nstrn-mo commited on
Commit
46bb4e1
·
verified ·
1 Parent(s): 4fc8138

Training in progress, epoch 1

Browse files
Files changed (35) hide show
  1. model.safetensors +1 -1
  2. run-5/checkpoint-498/config.json +56 -0
  3. run-5/checkpoint-498/model.safetensors +3 -0
  4. run-5/checkpoint-498/optimizer.pt +3 -0
  5. run-5/checkpoint-498/rng_state.pth +3 -0
  6. run-5/checkpoint-498/scheduler.pt +3 -0
  7. run-5/checkpoint-498/special_tokens_map.json +7 -0
  8. run-5/checkpoint-498/tokenizer.json +0 -0
  9. run-5/checkpoint-498/tokenizer_config.json +55 -0
  10. run-5/checkpoint-498/trainer_state.json +60 -0
  11. run-5/checkpoint-498/training_args.bin +3 -0
  12. run-5/checkpoint-498/vocab.txt +0 -0
  13. run-5/checkpoint-747/config.json +56 -0
  14. run-5/checkpoint-747/model.safetensors +3 -0
  15. run-5/checkpoint-747/optimizer.pt +3 -0
  16. run-5/checkpoint-747/rng_state.pth +3 -0
  17. run-5/checkpoint-747/scheduler.pt +3 -0
  18. run-5/checkpoint-747/special_tokens_map.json +7 -0
  19. run-5/checkpoint-747/tokenizer.json +0 -0
  20. run-5/checkpoint-747/tokenizer_config.json +55 -0
  21. run-5/checkpoint-747/trainer_state.json +79 -0
  22. run-5/checkpoint-747/training_args.bin +3 -0
  23. run-5/checkpoint-747/vocab.txt +0 -0
  24. run-6/checkpoint-249/config.json +56 -0
  25. run-6/checkpoint-249/model.safetensors +3 -0
  26. run-6/checkpoint-249/optimizer.pt +3 -0
  27. run-6/checkpoint-249/rng_state.pth +3 -0
  28. run-6/checkpoint-249/scheduler.pt +3 -0
  29. run-6/checkpoint-249/special_tokens_map.json +7 -0
  30. run-6/checkpoint-249/tokenizer.json +0 -0
  31. run-6/checkpoint-249/tokenizer_config.json +55 -0
  32. run-6/checkpoint-249/trainer_state.json +48 -0
  33. run-6/checkpoint-249/training_args.bin +3 -0
  34. run-6/checkpoint-249/vocab.txt +0 -0
  35. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c0c4a9a6aa17fec80de2329bf045a275e08108d5fda73f4b5d673da502d3626
3
  size 430942044
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2017ae47e0a4871c135db9e8fce17c6a7328851cec82271fc81e4878822fab8
3
  size 430942044
run-5/checkpoint-498/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nstrn-mo/bert-finetuned-arc-ner-hp",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": 0,
14
+ "1": 1,
15
+ "2": 2,
16
+ "3": 3,
17
+ "4": 4,
18
+ "5": 5,
19
+ "6": 6,
20
+ "7": 7,
21
+ "8": 8,
22
+ "9": 9,
23
+ "10": 10,
24
+ "11": 11,
25
+ "12": 12
26
+ },
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 3072,
29
+ "label2id": {
30
+ "0": 0,
31
+ "1": 1,
32
+ "2": 2,
33
+ "3": 3,
34
+ "4": 4,
35
+ "5": 5,
36
+ "6": 6,
37
+ "7": 7,
38
+ "8": 8,
39
+ "9": 9,
40
+ "10": 10,
41
+ "11": 11,
42
+ "12": 12
43
+ },
44
+ "layer_norm_eps": 1e-12,
45
+ "max_position_embeddings": 512,
46
+ "model_type": "bert",
47
+ "num_attention_heads": 12,
48
+ "num_hidden_layers": 12,
49
+ "pad_token_id": 0,
50
+ "position_embedding_type": "absolute",
51
+ "torch_dtype": "float32",
52
+ "transformers_version": "4.45.2",
53
+ "type_vocab_size": 2,
54
+ "use_cache": true,
55
+ "vocab_size": 28996
56
+ }
run-5/checkpoint-498/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2383ceca42c4a69ce38c4330839bbe8eadf423e903452a11a16d89b8b0c1fe53
3
+ size 430942044
run-5/checkpoint-498/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4c47cc22687691a3301ce2909b4d8307cae20fc45acff617d4fe16a881de121
