joseph10 commited on
Commit
c73b9a1
1 Parent(s): e8e848a

Training in progress, epoch 2

Browse files
logs/events.out.tfevents.1702108860.joseph_legion.21824.45 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48ecd1dd2bd01304c1a3fe796d7d90a71da6146ada8b580113f75b3451b21128
3
- size 5130
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9d97369574859a0b6f223b4acc57d19a073d08308d4ff38906c93169bc416e2
3
+ size 5610
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a3645a5496da713b5e2b5dd50ab23ac9aee0fedb44f2c8ce53e3994e4dc956c
3
  size 17550344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94d9e97610c59568079e01dda80c491d06f220bdb60b86eb6a656a7a852ffe33
3
  size 17550344
run-44/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-44/checkpoint-958/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94d9e97610c59568079e01dda80c491d06f220bdb60b86eb6a656a7a852ffe33
3
+ size 17550344
run-44/checkpoint-958/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c973c43da2814a9e5b14964890fd5904b3cc81f9ba455c94762cdc4566b605c
3
+ size 35125946
run-44/checkpoint-958/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:578998c06071562e181317b52f83815484d078eb30a3ff30acd77140e5dea6a3
3
+ size 14244
run-44/checkpoint-958/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:937ea06524192958372932f592e40754c15867d4183b8ef1d662f52f5b9226ae
3
+ size 1064
run-44/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-44/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-44/checkpoint-958/trainer_state.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8747714808043876,
3
+ "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-44\\checkpoint-958",
4
+ "epoch": 2.0,
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": 4.5410240915591696e-05,
14
+ "loss": 0.4851,
15
+ "step": 479
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8596892138939671,
20
+ "eval_loss": 0.47658035159111023,
21
+ "eval_runtime": 10.8435,
22
+ "eval_samples_per_second": 201.78,
23
+ "eval_steps_per_second": 1.66,
24
+ "step": 479
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 3.0273493943727797e-05,
29
+ "loss": 0.4611,
30
+ "step": 958
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8747714808043876,
35
+ "eval_loss": 0.4699705243110657,
36
+ "eval_runtime": 11.0102,
37
+ "eval_samples_per_second": 198.725,
38
+ "eval_steps_per_second": 1.635,
39
+ "step": 958
40
+ }
41
+ ],
42
+ "logging_steps": 500,
43
+ "max_steps": 1916,
44
+ "num_input_tokens_seen": 0,
45
+ "num_train_epochs": 4,
46
+ "save_steps": 500,
47
+ "total_flos": 2490953225088.0,
48
+ "trial_name": null,
49
+ "trial_params": {
50
+ "learning_rate": 6.0546987887455595e-05,
51
+ "num_train_epochs": 4,
52
+ "per_device_train_batch_size": 16,
53
+ "seed": 34
54
+ }
55
+ }
run-44/checkpoint-958/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67754f69bac3e36140ae4b3afde612f47f6df09ac98777181a98d08ebbee6769
3
+ size 4792
run-44/checkpoint-958/vocab.txt ADDED
The diff for this file is too large to render. See raw diff