Hugging Face's logo

apuku0723
/
AIALMWork01

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Metrics Community
apuku0723 commited on
Commit
4fb2117
·
1 Parent(s): 2e39f5c

Training in progress, epoch 3

Browse files
Files changed (35) hide show
  1. model.safetensors +1 -1
  2. run-2/checkpoint-1070/config.json +25 -0
  3. run-2/checkpoint-1070/model.safetensors +3 -0
  4. run-2/checkpoint-1070/optimizer.pt +3 -0
  5. run-2/checkpoint-1070/rng_state.pth +3 -0
  6. run-2/checkpoint-1070/scheduler.pt +3 -0
  7. run-2/checkpoint-1070/special_tokens_map.json +7 -0
  8. run-2/checkpoint-1070/tokenizer.json +0 -0
  9. run-2/checkpoint-1070/tokenizer_config.json +55 -0
  10. run-2/checkpoint-1070/trainer_state.json +56 -0
  11. run-2/checkpoint-1070/training_args.bin +3 -0
  12. run-2/checkpoint-1070/vocab.txt +0 -0
  13. run-2/checkpoint-1605/config.json +25 -0
  14. run-2/checkpoint-1605/model.safetensors +3 -0
  15. run-2/checkpoint-1605/optimizer.pt +3 -0
  16. run-2/checkpoint-1605/rng_state.pth +3 -0
  17. run-2/checkpoint-1605/scheduler.pt +3 -0
  18. run-2/checkpoint-1605/special_tokens_map.json +7 -0
  19. run-2/checkpoint-1605/tokenizer.json +0 -0
  20. run-2/checkpoint-1605/tokenizer_config.json +55 -0
  21. run-2/checkpoint-1605/trainer_state.json +71 -0
  22. run-2/checkpoint-1605/training_args.bin +3 -0
  23. run-2/checkpoint-1605/vocab.txt +0 -0
  24. run-2/checkpoint-535/config.json +25 -0
  25. run-2/checkpoint-535/model.safetensors +3 -0
  26. run-2/checkpoint-535/optimizer.pt +3 -0
  27. run-2/checkpoint-535/rng_state.pth +3 -0
  28. run-2/checkpoint-535/scheduler.pt +3 -0
  29. run-2/checkpoint-535/special_tokens_map.json +7 -0
  30. run-2/checkpoint-535/tokenizer.json +0 -0
  31. run-2/checkpoint-535/tokenizer_config.json +55 -0
  32. run-2/checkpoint-535/trainer_state.json +41 -0
  33. run-2/checkpoint-535/training_args.bin +3 -0
  34. run-2/checkpoint-535/vocab.txt +0 -0
  35. runs/Dec23_02-13-09_9bda7ec8aa80/events.out.tfevents.1703299869.9bda7ec8aa80.207.4 +2 -2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fa71b1c11813fbeacbd5788d1d83e7939f06f63743274fb23af74cefbe5fadc
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98e549dcae2464c99aa1bb502cc607b4f7ae0454092cf01e5b4587ab937d7f3c
3
  size 267832560
run-2/checkpoint-1070/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-2/checkpoint-1070/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74953d46e7f6aa6c592c6f1e8474a4eed9ce19b73209393cd0cd47c6431e3e91
3
+ size 267832560
run-2/checkpoint-1070/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5db06e71964dcad4695d18000ed08c856fe2e883332e040f04bd8dc0ab67cc36
3
+ size 535727290
run-2/checkpoint-1070/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de8b0598dc4c52ee1f8a38555a20c9b46272178c9a36e37c2bcd6b909c944afb
3
+ size 14244
run-2/checkpoint-1070/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd888fc6cacb03bec520cea04536ff22f9fb0623a22364e6e5ff35ba732a4894
3
+ size 1064
run-2/checkpoint-1070/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-2/checkpoint-1070/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-1070/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-2/checkpoint-1070/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-535",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1070,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.93,
13
+ "learning_rate": 1.2971511744265264e-06,
14
+ "loss": 0.6123,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_loss": 0.5840290784835815,
20
+ "eval_matthews_correlation": 0.0,
21
+ "eval_runtime": 0.7468,
22
+ "eval_samples_per_second": 1396.633,
23
+ "eval_steps_per_second": 88.378,
24
+ "step": 535
25
+ },
26
+ {
27
+ "epoch": 1.87,
28
+ "learning_rate": 9.016782553940487e-07,
29
+ "loss": 0.5516,
30
+ "step": 1000
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_loss": 0.5512143969535828,
35
+ "eval_matthews_correlation": 0.0,
36
+ "eval_runtime": 0.8297,
37
+ "eval_samples_per_second": 1257.023,
38
+ "eval_steps_per_second": 79.543,
39
+ "step": 1070
40
+ }
41
+ ],
42
+ "logging_steps": 500,
43
+ "max_steps": 2140,
44
+ "num_input_tokens_seen": 0,
45
+ "num_train_epochs": 4,
46
+ "save_steps": 500,
47
+ "total_flos": 85474071532008.0,
48
+ "train_batch_size": 16,
49
+ "trial_name": null,
50
+ "trial_params": {
51
+ "learning_rate": 1.692624093459004e-06,
52
+ "num_train_epochs": 4,
53
+ "per_device_train_batch_size": 16,
54
+ "seed": 6
55
+ }
56
+ }
run-2/checkpoint-1070/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddf6d1e41913d6b346143de2ae364997298bb25d96e0cee1326bb74d31817768
3
+ size 4792
run-2/checkpoint-1070/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-1605/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-2/checkpoint-1605/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98e549dcae2464c99aa1bb502cc607b4f7ae0454092cf01e5b4587ab937d7f3c
3
+ size 267832560
