antalvdb commited on
Commit
a8e9e13
·
verified ·
1 Parent(s): 1ddc7ca

Training in progress, epoch 1

Browse files
Files changed (38) hide show
  1. model.safetensors +1 -1
  2. run-4/checkpoint-28/config.json +25 -0
  3. run-4/checkpoint-28/model.safetensors +3 -0
  4. run-4/checkpoint-28/optimizer.pt +3 -0
  5. run-4/checkpoint-28/rng_state.pth +3 -0
  6. run-4/checkpoint-28/scheduler.pt +3 -0
  7. run-4/checkpoint-28/special_tokens_map.json +7 -0
  8. run-4/checkpoint-28/tokenizer.json +0 -0
  9. run-4/checkpoint-28/tokenizer_config.json +55 -0
  10. run-4/checkpoint-28/trainer_state.json +44 -0
  11. run-4/checkpoint-28/training_args.bin +3 -0
  12. run-4/checkpoint-28/vocab.txt +0 -0
  13. run-4/checkpoint-42/config.json +25 -0
  14. run-4/checkpoint-42/model.safetensors +3 -0
  15. run-4/checkpoint-42/optimizer.pt +3 -0
  16. run-4/checkpoint-42/rng_state.pth +3 -0
  17. run-4/checkpoint-42/scheduler.pt +3 -0
  18. run-4/checkpoint-42/special_tokens_map.json +7 -0
  19. run-4/checkpoint-42/tokenizer.json +0 -0
  20. run-4/checkpoint-42/tokenizer_config.json +55 -0
  21. run-4/checkpoint-42/trainer_state.json +53 -0
  22. run-4/checkpoint-42/training_args.bin +3 -0
  23. run-4/checkpoint-42/vocab.txt +0 -0
  24. run-7/checkpoint-54/config.json +25 -0
  25. run-7/checkpoint-54/model.safetensors +3 -0
  26. run-7/checkpoint-54/optimizer.pt +3 -0
  27. run-7/checkpoint-54/rng_state.pth +3 -0
  28. run-7/checkpoint-54/scheduler.pt +3 -0
  29. run-7/checkpoint-54/special_tokens_map.json +7 -0
  30. run-7/checkpoint-54/tokenizer.json +0 -0
  31. run-7/checkpoint-54/tokenizer_config.json +55 -0
  32. run-7/checkpoint-54/trainer_state.json +35 -0
  33. run-7/checkpoint-54/training_args.bin +3 -0
  34. run-7/checkpoint-54/vocab.txt +0 -0
  35. runs/Jan29_13-40-22_f96070633581/events.out.tfevents.1706536063.f96070633581.4947.7 +3 -0
  36. runs/Jan29_13-40-22_f96070633581/events.out.tfevents.1706536065.f96070633581.4947.8 +3 -0
  37. runs/Jan29_13-40-22_f96070633581/events.out.tfevents.1706536068.f96070633581.4947.9 +3 -0
  38. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:824d8063676fb15079c6517e1cb40ccb4078d854057ad1feef23518a177ccecb
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1041a2b755d0618c627bfa31d39e515627fcb1e921499e92ebbb2b1a83b961f
3
  size 267832560
run-4/checkpoint-28/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": "4.37.1",
24
+ "vocab_size": 30522
25
+ }
run-4/checkpoint-28/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8138cbf184e986b3cefa59102364ec7f0146dd1cd1cb63ab36be90b3c644115f
3
+ size 267832560
run-4/checkpoint-28/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c32341c15fdde72ef88272d78f142457f264f0d5d3540754af09d3eefd9e3c61
3
+ size 535727290
run-4/checkpoint-28/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:054e2e783b8cfd244184cddddd3f5dd2f06e1f8ef5e9815c282f5484cbbeada4
3
+ size 14244
run-4/checkpoint-28/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a591372808a12bdf3fb7cda20cada962b9d2e55f222e98f47249f0f4664a293
3
+ size 1064
run-4/checkpoint-28/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-28/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-28/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-28/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-14",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 28,
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": 0.6169001460075378,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.474,
16
+ "eval_samples_per_second": 2200.348,
17
+ "eval_steps_per_second": 139.236,
18
+ "step": 14
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6125791668891907,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.4826,
25
+ "eval_samples_per_second": 2161.39,
26
+ "eval_steps_per_second": 136.771,
27
+ "step": 28
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 42,
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": 1.0207194391783832e-05,
40
+ "num_train_epochs": 3,
41
+ "per_device_train_batch_size": 64,
42
+ "seed": 1
43
+ }
44
+ }
run-4/checkpoint-28/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:657e90ed8bccab12981cabaf584f7dcc8552922cb99ca8a9499470f76e81ab68
3
+ size 4792
run-4/checkpoint-28/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-42/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": "4.37.1",
24
+ "vocab_size": 30522
25
+ }
run-4/checkpoint-42/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae4e59d6cac3c66169233b35d9999ef70f2202f683bcbe9b926fadf8d22d9ee8
3
+ size 267832560
run-4/checkpoint-42/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ec7118e6031c0f85bfa55ede131c0b907d0564fbf159b8e5ec54fe5a871e336
