Hugging Face's logo

halu1003
/
LLMClassWork1

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Metrics Community
halu1003 commited on
Commit
72788ee
·
1 Parent(s): 1daebfb

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. model.safetensors +1 -1
  2. run-0/checkpoint-536/config.json +25 -0
  3. run-0/checkpoint-536/model.safetensors +3 -0
  4. run-0/checkpoint-536/optimizer.pt +3 -0
  5. run-0/checkpoint-536/rng_state.pth +3 -0
  6. run-0/checkpoint-536/scheduler.pt +3 -0
  7. run-0/checkpoint-536/special_tokens_map.json +7 -0
  8. run-0/checkpoint-536/tokenizer.json +0 -0
  9. run-0/checkpoint-536/tokenizer_config.json +55 -0
  10. run-0/checkpoint-536/trainer_state.json +50 -0
  11. run-0/checkpoint-536/training_args.bin +3 -0
  12. run-0/checkpoint-536/vocab.txt +0 -0
  13. run-0/checkpoint-804/config.json +25 -0
  14. run-0/checkpoint-804/model.safetensors +3 -0
  15. run-0/checkpoint-804/optimizer.pt +3 -0
  16. run-0/checkpoint-804/rng_state.pth +3 -0
  17. run-0/checkpoint-804/scheduler.pt +3 -0
  18. run-0/checkpoint-804/special_tokens_map.json +7 -0
  19. run-0/checkpoint-804/tokenizer.json +0 -0
  20. run-0/checkpoint-804/tokenizer_config.json +55 -0
  21. run-0/checkpoint-804/trainer_state.json +59 -0
  22. run-0/checkpoint-804/training_args.bin +3 -0
  23. run-0/checkpoint-804/vocab.txt +0 -0
  24. run-1/checkpoint-134/config.json +25 -0
  25. run-1/checkpoint-134/model.safetensors +3 -0
  26. run-1/checkpoint-134/optimizer.pt +3 -0
  27. run-1/checkpoint-134/rng_state.pth +3 -0
  28. run-1/checkpoint-134/scheduler.pt +3 -0
  29. run-1/checkpoint-134/special_tokens_map.json +7 -0
  30. run-1/checkpoint-134/tokenizer.json +0 -0
  31. run-1/checkpoint-134/tokenizer_config.json +55 -0
  32. run-1/checkpoint-134/trainer_state.json +35 -0
  33. run-1/checkpoint-134/training_args.bin +3 -0
  34. run-1/checkpoint-134/vocab.txt +0 -0
  35. runs/Dec23_02-22-21_04248f4b0c3a/events.out.tfevents.1703298577.04248f4b0c3a.492.2 +2 -2
  36. runs/Dec23_02-22-21_04248f4b0c3a/events.out.tfevents.1703298679.04248f4b0c3a.492.3 +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:c76ac2c7c0d5b97e0538cb1c06213e6f3c2e465ebefa114d4639987f439674db
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ff9f6968410a06a7e54fed912c3823c6e302e93856d594b0391906d3fcc1aae
3
  size 267832560
run-0/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": "4.36.2",
24
+ "vocab_size": 30522
25
+ }
run-0/checkpoint-536/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0d8d658a1aab0a5d83c4f6d10f2c7478018a2c14f539e05fc488439058de0ac
3
+ size 267832560
run-0/checkpoint-536/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6231d35fc5ff8a9b2189ddb75bd750d5e769ec908b0544b7711f51f7d19899e1
3
+ size 535727290
run-0/checkpoint-536/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3677640bdcfe3e1ceab4bebbdff4b248f96d31e04cef5e72dd1bf4bfb7204a5
3
+ size 14308
run-0/checkpoint-536/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7be41c9acf3601c4f6fcf820dee2f1e97e1c699f50682637ba3e5cccd034b8b9
3
+ size 1064
run-0/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-0/checkpoint-536/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/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-0/checkpoint-536/trainer_state.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4677857815103733,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-536",
4
+ "epoch": 2.0,
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": 0.49786698818206787,
14
+ "eval_matthews_correlation": 0.4184145751988745,
15
+ "eval_runtime": 0.7269,
16
+ "eval_samples_per_second": 1434.823,
17
+ "eval_steps_per_second": 90.794,
18
+ "step": 268
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "learning_rate": 4.774138267483819e-06,
23
+ "loss": 0.4832,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_loss": 0.4944550395011902,
29
+ "eval_matthews_correlation": 0.4677857815103733,
30
+ "eval_runtime": 0.718,
31
+ "eval_samples_per_second": 1452.645,
32
+ "eval_steps_per_second": 91.922,
33
+ "step": 536
34
+ }
35
+ ],
36
+ "logging_steps": 500,
37
+ "max_steps": 804,
38
+ "num_input_tokens_seen": 0,
39
+ "num_train_epochs": 3,
40
+ "save_steps": 500,
41
+ "total_flos": 95617141643160.0,
42
+ "train_batch_size": 32,
43
+ "trial_name": null,
44
+ "trial_params": {
45
+ "learning_rate": 1.2626339365319049e-05,
46
+ "num_train_epochs": 3,
47
+ "per_device_train_batch_size": 32,
48
+ "seed": 26
49
+ }
50
+ }
run-0/checkpoint-536/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7e9f7fe4fd4c0b5f75f4b1edba90e62e58e68cc29d0c4d5b77fd765418da22f
3
+ size 4792
run-0/checkpoint-536/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
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": "4.36.2",
