Hugging Face's logo

joseph10
/
tiny-bert-sst2-distilled

Text Classification
Transformers
TensorBoard
Safetensors
bert
text-embeddings-inference
Model card Files
xet
 Metrics Community
joseph10 commited on
Commit
6bb2ee3
·
1 Parent(s): 031413e

Training in progress, epoch 4

Browse files
Files changed (13) hide show
  1. logs/events.out.tfevents.1701809998.joseph_legion.26688.2 +2 -2
  2. model.safetensors +1 -1
  3. run-1/checkpoint-960/config.json +38 -0
  4. run-1/checkpoint-960/model.safetensors +3 -0
  5. run-1/checkpoint-960/optimizer.pt +3 -0
  6. run-1/checkpoint-960/rng_state.pth +3 -0
  7. run-1/checkpoint-960/scheduler.pt +3 -0
  8. run-1/checkpoint-960/special_tokens_map.json +7 -0
  9. run-1/checkpoint-960/tokenizer.json +0 -0
  10. run-1/checkpoint-960/tokenizer_config.json +57 -0
  11. run-1/checkpoint-960/trainer_state.json +84 -0
  12. run-1/checkpoint-960/training_args.bin +3 -0
  13. run-1/checkpoint-960/vocab.txt +0 -0
logs/events.out.tfevents.1701809998.joseph_legion.26688.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a1578f74e41609f1c342f4b15965a1a5c462efa4dd5e66ea1bbbf7b7f27c46a
3
- size 5805
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1079ccc33fe7d393f50253f31d7b10e3d9dcc962aa4eadec7b5e83f843d4fa0
3
+ size 6285
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da55d42ddc6b00e380465e06068b7b1c5a34657af2efa97698c5308fcc0269e3
3
  size 17550344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:646d4eaadbe2e59c49f4229a123b5fd702227a69dfe7be2c27f2b52414ce66d7
3
  size 17550344
run-1/checkpoint-960/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-1/checkpoint-960/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:646d4eaadbe2e59c49f4229a123b5fd702227a69dfe7be2c27f2b52414ce66d7
3
+ size 17550344
run-1/checkpoint-960/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67f0f47bf81b4fcdcb36a8c0523936de0f9011212ce36d0cdbf7c11b03e82341
3
+ size 35125946
run-1/checkpoint-960/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46bd578ca755b03be08396f6663241bc30da4fc6c9b2608fd0b7437cebcfd5ba
3
+ size 14244
run-1/checkpoint-960/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d4da0d4027e45b2642346bfdffd0deedeea9f6fb01b33e26393df7ddd33936c
3
+ size 1064
run-1/checkpoint-960/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-1/checkpoint-960/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-960/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-1/checkpoint-960/trainer_state.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8555758683729433,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled\\run-1\\checkpoint-240",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 960,
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": 8.630879766805442e-06,
14
+ "loss": 0.5344,
15
+ "step": 240
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8555758683729433,
20
+ "eval_loss": 0.4917151629924774,
21
+ "eval_runtime": 15.8805,
22
+ "eval_samples_per_second": 137.779,
23
+ "eval_steps_per_second": 1.133,
24
+ "step": 240
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 6.47315982510408e-06,
29
+ "loss": 0.4822,
30
+ "step": 480
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8555758683729433,
35
+ "eval_loss": 0.4872347116470337,
36
+ "eval_runtime": 15.9586,
37
+ "eval_samples_per_second": 137.104,
38
+ "eval_steps_per_second": 1.128,
39
+ "step": 480
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 4.315439883402721e-06,
44
+ "loss": 0.4784,
45
+ "step": 720
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8555758683729433,
50
+ "eval_loss": 0.4853495657444,
51
+ "eval_runtime": 15.8895,
52
+ "eval_samples_per_second": 137.701,
53
+ "eval_steps_per_second": 1.133,
54
+ "step": 720
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 2.1577199417013606e-06,
59
+ "loss": 0.4767,
60
+ "step": 960
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8555758683729433,
65
+ "eval_loss": 0.4839287996292114,
66
+ "eval_runtime": 15.86,
67
+ "eval_samples_per_second": 137.957,
68
+ "eval_steps_per_second": 1.135,
69
+ "step": 960
70
+ }
71
+ ],
72
+ "logging_steps": 500,
73
+ "max_steps": 1200,
74
+ "num_train_epochs": 5,
75
+ "save_steps": 500,
76
+ "total_flos": 6474259605024.0,
77
+ "trial_name": null,
78
+ "trial_params": {
79
+ "learning_rate": 1.0788599708506802e-05,
80
+ "num_train_epochs": 5,
81
+ "per_device_train_batch_size": 32,
82
+ "seed": 7
83
+ }
84
+ }
run-1/checkpoint-960/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04663dbe7637a3519a34a8cf9e2677fd38fcd880bb74e76f6f906b6293163a6b
3
+ size 4664
run-1/checkpoint-960/vocab.txt ADDED
The diff for this file is too large to render. See raw diff