joseph10 commited on
Commit
bfab4a6
1 Parent(s): 1a6af44

Training in progress, epoch 4

Browse files
logs/events.out.tfevents.1702101568.joseph_legion.21824.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90de0d26863552ac27a8f017d7aef5c754c97c88f427900815ed5c876a75e617
3
- size 5608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:735610ff367133154ab56d387d972c4023c52850bfd1ca05b09dc85edc24f44c
3
+ size 6568
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:757293b4fcd6083231ea27de781663d2fc834bfe4ab383be07adc001c908781e
3
  size 17550344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77bff236d5c588141a27efba0dc721d5c68e991663a28a8dd04423161b98ca06
3
  size 17550344
run-1/checkpoint-5745/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "agvidit1/GoogleTinyBert_HateSpeech_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": "noHate",
13
+ "1": "hate",
14
+ "2": "idk/skip",
15
+ "3": "relation"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 512,
19
+ "label2id": {
20
+ "hate": "1",
21
+ "idk/skip": "2",
22
+ "noHate": "0",
23
+ "relation": "3"
24
+ },
25
+ "layer_norm_eps": 1e-12,
26
+ "max_position_embeddings": 512,
27
+ "model_type": "bert",
28
+ "num_attention_heads": 2,
29
+ "num_hidden_layers": 2,
30
+ "pad_token_id": 0,
31
+ "position_embedding_type": "absolute",
32
+ "problem_type": "single_label_classification",
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.36.0.dev0",
35
+ "type_vocab_size": 2,
36
+ "use_cache": true,
37
+ "vocab_size": 30522
38
+ }
run-1/checkpoint-5745/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4163ee3a5eb5a59d926198a11cd34b55bfa7f589473e6864be6a765534ef47d
3
+ size 17550344
run-1/checkpoint-5745/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:776d6f293c4ae6d998f66b463211f0b84b93695bf59e7487912d3113e1b5b4bb
3
+ size 35125946
run-1/checkpoint-5745/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5335b453e72d1240d5c9578904b088b1fac9979722033eca4c38d5ebefc5934
3
+ size 14308
run-1/checkpoint-5745/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dd0d244868542b3e76e9496f1ae51faf1244c1a19b0348edbb7b422066b6df3
3
+ size 1064
run-1/checkpoint-5745/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-5745/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": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-1/checkpoint-5745/trainer_state.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8743144424131627,
3
+ "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-1\\checkpoint-5745",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 5745,
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": 2.623415476779745e-05,
14
+ "loss": 0.4826,
15
+ "step": 1915
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8574040219378428,
20
+ "eval_loss": 0.484986811876297,
21
+ "eval_runtime": 10.9318,
22
+ "eval_samples_per_second": 200.15,
23
+ "eval_steps_per_second": 1.647,
24
+ "step": 1915
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 1.9675616075848086e-05,
29
+ "loss": 0.4636,
30
+ "step": 3830
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8638025594149908,
35
+ "eval_loss": 0.4823402464389801,
36
+ "eval_runtime": 10.7788,
37
+ "eval_samples_per_second": 202.991,
38
+ "eval_steps_per_second": 1.67,
39
+ "step": 3830
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 1.3117077383898726e-05,
44
+ "loss": 0.4549,
45
+ "step": 5745
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8743144424131627,
50
+ "eval_loss": 0.4747394323348999,
51
+ "eval_runtime": 10.8039,
52
+ "eval_samples_per_second": 202.519,
53
+ "eval_steps_per_second": 1.666,
54
+ "step": 5745
55
+ }
56
+ ],
57
+ "logging_steps": 500,
58
+ "max_steps": 9575,
59
+ "num_input_tokens_seen": 0,
60
+ "num_train_epochs": 5,
61
+ "save_steps": 500,
62
+ "total_flos": 2318595518400.0,
63
+ "trial_name": null,
64
+ "trial_params": {
65
+ "learning_rate": 3.279269345974681e-05,
66
+ "num_train_epochs": 5,
67
+ "per_device_train_batch_size": 4,
68
+ "seed": 20
69
+ }
70
+ }
