agvidit1 commited on
Commit
2d39e2e
·
1 Parent(s): 9fc2572

Training in progress, epoch 2

Browse files
logs/events.out.tfevents.1702154602.tron63.umiacs.umd.edu CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:904ec181de4b27a306a0a5f3746a0dcf7bdc3a010a82dd1b496d5f02ea26680a
3
- size 4479
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f04ef07d8ecf00e355b7a0467dfbc1c38eeefa091fe959683c632dcc9228b88b
3
+ size 4959
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78cc1b2606ec7675843e1e0cd3fc302dcc62a5e310f73e031724e24ecb4ebca4
3
  size 267838720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41ed59ff021120a9984057d8bacb44dd7bfcb873db7b91fbef75ae074a265ca2
3
  size 267838720
run-0/checkpoint-548/config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "agvidit1/DistilledBert_HateSpeech_pretrain",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "noHate",
13
+ "1": "hate",
14
+ "2": "idk/skip",
15
+ "3": "relation"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "label2id": {
19
+ "hate": "1",
20
+ "idk/skip": "2",
21
+ "noHate": "0",
22
+ "relation": "3"
23
+ },
24
+ "max_position_embeddings": 512,
25
+ "model_type": "distilbert",
26
+ "n_heads": 12,
27
+ "n_layers": 6,
28
+ "pad_token_id": 0,
29
+ "problem_type": "single_label_classification",
30
+ "qa_dropout": 0.1,
31
+ "seq_classif_dropout": 0.2,
32
+ "sinusoidal_pos_embds": false,
33
+ "tie_weights_": true,
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.35.2",
36
+ "vocab_size": 30522
37
+ }
run-0/checkpoint-548/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41ed59ff021120a9984057d8bacb44dd7bfcb873db7b91fbef75ae074a265ca2
3
+ size 267838720
run-0/checkpoint-548/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3974c30732171957bb5af534e76f81d69c0b0a9dc7d46ca3c0fc8dfa21cfd650
3
+ size 535739578
run-0/checkpoint-548/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d4c1e30249fd9b6e11118ec5efc93e49514f765d8e319e939eb2de3735c5e69
3
+ size 14308
run-0/checkpoint-548/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a0da41139c722a21b86798c2191deeb55a020103e462a9a8c4a55eef4d2793f
3
+ size 1064
run-0/checkpoint-548/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-0/checkpoint-548/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-0/checkpoint-548/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8893967093235832,
3
+ "best_model_checkpoint": "distilbert-hate_speech18/run-0/checkpoint-548",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 548,
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": 1.2320593222558211e-05,
14
+ "loss": 0.4773,
15
+ "step": 274
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8747714808043876,
20
+ "eval_loss": 0.4582797884941101,
21
+ "eval_runtime": 2.2824,
22
+ "eval_samples_per_second": 479.322,
23
+ "eval_steps_per_second": 30.231,
24
+ "step": 274
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 6.160296611279106e-06,
29
+ "loss": 0.4216,
30
+ "step": 548
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8893967093235832,
35
+ "eval_loss": 0.4573306441307068,
36
+ "eval_runtime": 2.2635,
37
+ "eval_samples_per_second": 483.316,
38
+ "eval_steps_per_second": 30.483,
39
+ "step": 548
40
+ }
41
+ ],
42
+ "logging_steps": 500,
43
+ "max_steps": 822,
44
+ "num_train_epochs": 3,
45
+ "save_steps": 500,
46
+ "total_flos": 371152219305840.0,
47
+ "trial_name": null,
48
+ "trial_params": {
49
+ "alpha": 0.6923372412428416,
50
+ "learning_rate": 1.8480889833837317e-05,
51
+ "num_train_epochs": 3,
52
+ "per_device_eval_batch_size": 16,
53
+ "per_device_train_batch_size": 32,
54
+ "temperature": 15
55
+ }
56
+ }
run-0/checkpoint-548/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72d814883616bbce8caced582b3d3544fbb87c238bdcd6ca6524e1226e82f142
3
+ size 4664
run-0/checkpoint-548/vocab.txt ADDED
The diff for this file is too large to render. See raw diff