joseph10 commited on
Commit
8c413e4
·
1 Parent(s): 1a31441

Training in progress, epoch 1

Browse files
logs/events.out.tfevents.1702105805.joseph_legion.21824.25 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68c711bd0f5169628a8813e85cfcebdb66230864ed4addf575620d4381bb2e00
3
- size 5128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf8784d216d26d90b7c80dbe8befb484fa1b4f28a350058f091ba929576abca6
3
+ size 5608
logs/events.out.tfevents.1702106022.joseph_legion.21824.26 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4ba6fea069ff14452b99609f9a4e434dd5424e23b174f26313b7a27fb25b80b
3
+ size 5129
logs/events.out.tfevents.1702106061.joseph_legion.21824.27 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87060aafe340214757a68deecc436f677dddcc0a7ad191bdb85bd48da3ac1763
3
+ size 5128
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fcf3e1d78b40ddde099232cb15d6bc4958e4eb6c619293b840a5f71b4b72ef22
3
  size 17550344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c554bc997849d12acf29c19c8bd3d0dc4b4457dcf0163fa4084c96ccbd583c60
3
  size 17550344
run-26/checkpoint-958/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-26/checkpoint-958/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c554bc997849d12acf29c19c8bd3d0dc4b4457dcf0163fa4084c96ccbd583c60
3
+ size 17550344
run-26/checkpoint-958/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a62ff98904e6247f3a4ed99118958ac4dc0f7f115cf776ecace8f012f9d495e
3
+ size 35125946
run-26/checkpoint-958/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29036aed78361480273e7b8d21bfef37a09f4028e58a23dc2f8139c84d900440
3
+ size 14308
run-26/checkpoint-958/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b931dafc27cd207bb79ffaee3fdb37bafd7bada5d05309a2cb065413a25db43
3
+ size 1064
run-26/checkpoint-958/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-26/checkpoint-958/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-26/checkpoint-958/trainer_state.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8610603290676416,
3
+ "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-26\\checkpoint-958",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 958,
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": 6.129140788326744e-05,
14
+ "loss": 0.4755,
15
+ "step": 958
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8610603290676416,
20
+ "eval_loss": 0.47343045473098755,
21
+ "eval_runtime": 10.772,
22
+ "eval_samples_per_second": 203.119,
23
+ "eval_steps_per_second": 1.671,
24
+ "step": 958
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 2874,
29
+ "num_input_tokens_seen": 0,
30
+ "num_train_epochs": 3,
31
+ "save_steps": 500,
32
+ "total_flos": 982977235584.0,
33
+ "trial_name": null,
34
+ "trial_params": {
35
+ "learning_rate": 9.193711182490116e-05,
36
+ "num_train_epochs": 3,
37
+ "per_device_train_batch_size": 8,
38
+ "seed": 31
39
+ }
40
+ }
run-26/checkpoint-958/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5614454ac5392408e7ad917f8d31e0a2976a3888becd736d8ae16fdc913abcab
3
+ size 4792
run-26/checkpoint-958/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 sha256:4cf628fdf66c74eba47d8143dc69f647516dd943551454a25900f46257581183
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5614454ac5392408e7ad917f8d31e0a2976a3888becd736d8ae16fdc913abcab
3
  size 4792