run-1/checkpoint-5745/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59411321184df9b5467011aae72cb0ff2b032602f5f6a940dcbdfbe56e8e2dd1
3
+ size 4792
run-1/checkpoint-5745/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-7660/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "agvidit1/GoogleTinyBert_HateSpeech_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": "noHate",
13
+ "1": "hate",
14
+ "2": "idk/skip",
15
+ "3": "relation"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 512,
19
+ "label2id": {
20
+ "hate": "1",
21
+ "idk/skip": "2",
22
+ "noHate": "0",
23
+ "relation": "3"
24
+ },
25
+ "layer_norm_eps": 1e-12,
26
+ "max_position_embeddings": 512,
27
+ "model_type": "bert",
28
+ "num_attention_heads": 2,
29
+ "num_hidden_layers": 2,
30
+ "pad_token_id": 0,
31
+ "position_embedding_type": "absolute",
32
+ "problem_type": "single_label_classification",
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.36.0.dev0",
35
+ "type_vocab_size": 2,
36
+ "use_cache": true,
37
+ "vocab_size": 30522
38
+ }
run-1/checkpoint-7660/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77bff236d5c588141a27efba0dc721d5c68e991663a28a8dd04423161b98ca06
3
+ size 17550344
run-1/checkpoint-7660/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ece48465c5dcc5262a72fd09ed894efcb9f92d0552ea99ae670fb83132156ca1
3
+ size 35125946
run-1/checkpoint-7660/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41dadc52d5855d01e74fe830240646497c892ac6e60640356d1ce96116a783e0
3
+ size 14308
run-1/checkpoint-7660/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6023c5e0000006145dad9dd81e3c4ec70052b923c0bcee0c2b238b58ad450eef
3
+ size 1064
run-1/checkpoint-7660/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-7660/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": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-1/checkpoint-7660/trainer_state.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8761425959780622,
3
+ "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-1\\checkpoint-7660",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 7660,
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": 2.623415476779745e-05,
14
+ "loss": 0.4826,
15
+ "step": 1915
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8574040219378428,
20
+ "eval_loss": 0.484986811876297,
21
+ "eval_runtime": 10.9318,
22
+ "eval_samples_per_second": 200.15,
23
+ "eval_steps_per_second": 1.647,
24
+ "step": 1915
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 1.9675616075848086e-05,
29
+ "loss": 0.4636,
30
+ "step": 3830
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8638025594149908,
35
+ "eval_loss": 0.4823402464389801,
36
+ "eval_runtime": 10.7788,
37
+ "eval_samples_per_second": 202.991,
38
+ "eval_steps_per_second": 1.67,
39
+ "step": 3830
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 1.3117077383898726e-05,
44
+ "loss": 0.4549,
45
+ "step": 5745
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8743144424131627,
50
+ "eval_loss": 0.4747394323348999,
51
+ "eval_runtime": 10.8039,
52
+ "eval_samples_per_second": 202.519,
53
+ "eval_steps_per_second": 1.666,
54
+ "step": 5745
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 6.558538691949363e-06,
59
+ "loss": 0.4488,
60
+ "step": 7660
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8761425959780622,
65
+ "eval_loss": 0.47820988297462463,
66
+ "eval_runtime": 10.9143,
67
+ "eval_samples_per_second": 200.471,
68
+ "eval_steps_per_second": 1.649,
69
+ "step": 7660
70
+ }
71
+ ],
72
+ "logging_steps": 500,
73
+ "max_steps": 9575,
74
+ "num_input_tokens_seen": 0,
75
+ "num_train_epochs": 5,
76
+ "save_steps": 500,
77
+ "total_flos": 3092347938432.0,
78
+ "trial_name": null,
79
+ "trial_params": {
80
+ "learning_rate": 3.279269345974681e-05,
81
+ "num_train_epochs": 5,
82
+ "per_device_train_batch_size": 4,
83
+ "seed": 20
84
+ }
85
+ }
run-1/checkpoint-7660/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59411321184df9b5467011aae72cb0ff2b032602f5f6a940dcbdfbe56e8e2dd1
3
+ size 4792
run-1/checkpoint-7660/vocab.txt ADDED
The diff for this file is too large to render. See raw diff