3
+ size 535727290
run-4/checkpoint-42/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9273ac1908b67fadc9743ec0fe021c17353b88301c845833c1138c1936565683
3
+ size 14244
run-4/checkpoint-42/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eef1c0b1c48fce35fdb6aba30955239c5a6255892cacd9059e566dc082348899
3
+ size 1064
run-4/checkpoint-42/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-42/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-42/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-42/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-14",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 42,
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": 0.6169001460075378,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.474,
16
+ "eval_samples_per_second": 2200.348,
17
+ "eval_steps_per_second": 139.236,
18
+ "step": 14
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6125791668891907,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.4826,
25
+ "eval_samples_per_second": 2161.39,
26
+ "eval_steps_per_second": 136.771,
27
+ "step": 28
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6109025478363037,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 0.482,
34
+ "eval_samples_per_second": 2163.851,
35
+ "eval_steps_per_second": 136.926,
36
+ "step": 42
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 42,
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": 1.0207194391783832e-05,
49
+ "num_train_epochs": 3,
50
+ "per_device_train_batch_size": 64,
51
+ "seed": 1
52
+ }
53
+ }
run-4/checkpoint-42/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:657e90ed8bccab12981cabaf584f7dcc8552922cb99ca8a9499470f76e81ab68
3
+ size 4792
run-4/checkpoint-42/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-54/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": "4.37.1",
24
+ "vocab_size": 30522
25
+ }
run-7/checkpoint-54/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1041a2b755d0618c627bfa31d39e515627fcb1e921499e92ebbb2b1a83b961f
3
+ size 267832560
run-7/checkpoint-54/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ae81cf682c19acb18963ea4482721095c802ca99ea181655416160b752080cd
3
+ size 535727290
run-7/checkpoint-54/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cb90db51ad0a5deade0864189b711e5979117ec021a191663b479054e712a2d
3
+ size 14244
run-7/checkpoint-54/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14f3909d1edbf22840b165de29b0376eb2688efa3af29167b98576da3d5d460b
3
+ size 1064
run-7/checkpoint-54/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-7/checkpoint-54/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-54/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-7/checkpoint-54/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.06558874629318973,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-54",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 54,
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": 0.5851961970329285,
14
+ "eval_matthews_correlation": 0.06558874629318973,
15
+ "eval_runtime": 0.479,
16
+ "eval_samples_per_second": 2177.373,
17
+ "eval_steps_per_second": 137.782,
18
+ "step": 54
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 162,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 3,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 16,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 3.674569911456489e-05,
31
+ "num_train_epochs": 3,
32
+ "per_device_train_batch_size": 16,
33
+ "seed": 4
34
+ }
35
+ }
run-7/checkpoint-54/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe1109669fdc81f8d310b4dd7aeb333be85e0b51262046c765f4a0c37a09db90
3
+ size 4792
run-7/checkpoint-54/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Jan29_13-40-22_f96070633581/events.out.tfevents.1706536063.f96070633581.4947.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29b3654aaaacb3ac57022eddbe022b62d84ca07d493db88ccdb4f3271264bdad
3
+ size 4659
runs/Jan29_13-40-22_f96070633581/events.out.tfevents.1706536065.f96070633581.4947.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d9f9c69dcf096aa22e27623d1c4530cf4cef781e914ad440b67ef88645a0e0b
3
+ size 4659
runs/Jan29_13-40-22_f96070633581/events.out.tfevents.1706536068.f96070633581.4947.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b0ec70c0d6027107f1812b90c28f8a651a4f39b44619f1e8e6e8695951eea3f
3
+ size 5677
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:657e90ed8bccab12981cabaf584f7dcc8552922cb99ca8a9499470f76e81ab68
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe1109669fdc81f8d310b4dd7aeb333be85e0b51262046c765f4a0c37a09db90
3
  size 4792