run-2/checkpoint-1605/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4a82fc86f912034041f0fe663d951efaa454e0f4aade4b348fa28401531de50
3
+ size 535727290
run-2/checkpoint-1605/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cb90214f5e58f0abd7ac782aef5925047b906217a608278afe78cb3d96a555f
3
+ size 14244
run-2/checkpoint-1605/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d9292823332bce32537c4c3fd18cf789d828698babc12a7cf899ba26a5d8927
3
+ size 1064
run-2/checkpoint-1605/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-2/checkpoint-1605/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-1605/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-2/checkpoint-1605/trainer_state.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.20735838851492006,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-1605",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1605,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.93,
13
+ "learning_rate": 1.2971511744265264e-06,
14
+ "loss": 0.6123,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_loss": 0.5840290784835815,
20
+ "eval_matthews_correlation": 0.0,
21
+ "eval_runtime": 0.7468,
22
+ "eval_samples_per_second": 1396.633,
23
+ "eval_steps_per_second": 88.378,
24
+ "step": 535
25
+ },
26
+ {
27
+ "epoch": 1.87,
28
+ "learning_rate": 9.016782553940487e-07,
29
+ "loss": 0.5516,
30
+ "step": 1000
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_loss": 0.5512143969535828,
35
+ "eval_matthews_correlation": 0.0,
36
+ "eval_runtime": 0.8297,
37
+ "eval_samples_per_second": 1257.023,
38
+ "eval_steps_per_second": 79.543,
39
+ "step": 1070
40
+ },
41
+ {
42
+ "epoch": 2.8,
43
+ "learning_rate": 5.062053363615713e-07,
44
+ "loss": 0.5157,
45
+ "step": 1500
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_loss": 0.5409293174743652,
50
+ "eval_matthews_correlation": 0.20735838851492006,
51
+ "eval_runtime": 0.7486,
52
+ "eval_samples_per_second": 1393.339,
53
+ "eval_steps_per_second": 88.169,
54
+ "step": 1605
55
+ }
56
+ ],
57
+ "logging_steps": 500,
58
+ "max_steps": 2140,
59
+ "num_input_tokens_seen": 0,
60
+ "num_train_epochs": 4,
61
+ "save_steps": 500,
62
+ "total_flos": 128478888074592.0,
63
+ "train_batch_size": 16,
64
+ "trial_name": null,
65
+ "trial_params": {
66
+ "learning_rate": 1.692624093459004e-06,
67
+ "num_train_epochs": 4,
68
+ "per_device_train_batch_size": 16,
69
+ "seed": 6
70
+ }
71
+ }
run-2/checkpoint-1605/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddf6d1e41913d6b346143de2ae364997298bb25d96e0cee1326bb74d31817768
3
+ size 4792
run-2/checkpoint-1605/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-535/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-2/checkpoint-535/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fa71b1c11813fbeacbd5788d1d83e7939f06f63743274fb23af74cefbe5fadc
3
+ size 267832560
run-2/checkpoint-535/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad1dcfb9c309f79737b65f8003b3836af4792d1a7f6116560e7487997ac4cdb2
3
+ size 535727290
run-2/checkpoint-535/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c88b090636b6b9c51c55a1dc74026463325b62565ccc9351a9a529deb76af73e
3
+ size 14244
run-2/checkpoint-535/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba57e677df3ba1396881fc1e3a8d210f9c1936d5038a692b782d32709c64f010
3
+ size 1064
run-2/checkpoint-535/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-2/checkpoint-535/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-535/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-2/checkpoint-535/trainer_state.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-535",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 535,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.93,
13
+ "learning_rate": 1.2971511744265264e-06,
14
+ "loss": 0.6123,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_loss": 0.5840290784835815,
20
+ "eval_matthews_correlation": 0.0,
21
+ "eval_runtime": 0.7468,
22
+ "eval_samples_per_second": 1396.633,
23
+ "eval_steps_per_second": 88.378,
24
+ "step": 535
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 2140,
29
+ "num_input_tokens_seen": 0,
30
+ "num_train_epochs": 4,
31
+ "save_steps": 500,
32
+ "total_flos": 42724875672768.0,
33
+ "train_batch_size": 16,
34
+ "trial_name": null,
35
+ "trial_params": {
36
+ "learning_rate": 1.692624093459004e-06,
37
+ "num_train_epochs": 4,
38
+ "per_device_train_batch_size": 16,
39
+ "seed": 6
40
+ }
41
+ }
run-2/checkpoint-535/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddf6d1e41913d6b346143de2ae364997298bb25d96e0cee1326bb74d31817768
3
+ size 4792
run-2/checkpoint-535/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec23_02-13-09_9bda7ec8aa80/events.out.tfevents.1703299869.9bda7ec8aa80.207.4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3cda9ccf3ea7964ac8c575349cd21884bd2733a6a317bf220fa2803a840998a
3
- size 4998
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac4688907488c1beb1dd302b78481ba5f65db52ad16b9fde23a6fc9ed6bc61fb
3
+ size 6671