3
+ size 861998266
run-5/checkpoint-498/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a52e1687874240dc2f195388b3a14e21795a08a2e06360226802394635c650d
3
+ size 13990
run-5/checkpoint-498/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3884006ffddc2b35f3f6494dd03d292ec5e01836534f3e63be09fcba0fc3a6a5
3
+ size 1064
run-5/checkpoint-498/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-5/checkpoint-498/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-498/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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
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": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-5/checkpoint-498/trainer_state.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 498,
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_accuracy": 0.9474281226822564,
14
+ "eval_f1": 0.5983899821109123,
15
+ "eval_loss": 0.2598363757133484,
16
+ "eval_precision": 0.5280189423835833,
17
+ "eval_recall": 0.6904024767801857,
18
+ "eval_runtime": 2.6948,
19
+ "eval_samples_per_second": 315.049,
20
+ "eval_steps_per_second": 39.706,
21
+ "step": 249
22
+ },
23
+ {
24
+ "epoch": 2.0,
25
+ "eval_accuracy": 0.9475153789101697,
26
+ "eval_f1": 0.5929243170622481,
27
+ "eval_loss": 0.2730964422225952,
28
+ "eval_precision": 0.5237341772151899,
29
+ "eval_recall": 0.6831785345717234,
30
+ "eval_runtime": 2.7275,
31
+ "eval_samples_per_second": 311.27,
32
+ "eval_steps_per_second": 39.23,
33
+ "step": 498
34
+ }
35
+ ],
36
+ "logging_steps": 500,
37
+ "max_steps": 747,
38
+ "num_input_tokens_seen": 0,
39
+ "num_train_epochs": 3,
40
+ "save_steps": 500,
41
+ "stateful_callbacks": {
42
+ "TrainerControl": {
43
+ "args": {
44
+ "should_epoch_stop": false,
45
+ "should_evaluate": false,
46
+ "should_log": false,
47
+ "should_save": true,
48
+ "should_training_stop": false
49
+ },
50
+ "attributes": {}
51
+ }
52
+ },
53
+ "total_flos": 0,
54
+ "train_batch_size": 8,
55
+ "trial_name": null,
56
+ "trial_params": {
57
+ "learning_rate": 3.779200281057872e-06,
58
+ "weight_decay": 0.0005857220487781096
59
+ }
60
+ }
run-5/checkpoint-498/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:635c431a465c55743bd7814ca8044d4f39265cc9481fdbf307fcf59409d1cf73
3
+ size 5240
run-5/checkpoint-498/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-747/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nstrn-mo/bert-finetuned-arc-ner-hp",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": 0,
14
+ "1": 1,
15
+ "2": 2,
16
+ "3": 3,
17
+ "4": 4,
18
+ "5": 5,
19
+ "6": 6,
20
+ "7": 7,
21
+ "8": 8,
22
+ "9": 9,
23
+ "10": 10,
24
+ "11": 11,
25
+ "12": 12
26
+ },
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 3072,
29
+ "label2id": {
30
+ "0": 0,
31
+ "1": 1,
32
+ "2": 2,
33
+ "3": 3,
34
+ "4": 4,
35
+ "5": 5,
36
+ "6": 6,
37
+ "7": 7,
38
+ "8": 8,
39
+ "9": 9,
40
+ "10": 10,
41
+ "11": 11,
42
+ "12": 12
43
+ },
44
+ "layer_norm_eps": 1e-12,
45
+ "max_position_embeddings": 512,
46
+ "model_type": "bert",
47
+ "num_attention_heads": 12,
48
+ "num_hidden_layers": 12,
49
+ "pad_token_id": 0,
50
+ "position_embedding_type": "absolute",
51
+ "torch_dtype": "float32",
52
+ "transformers_version": "4.45.2",
53
+ "type_vocab_size": 2,
54
+ "use_cache": true,
55
+ "vocab_size": 28996
