Hugging Face's logo

JiAYu1997
/
LLM_Practice001

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Model card Files Metrics Community
JiAYu1997 commited on
Commit
8d0af58
·
verified ·
1 Parent(s): cd0c84f

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. model.safetensors +1 -1
  2. run-1/checkpoint-268/config.json +25 -0
  3. run-1/checkpoint-268/model.safetensors +3 -0
  4. run-1/checkpoint-268/optimizer.pt +3 -0
  5. run-1/checkpoint-268/rng_state.pth +3 -0
  6. run-1/checkpoint-268/scheduler.pt +3 -0
  7. run-1/checkpoint-268/special_tokens_map.json +7 -0
  8. run-1/checkpoint-268/tokenizer.json +0 -0
  9. run-1/checkpoint-268/tokenizer_config.json +55 -0
  10. run-1/checkpoint-268/trainer_state.json +44 -0
  11. run-1/checkpoint-268/training_args.bin +3 -0
  12. run-1/checkpoint-268/vocab.txt +0 -0
  13. run-1/checkpoint-402/config.json +25 -0
  14. run-1/checkpoint-402/model.safetensors +3 -0
  15. run-1/checkpoint-402/optimizer.pt +3 -0
  16. run-1/checkpoint-402/rng_state.pth +3 -0
  17. run-1/checkpoint-402/scheduler.pt +3 -0
  18. run-1/checkpoint-402/special_tokens_map.json +7 -0
  19. run-1/checkpoint-402/tokenizer.json +0 -0
  20. run-1/checkpoint-402/tokenizer_config.json +55 -0
  21. run-1/checkpoint-402/trainer_state.json +53 -0
  22. run-1/checkpoint-402/training_args.bin +3 -0
  23. run-1/checkpoint-402/vocab.txt +0 -0
  24. run-2/checkpoint-268/config.json +25 -0
  25. run-2/checkpoint-268/model.safetensors +3 -0
  26. run-2/checkpoint-268/optimizer.pt +3 -0
  27. run-2/checkpoint-268/rng_state.pth +3 -0
  28. run-2/checkpoint-268/scheduler.pt +3 -0
  29. run-2/checkpoint-268/special_tokens_map.json +7 -0
  30. run-2/checkpoint-268/tokenizer.json +0 -0
  31. run-2/checkpoint-268/tokenizer_config.json +55 -0
  32. run-2/checkpoint-268/trainer_state.json +35 -0
  33. run-2/checkpoint-268/training_args.bin +3 -0
  34. run-2/checkpoint-268/vocab.txt +0 -0
  35. runs/Feb07_07-45-57_5815a830ed1c/events.out.tfevents.1707292902.5815a830ed1c.392.3 +2 -2
  36. runs/Feb07_07-45-57_5815a830ed1c/events.out.tfevents.1707292978.5815a830ed1c.392.4 +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 sha256:9b0270b07bfbec4109b4ddda5753849594e831c4e505a19dd158e923aaf46b8f
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ef6f5d7411f35f77dcb4a60d74b19b0b59316cbe092fbeed288863357d6f045
3
  size 267832560
run-1/checkpoint-268/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": "4.37.2",
24
+ "vocab_size": 30522
25
+ }
run-1/checkpoint-268/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:badb272c388e029c1d5d751bfe70d5a8e1c1b2d0b68d5d853ca3eac3c39b50ea
3
+ size 267832560
run-1/checkpoint-268/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43810cfdaa05c94fbef2a322da8548666d57c5a225b624f541facdd335bff207
3
+ size 535727290
run-1/checkpoint-268/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:457eccb00a09a897f4095458512c62e9795d865a1b3e36ddb88785e2bf323f72
3
+ size 14244
run-1/checkpoint-268/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2884391ff2f26cd1c09f4c8a0b11d8ebc5430fd630345b1ca46ea0b061e7a6a5
3
+ size 1064
run-1/checkpoint-268/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-268/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-268/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-268/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5052273447208777,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-268",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 268,
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": 0.4760828912258148,
14
+ "eval_matthews_correlation": 0.44710293548831637,
15
+ "eval_runtime": 0.7813,
16
+ "eval_samples_per_second": 1335.016,
17
+ "eval_steps_per_second": 84.478,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.4732511639595032,
23
+ "eval_matthews_correlation": 0.5052273447208777,
24
+ "eval_runtime": 1.1006,
25
+ "eval_samples_per_second": 947.7,
26
+ "eval_steps_per_second": 59.97,
27
+ "step": 268
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 402,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 3,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 64,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 2.9805771852415407e-05,
40
+ "num_train_epochs": 3,
41
+ "per_device_train_batch_size": 64,
42
+ "seed": 16
43
+ }
44
+ }
run-1/checkpoint-268/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42dc4a2db4fcbdc1296d623b336dd924ed0f0ce59aefb8c702da40300715a020
3
+ size 4792
run-1/checkpoint-268/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-402/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": "4.37.2",
24
+ "vocab_size": 30522
25
+ }
run-1/checkpoint-402/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bdfcba1c7f038e0c72d9fff4f15b354e41b2cab9faa241913be25a5f1f1a60b
3
+ size 267832560
