joseph10 commited on
Commit
c51ba0e
·
1 Parent(s): 5be60ea

Training in progress, epoch 1

Browse files
logs/events.out.tfevents.1702225072.joseph_legion.22340.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc1691bfb0109223c4e94aa4eeddb86ccd82205db1dc2cfe5d4e637235e2dd0a
3
- size 5941
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e567abd4db56db68d7223056b059966197cbdbe7cc9c57bff5a5460c9814f53
3
+ size 6775
logs/events.out.tfevents.1702225147.joseph_legion.22340.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c190b2365f86dac325873d0c535c13025f443faeaf9d966e11dce5b671c0c93
3
+ size 4990
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d81389b47286812d22202a7d051779b7e614412fd54fd3898c8c0a9b1a1b6ad
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:615bbb736d95c4c9ddbc49a0137f59ffed75e4576acac5ed0a3fc9497f064404
3
  size 17549312
run-1/checkpoint-220/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "agvidit1/TinyBert-Berttoken-Toxigen-pretrain",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": 0,
13
+ "1": 1
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "0": 0,
19
+ "1": 1
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.36.0.dev0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-1/checkpoint-220/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d83d3568bd71770846b148a41db615fecc4caa566149091b76ed7eaec13c59d1
3
+ size 17549312
run-1/checkpoint-220/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a28f20aa0b4c490840b3a508d651eb2c92b6d614d0b215e021da99af8abc0a84
3
+ size 35123898
run-1/checkpoint-220/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7490a59add9b8bbe4259dbc0adb9870a059024eef767fd9d1db3db4b03e7ff2
3
+ size 14308
run-1/checkpoint-220/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b00dcdf66bb8cc7c5d5290c74d4784a176d88b117a0fc47daf69f0fcfe904ad
3
+ size 1064
run-1/checkpoint-220/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
run-1/checkpoint-220/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "DistilBertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-1/checkpoint-220/trainer_state.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.451010101010101,
3
+ "best_model_checkpoint": "tinybert-toxigen-bothpretrained\\run-1\\checkpoint-220",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 220,
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
+ "learning_rate": 2.266610127439989e-05,
14
+ "loss": 0.1001,
15
+ "step": 55
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.36262626262626263,
20
+ "eval_loss": 0.09902925044298172,
21
+ "eval_runtime": 3.347,
22
+ "eval_samples_per_second": 591.576,
23
+ "eval_steps_per_second": 4.78,
24
+ "step": 55
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 1.511073418293326e-05,
29
+ "loss": 0.0993,
30
+ "step": 110
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.3939393939393939,
35
+ "eval_loss": 0.09844165295362473,
36
+ "eval_runtime": 3.4042,
37
+ "eval_samples_per_second": 581.63,
38
+ "eval_steps_per_second": 4.7,
39
+ "step": 110
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 7.55536709146663e-06,
44
+ "loss": 0.0988,
45
+ "step": 165
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.4404040404040404,
50
+ "eval_loss": 0.09817706793546677,
51
+ "eval_runtime": 3.3652,
52
+ "eval_samples_per_second": 588.382,
53
+ "eval_steps_per_second": 4.755,
54
+ "step": 165
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 0.0,
59
+ "loss": 0.0987,
60
+ "step": 220
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.451010101010101,
65
+ "eval_loss": 0.09811734408140182,
66
+ "eval_runtime": 3.3507,
67
+ "eval_samples_per_second": 590.915,
68
+ "eval_steps_per_second": 4.775,
69
+ "step": 220
70
+ }
71
+ ],
72
+ "logging_steps": 500,
73
+ "max_steps": 220,
74
+ "num_input_tokens_seen": 0,
75
+ "num_train_epochs": 4,
76
+ "save_steps": 500,
77
+ "total_flos": 3368572315560.0,
78
+ "trial_name": null,
79
+ "trial_params": {
80
+ "alpha": 0.13686313401622996,
81
+ "learning_rate": 3.022146836586652e-05,
82
+ "num_train_epochs": 4,
83
+ "temperature": 18
84
+ }
85
+ }
run-1/checkpoint-220/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5f34756ebf1bea0a65f2812e839a2b342e11b792f6f39339c1ab1dc75e14c2b
3
+ size 4792
run-1/checkpoint-220/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-55/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "agvidit1/TinyBert-Berttoken-Toxigen-pretrain",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": 0,
13
+ "1": 1
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "0": 0,
19
+ "1": 1
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.36.0.dev0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-2/checkpoint-55/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:615bbb736d95c4c9ddbc49a0137f59ffed75e4576acac5ed0a3fc9497f064404
3
+ size 17549312
run-2/checkpoint-55/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6be479d26da8cc4727db54e4a9c77ee4c8becc5b9d385c34f8fec524aa14f3d4
3
+ size 35123898
run-2/checkpoint-55/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9684c683f536a580a60f9875e5f0c89c28c0f0b16080832ddf6bf0362cbd5e4
3
+ size 14308
run-2/checkpoint-55/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a32b114d8ed709cf6fab86467e8a5d7d090b250e204e2daad67c86fbdf48996
3
+ size 1064
run-2/checkpoint-55/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
run-2/checkpoint-55/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "DistilBertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-2/checkpoint-55/trainer_state.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3621212121212121,
3
+ "best_model_checkpoint": "tinybert-toxigen-bothpretrained\\run-2\\checkpoint-55",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 55,
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
+ "learning_rate": 1.5441792724155395e-05,
14
+ "loss": 0.036,
15
+ "step": 55
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.3621212121212121,
20
+ "eval_loss": 0.035133831202983856,
21
+ "eval_runtime": 3.3771,
22
+ "eval_samples_per_second": 586.31,
23
+ "eval_steps_per_second": 4.738,
24
+ "step": 55
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 385,
29
+ "num_input_tokens_seen": 0,
30
+ "num_train_epochs": 7,
31
+ "save_steps": 500,
32
+ "total_flos": 847072419720.0,
33
+ "trial_name": null,
34
+ "trial_params": {
35
+ "alpha": 0.04724864888100444,
36
+ "learning_rate": 1.801542484484796e-05,
37
+ "num_train_epochs": 7,
38
+ "temperature": 8
39
+ }
40
+ }
run-2/checkpoint-55/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3665af9c3c019c7a654a9c71965a2fc9fda3a71cd4b9490a09ae818e2cde0bb0
3
+ size 4792
run-2/checkpoint-55/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:f5f34756ebf1bea0a65f2812e839a2b342e11b792f6f39339c1ab1dc75e14c2b
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3665af9c3c019c7a654a9c71965a2fc9fda3a71cd4b9490a09ae818e2cde0bb0
3
  size 4792