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 sha256:63c6403a6a52b0242ea0d4471d999d2ed8dbcef6a32979b7103bc6f56e152b0a
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:d1f3d54a81bc00afc3bb0d6c6893d8982c4c74daea63e905f6c1b63fe16cc51c
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 sha256:29620bb2ec4550a151bf2c20279c633b6c802f2d2e5efd90f270a16177f71113
3
+ size 14308
run-0/checkpoint-804/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6276434d38891f7716a9fdb7edf962d9520f6e4e7b2519bbd518661f19a7681
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 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4797446434500675,
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": 0.49786698818206787,
14
+ "eval_matthews_correlation": 0.4184145751988745,
15
+ "eval_runtime": 0.7269,
16
+ "eval_samples_per_second": 1434.823,
17
+ "eval_steps_per_second": 90.794,
18
+ "step": 268
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "learning_rate": 4.774138267483819e-06,
23
+ "loss": 0.4832,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_loss": 0.4944550395011902,
29
+ "eval_matthews_correlation": 0.4677857815103733,
30
+ "eval_runtime": 0.718,
31
+ "eval_samples_per_second": 1452.645,
32
+ "eval_steps_per_second": 91.922,
33
+ "step": 536
34
+ },
35
+ {
36
+ "epoch": 3.0,
37
+ "eval_loss": 0.5118187665939331,
38
+ "eval_matthews_correlation": 0.4797446434500675,
39
+ "eval_runtime": 1.1155,
40
+ "eval_samples_per_second": 935.047,
41
+ "eval_steps_per_second": 59.169,
42
+ "step": 804
43
+ }
44
+ ],
45
+ "logging_steps": 500,
46
+ "max_steps": 804,
47
+ "num_input_tokens_seen": 0,
48
+ "num_train_epochs": 3,
49
+ "save_steps": 500,
50
+ "total_flos": 95617141643160.0,
51
+ "train_batch_size": 32,
52
+ "trial_name": null,
53
+ "trial_params": {
54
+ "learning_rate": 1.2626339365319049e-05,
55
+ "num_train_epochs": 3,
56
+ "per_device_train_batch_size": 32,
57
+ "seed": 26
58
+ }
59
+ }
run-0/checkpoint-804/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7e9f7fe4fd4c0b5f75f4b1edba90e62e58e68cc29d0c4d5b77fd765418da22f
3
+ size 4792
run-0/checkpoint-804/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-134/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-1/checkpoint-134/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ff9f6968410a06a7e54fed912c3823c6e302e93856d594b0391906d3fcc1aae
3
+ size 267832560
run-1/checkpoint-134/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b42f1b1522eebb8d40ebb7c4305c876dc3ab28af603b49cffe7bea47600c4886
3
+ size 535727290
run-1/checkpoint-134/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0da320c4f66f15dce8c7e2f3aca2047176222eb5d969ff3492ff1f198325a7dd
3
+ size 14244
run-1/checkpoint-134/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ae6af0781434c85d58ae355c507c580773672e8006ff1f0b5b491a99a4f52f2
3
+ size 1064
run-1/checkpoint-134/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-134/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-134/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-134/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.44075455043157863,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-134",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 134,
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": 0.47572973370552063,
14
+ "eval_matthews_correlation": 0.44075455043157863,
15
+ "eval_runtime": 0.7472,
16
+ "eval_samples_per_second": 1395.808,
17
+ "eval_steps_per_second": 88.325,
18
+ "step": 134
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 402,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 3,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 64,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 6.238111577485738e-05,
31
+ "num_train_epochs": 3,
32
+ "per_device_train_batch_size": 64,
33
+ "seed": 5
34
+ }
35
+ }
run-1/checkpoint-134/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e50c6849763306314de124bc4b6d43aafce6a6fe2ad2c143497ab357b26a273
3
+ size 4792
run-1/checkpoint-134/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec23_02-22-21_04248f4b0c3a/events.out.tfevents.1703298577.04248f4b0c3a.492.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e3c478d4b33851e33b3b62bc9ddae40b9d874628e2fb39284dfbd8d09e4667e
3
- size 4687
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c647b2cbbed05ea6e6f4110fde0b089932bfe126773f5acb8546d0ae9478d18
3
+ size 5868
runs/Dec23_02-22-21_04248f4b0c3a/events.out.tfevents.1703298679.04248f4b0c3a.492.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f4989fa55602dcc148981a83338cd8ba489725cc15a33dbc66b50cdc9c9c1d9
3
+ size 5020
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7e9f7fe4fd4c0b5f75f4b1edba90e62e58e68cc29d0c4d5b77fd765418da22f
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e50c6849763306314de124bc4b6d43aafce6a6fe2ad2c143497ab357b26a273
3
  size 4792