoint-14/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:151a538db6640f76ea8063425033dc95092205a4dde40cc52ce6a064f5473498
3
+ size 1064
run-6/checkpoint-14/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-14/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-14/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-6/checkpoint-14/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-14",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 14,
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": 0.627941370010376,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7525,
16
+ "eval_samples_per_second": 1386.032,
17
+ "eval_steps_per_second": 87.707,
18
+ "step": 14
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 14,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 1,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 64,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 1.0399546183387383e-05,
31
+ "num_train_epochs": 1,
32
+ "per_device_train_batch_size": 64,
33
+ "seed": 37
34
+ }
35
+ }
run-6/checkpoint-14/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f1c55eb56f5dcac69aa8baa8fa1d8d897ba36e16df8574e21a5ce137b2ef2b7
3
+ size 4984
run-6/checkpoint-14/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Feb27_17-28-42_b3bc3fede2ea/events.out.tfevents.1709056297.b3bc3fede2ea.5958.20 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68754283602d5d51be57779afb671b366ca1250d5c2061706e74f5e65960fdbb
3
+ size 4876
runs/Feb27_17-28-42_b3bc3fede2ea/events.out.tfevents.1709056309.b3bc3fede2ea.5958.21 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6996f243d322f411ffb5978acf050d9ea9af106ad81a8b0336103f0ac8bc8e8f
3
+ size 5220
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96cdd25f5d049df8044e9c1301f4a9a4c9c9e52ba47ffe4bfc2f0bf462dee61d
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f1c55eb56f5dcac69aa8baa8fa1d8d897ba36e16df8574e21a5ce137b2ef2b7
3
  size 4984