56
+ }
run-5/checkpoint-747/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f842fefdf943bc33291689d3390fe43bba076b55531c82ccfe4329618330b4a8
3
+ size 430942044
run-5/checkpoint-747/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bd5d1e1bff51cc1e3901f76f81e9573d4540552be484a290a45f4b3ee0ce3b2
3
+ size 861998266
run-5/checkpoint-747/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f0b7659a63e1836612be0a090b93019e7f4209ad01bfffa613498191b369ed9
3
+ size 13990
run-5/checkpoint-747/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6085e7b2717cf718ae603778939c827f20442bf4a931cc02597e2d7880ba4186
3
+ size 1064
run-5/checkpoint-747/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-5/checkpoint-747/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-747/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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
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": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-5/checkpoint-747/trainer_state.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 747,
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_accuracy": 0.9474281226822564,
14
+ "eval_f1": 0.5983899821109123,
15
+ "eval_loss": 0.2598363757133484,
16
+ "eval_precision": 0.5280189423835833,
17
+ "eval_recall": 0.6904024767801857,
18
+ "eval_runtime": 2.6948,
19
+ "eval_samples_per_second": 315.049,
20
+ "eval_steps_per_second": 39.706,
21
+ "step": 249
22
+ },
23
+ {
24
+ "epoch": 2.0,
25
+ "eval_accuracy": 0.9475153789101697,
26
+ "eval_f1": 0.5929243170622481,
27
+ "eval_loss": 0.2730964422225952,
28
+ "eval_precision": 0.5237341772151899,
29
+ "eval_recall": 0.6831785345717234,
30
+ "eval_runtime": 2.7275,
31
+ "eval_samples_per_second": 311.27,
32
+ "eval_steps_per_second": 39.23,
33
+ "step": 498
34
+ },
35
+ {
36
+ "epoch": 2.0080321285140563,
37
+ "grad_norm": 0.12022259831428528,
38
+ "learning_rate": 1.2496150862400192e-06,
39
+ "loss": 0.0129,
40
+ "step": 500
41
+ },
42
+ {
43
+ "epoch": 3.0,
44
+ "eval_accuracy": 0.9469918415426901,
45
+ "eval_f1": 0.5942806076854334,
46
+ "eval_loss": 0.27816858887672424,
47
+ "eval_precision": 0.5240346729708432,
48
+ "eval_recall": 0.6862745098039216,
49
+ "eval_runtime": 2.758,
50
+ "eval_samples_per_second": 307.834,
51
+ "eval_steps_per_second": 38.796,
52
+ "step": 747
53
+ }
54
+ ],
55
+ "logging_steps": 500,
56
+ "max_steps": 747,
57
+ "num_input_tokens_seen": 0,
58
+ "num_train_epochs": 3,
59
+ "save_steps": 500,
60
+ "stateful_callbacks": {
61
+ "TrainerControl": {
62
+ "args": {
63
+ "should_epoch_stop": false,
64
+ "should_evaluate": false,
65
+ "should_log": false,
66
+ "should_save": true,
67
+ "should_training_stop": true
68
+ },
69
+ "attributes": {}
70
+ }
71
+ },
72
+ "total_flos": 134021308141506.0,
73
+ "train_batch_size": 8,
74
+ "trial_name": null,
75
+ "trial_params": {
76
+ "learning_rate": 3.779200281057872e-06,
77
+ "weight_decay": 0.0005857220487781096
78
+ }
79
+ }
run-5/checkpoint-747/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:635c431a465c55743bd7814ca8044d4f39265cc9481fdbf307fcf59409d1cf73
3
+ size 5240
run-5/checkpoint-747/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-249/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nstrn-mo/bert-finetuned-arc-ner-hp",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": 0,