run-1/checkpoint-402/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d88a4eac3c9bafd037126b2d8190104c74dc8f87f96e8a9106e19f2a58707615
3
+ size 535727290
run-1/checkpoint-402/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5e7118f4588e5f734d3aab73b47621dba72d254b14ee7827f20c37f4533cee6
3
+ size 14244
run-1/checkpoint-402/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:362eb36eab73788d542eb052b6e70f5616910105de8832d7bc7b783277dc7e6d
3
+ size 1064
run-1/checkpoint-402/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-402/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-402/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-402/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5304969997797532,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-402",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 402,
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": 0.4760828912258148,
14
+ "eval_matthews_correlation": 0.44710293548831637,
15
+ "eval_runtime": 0.7813,
16
+ "eval_samples_per_second": 1335.016,
17
+ "eval_steps_per_second": 84.478,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.4732511639595032,
23
+ "eval_matthews_correlation": 0.5052273447208777,
24
+ "eval_runtime": 1.1006,
25
+ "eval_samples_per_second": 947.7,
26
+ "eval_steps_per_second": 59.97,
27
+ "step": 268
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.511177659034729,
32
+ "eval_matthews_correlation": 0.5304969997797532,
33
+ "eval_runtime": 0.8787,
34
+ "eval_samples_per_second": 1186.961,
35
+ "eval_steps_per_second": 75.11,
36
+ "step": 402
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 402,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 3,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 64,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 2.9805771852415407e-05,
49
+ "num_train_epochs": 3,
50
+ "per_device_train_batch_size": 64,
51
+ "seed": 16
52
+ }
53
+ }
run-1/checkpoint-402/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42dc4a2db4fcbdc1296d623b336dd924ed0f0ce59aefb8c702da40300715a020
3
+ size 4792
run-1/checkpoint-402/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-268/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": "4.37.2",
24
+ "vocab_size": 30522
25
+ }
run-2/checkpoint-268/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ef6f5d7411f35f77dcb4a60d74b19b0b59316cbe092fbeed288863357d6f045
3
+ size 267832560
run-2/checkpoint-268/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a59cd672c16f315c81ee7e1b896f596bdc2d984130def6141406606e689b3a0c
3
+ size 535727290
run-2/checkpoint-268/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e12644f927e5ae6ecc7e528516fffc6c27f780f6d27283638d406ad472fc171
3
+ size 14244
run-2/checkpoint-268/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce0445833920e4a19646f6669cab6b9b62507a6ad8c6e54d2e5dcc642618ba29
3
+ size 1064
run-2/checkpoint-268/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-268/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-268/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-268/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3740621403006116,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-268",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 268,
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": 0.5232119560241699,
14
+ "eval_matthews_correlation": 0.3740621403006116,
15
+ "eval_runtime": 0.701,
16
+ "eval_samples_per_second": 1487.933,
17
+ "eval_steps_per_second": 94.155,
18
+ "step": 268
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 268,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 1,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 32,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 1.3298277125166165e-05,
31
+ "num_train_epochs": 1,
32
+ "per_device_train_batch_size": 32,
33
+ "seed": 39
34
+ }
35
+ }
run-2/checkpoint-268/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3017d18ed486b159f5b70b2650dabf79c9ca6bf9a30c732038e7af85f11ca5c9
3
+ size 4792
run-2/checkpoint-268/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Feb07_07-45-57_5815a830ed1c/events.out.tfevents.1707292902.5815a830ed1c.392.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:676994c2cab4f1bce16ad1687923ca14944b5d56c2781619d2bf0fb21acd45b7
3
- size 5025
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df1f1f1be6c4962e250469aa2820bcdd128966aadfc40acc962d777dc46dccbc
3
+ size 5714
runs/Feb07_07-45-57_5815a830ed1c/events.out.tfevents.1707292978.5815a830ed1c.392.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20ce771433a19b6c02a5b236574530c69fc8ca6c3b05c606f1a58e41e15a7a68
3
+ size 5044
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42dc4a2db4fcbdc1296d623b336dd924ed0f0ce59aefb8c702da40300715a020
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3017d18ed486b159f5b70b2650dabf79c9ca6bf9a30c732038e7af85f11ca5c9
3
  size 4792