joseph10 commited on
Commit
e263a16
1 Parent(s): b1aedbd

Training in progress, epoch 2

Browse files
logs/events.out.tfevents.1702104670.joseph_legion.21824.18 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5dcd4b643d8547c1e93b0c577432971106fd457bd86dac221ff1a8900ff47935
3
- size 5128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8de7c195a610debce3cd665002eb3118d7a5c8c17f704c87a0a0346379d135f
3
+ size 5962
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dcea07bf50e832235f6608d80fc13990e5f45d12e6e53e0fc013587e6d115a48
3
  size 17550344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99646fe6ddc0233e112fc5d774d756cb981e2b8ee229a89856595753963264e4
3
  size 17550344
run-17/checkpoint-3830/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-17/checkpoint-3830/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99646fe6ddc0233e112fc5d774d756cb981e2b8ee229a89856595753963264e4
3
+ size 17550344
run-17/checkpoint-3830/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ad9fdb70e8f1a8fc8c4e0405a9b0dc898459ee37561613d4e2cd80f4071888a
3
+ size 35125946
run-17/checkpoint-3830/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3daf0fc9a1f803d6849680dbe7656aaaad7bc90ca1091eb0a599782edfc26cd5
3
+ size 14308
run-17/checkpoint-3830/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9eb29a8bda6a2b3619f885b772a9fcd19dc4eab1437ca5e66e0c157ba61ebe7
3
+ size 1064
run-17/checkpoint-3830/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-17/checkpoint-3830/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-17/checkpoint-3830/trainer_state.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8747714808043876,
3
+ "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-17\\checkpoint-3830",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3830,
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": 4.804034664994629e-05,
14
+ "loss": 0.4759,
15
+ "step": 1915
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.863345521023766,
20
+ "eval_loss": 0.4774511456489563,
21
+ "eval_runtime": 10.6465,
22
+ "eval_samples_per_second": 205.513,
23
+ "eval_steps_per_second": 1.691,
24
+ "step": 1915
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 0.0,
29
+ "loss": 0.4517,
30
+ "step": 3830
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8747714808043876,
35
+ "eval_loss": 0.4742494225502014,
36
+ "eval_runtime": 10.7351,
37
+ "eval_samples_per_second": 203.818,
38
+ "eval_steps_per_second": 1.677,
39
+ "step": 3830
40
+ }
41
+ ],
42
+ "logging_steps": 500,
43
+ "max_steps": 3830,
44
+ "num_input_tokens_seen": 0,
45
+ "num_train_epochs": 2,
46
+ "save_steps": 500,
47
+ "total_flos": 1545627716256.0,
48
+ "trial_name": null,
49
+ "trial_params": {
50
+ "learning_rate": 9.608069329989258e-05,
51
+ "num_train_epochs": 2,
52
+ "per_device_train_batch_size": 4,
53
+ "seed": 20
54
+ }
55
+ }
run-17/checkpoint-3830/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba047a36782a5aa605584ebb8913772af42ea68e7920a5e3f5407f2c458b5352
3
+ size 4792
run-17/checkpoint-3830/vocab.txt ADDED
The diff for this file is too large to render. See raw diff