14
+ "1": 1,
15
+ "2": 2,
16
+ "3": 3,
17
+ "4": 4,
18
+ "5": 5,
19
+ "6": 6,
20
+ "7": 7,
21
+ "8": 8,
22
+ "9": 9,
23
+ "10": 10,
24
+ "11": 11,
25
+ "12": 12
26
+ },
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 3072,
29
+ "label2id": {
30
+ "0": 0,
31
+ "1": 1,
32
+ "2": 2,
33
+ "3": 3,
34
+ "4": 4,
35
+ "5": 5,
36
+ "6": 6,
37
+ "7": 7,
38
+ "8": 8,
39
+ "9": 9,
40
+ "10": 10,
41
+ "11": 11,
42
+ "12": 12
43
+ },
44
+ "layer_norm_eps": 1e-12,
45
+ "max_position_embeddings": 512,
46
+ "model_type": "bert",
47
+ "num_attention_heads": 12,
48
+ "num_hidden_layers": 12,
49
+ "pad_token_id": 0,
50
+ "position_embedding_type": "absolute",
51
+ "torch_dtype": "float32",
52
+ "transformers_version": "4.45.2",
53
+ "type_vocab_size": 2,
54
+ "use_cache": true,
55
+ "vocab_size": 28996
56
+ }
run-6/checkpoint-249/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2017ae47e0a4871c135db9e8fce17c6a7328851cec82271fc81e4878822fab8
3
+ size 430942044
run-6/checkpoint-249/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a982855a37556f869a875540f2485a02d4993c840c1a31e1f935489e98d0fd8b
3
+ size 861998266
run-6/checkpoint-249/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2ffd2e67a5e106bcbed7941bfeb9076b68a447bab53d273e41d280ee2e05187
3
+ size 13990
run-6/checkpoint-249/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f59a7c556d6098bbf82e8a261c87e0dea97b6d0793ea80c4932cbd2323b6592b
3
+ size 1064
run-6/checkpoint-249/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-249/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-249/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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
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": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-6/checkpoint-249/trainer_state.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 249,
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_accuracy": 0.9472099821124733,
14
+ "eval_f1": 0.5949084412684235,
15
+ "eval_loss": 0.25175559520721436,
16
+ "eval_precision": 0.5244094488188976,
17
+ "eval_recall": 0.6873065015479877,
18
+ "eval_runtime": 2.6615,
19
+ "eval_samples_per_second": 318.997,
20
+ "eval_steps_per_second": 40.203,
21
+ "step": 249
22
+ }
23
+ ],
24
+ "logging_steps": 500,
25
+ "max_steps": 747,
26
+ "num_input_tokens_seen": 0,
27
+ "num_train_epochs": 3,
28
+ "save_steps": 500,
29
+ "stateful_callbacks": {
30
+ "TrainerControl": {
31
+ "args": {
32
+ "should_epoch_stop": false,
33
+ "should_evaluate": false,
34
+ "should_log": false,
35
+ "should_save": true,
36
+ "should_training_stop": false
37
+ },
38
+ "attributes": {}
39
+ }
40
+ },
41
+ "total_flos": 0,
42
+ "train_batch_size": 8,
43
+ "trial_name": null,
44
+ "trial_params": {
45
+ "learning_rate": 1.7924917300393731e-06,
46
+ "weight_decay": 7.731086067996299e-05
47
+ }
48
+ }
run-6/checkpoint-249/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fc8562573bc7d32b8d7379f9f5fc4af7c9df15d8c1964ded0d5cb79442c0109
3
+ size 5240
run-6/checkpoint-249/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:635c431a465c55743bd7814ca8044d4f39265cc9481fdbf307fcf59409d1cf73
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fc8562573bc7d32b8d7379f9f5fc4af7c9df15d8c1964ded0d5cb79442c0109
3
  size 5240