joseph10 commited on
Commit
55bfa37
·
1 Parent(s): 5072214

Training in progress, epoch 4

Browse files
logs/events.out.tfevents.1701809488.joseph_legion.26688.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:403d537ffdb5cd3e9414d8cc18fa50a6bf5d2f59cb9ae7c5ef0e364996a18e50
3
- size 5804
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9011c8076932198488394ca7f9122d0045079bd9d7d9d838b222158fa3b68d8b
3
+ size 6638
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14625458bf96ae96bcfdf8f2df81e9fd16deceea6eb0fc9a34e0053da437b3e2
3
  size 17550344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:776521852cf94ad5d67a52537c810088894c9923abc0388dbed7248f1c7940f3
3
  size 17550344
run-0/checkpoint-7660/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
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": "4.35.2",
35
+ "type_vocab_size": 2,
36
+ "use_cache": true,
37
+ "vocab_size": 30522
38
+ }
run-0/checkpoint-7660/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:776521852cf94ad5d67a52537c810088894c9923abc0388dbed7248f1c7940f3
3
+ size 17550344
run-0/checkpoint-7660/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5244e427a219dabbc6cd0f68b61201a2e7748973ee37ef5c9b5638aee6975517
3
+ size 35125946
run-0/checkpoint-7660/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3024c8f7ed138edaecc9de8a5c40faa361635c37f889c415424bef688cf8181c
3
+ size 14308
run-0/checkpoint-7660/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ec977b3d02fb26f1b21fd222bbbab07b56deb5c1448150221c4ed0d07743557
3
+ size 1064
run-0/checkpoint-7660/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-0/checkpoint-7660/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/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-0/checkpoint-7660/trainer_state.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8555758683729433,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled\\run-0\\checkpoint-1915",
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": 1.7055505646941732e-06,
14
+ "loss": 0.5482,
15
+ "step": 1915
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8555758683729433,
20
+ "eval_loss": 0.4959913194179535,
21
+ "eval_runtime": 28.3105,
22
+ "eval_samples_per_second": 77.286,
23
+ "eval_steps_per_second": 0.636,
24
+ "step": 1915
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 1.1370337097961155e-06,
29
+ "loss": 0.4846,
30
+ "step": 3830
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8555758683729433,
35
+ "eval_loss": 0.4906463325023651,
36
+ "eval_runtime": 28.7931,
37
+ "eval_samples_per_second": 75.99,
38
+ "eval_steps_per_second": 0.625,
39
+ "step": 3830
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 5.685168548980578e-07,
44
+ "loss": 0.4819,
45
+ "step": 5745
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8555758683729433,
50
+ "eval_loss": 0.49088209867477417,
51
+ "eval_runtime": 28.9817,
52
+ "eval_samples_per_second": 75.496,
53
+ "eval_steps_per_second": 0.621,
54
+ "step": 5745
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 0.0,
59
+ "loss": 0.4811,
60
+ "step": 7660
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8555758683729433,
65
+ "eval_loss": 0.4908199608325958,
66
+ "eval_runtime": 28.8203,
67
+ "eval_samples_per_second": 75.919,
68
+ "eval_steps_per_second": 0.625,
69
+ "step": 7660
70
+ }
71
+ ],
72
+ "logging_steps": 500,
73
+ "max_steps": 7660,
74
+ "num_train_epochs": 4,
75
+ "save_steps": 500,
76
+ "total_flos": 3123772381440.0,
77
+ "trial_name": null,
78
+ "trial_params": {
79
+ "learning_rate": 2.274067419592231e-06,
80
+ "num_train_epochs": 4,
81
+ "per_device_train_batch_size": 4,
82
+ "seed": 29
83
+ }
84
+ }
run-0/checkpoint-7660/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:226a82a051d77a8df2f120b4bfa6bfc650e966ad1da2a183888ee63c145a2988
3
+ size 4664
run-0/checkpoint-7660/vocab.txt ADDED
The diff for this file is too large to render. See raw diff