Hugging Face's logo

xuancoblab2023
/
tiny-bert-sst2-distilled

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
xuancoblab2023 commited on
Commit
1384697
·
verified ·
1 Parent(s): 8381779

Training in progress, epoch 1

Browse files
Files changed (16) hide show
  1. logs/events.out.tfevents.1713589257.1376c752d37a.9760.28 +2 -2
  2. logs/events.out.tfevents.1713589358.1376c752d37a.9760.29 +3 -0
  3. logs/events.out.tfevents.1713589374.1376c752d37a.9760.30 +3 -0
  4. model.safetensors +1 -1
  5. run-30/checkpoint-214/config.json +34 -0
  6. run-30/checkpoint-214/model.safetensors +3 -0
  7. run-30/checkpoint-214/optimizer.pt +3 -0
  8. run-30/checkpoint-214/rng_state.pth +3 -0
  9. run-30/checkpoint-214/scheduler.pt +3 -0
  10. run-30/checkpoint-214/special_tokens_map.json +7 -0
  11. run-30/checkpoint-214/tokenizer.json +0 -0
  12. run-30/checkpoint-214/tokenizer_config.json +57 -0
  13. run-30/checkpoint-214/trainer_state.json +46 -0
  14. run-30/checkpoint-214/training_args.bin +3 -0
  15. run-30/checkpoint-214/vocab.txt +0 -0
  16. training_args.bin +1 -1
logs/events.out.tfevents.1713589257.1376c752d37a.9760.28 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1f20a781f6df626a53ae033ef396f823a35d04ae68ecef5628384c84417fef9
3
- size 8402
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85741d564d7afb8b04ba98f9ea8ae6bf00765572477fdc54195bc96ab129d6ae
3
+ size 9132
logs/events.out.tfevents.1713589358.1376c752d37a.9760.29 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17e736a0473503164a4004c44e8a15fdb8f0da0da21d96478e9821f9aff52243
3
+ size 5484
logs/events.out.tfevents.1713589374.1376c752d37a.9760.30 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f18436bc35e1516cf562c5a2ed2d64f9cdb5346087422069c20af492bbc99586
3
+ size 5482
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c9f799af2e4d0b43ba1467fcec4216b771f08d3d68237e807fd38c764cac05d
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e055eaa4180a5dd2ffea1b3dbe87c44481cfc77da37ac68f686329241dad5d72
3
  size 17549312
run-30/checkpoint-214/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.40.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-30/checkpoint-214/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e055eaa4180a5dd2ffea1b3dbe87c44481cfc77da37ac68f686329241dad5d72
3
+ size 17549312
run-30/checkpoint-214/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e91d51f04428947b330472bc1b6c15e94d9cb808cb95db5d380f2b5efe651a58
3
+ size 35123898
run-30/checkpoint-214/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc7e492e6768bc7c3c01ac823da5a8177cf34fc1b175dd727fa3be969661a151
3
+ size 14308
run-30/checkpoint-214/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8b321f6409e4f179b9ec1c4bb9386a41d67fe0bb3b4ae579c770f5ead99e3d5
3
+ size 1064
run-30/checkpoint-214/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-30/checkpoint-214/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-30/checkpoint-214/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-30/checkpoint-214/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.70298769771529,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-30/checkpoint-214",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 214,
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
+ "grad_norm": 6.404624938964844,
14
+ "learning_rate": 0.0006827366491550371,
15
+ "loss": 0.5674,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.70298769771529,
21
+ "eval_f1": 0.47461139896373056,
22
+ "eval_loss": 0.5547006130218506,
23
+ "eval_mcc": 0.28558083057134703,
24
+ "eval_precision": 0.5782828282828283,
25
+ "eval_recall": 0.4024604569420035,
26
+ "eval_runtime": 3.121,
27
+ "eval_samples_per_second": 546.936,
28
+ "eval_steps_per_second": 17.302,
29
+ "step": 214
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 1926,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 9,
36
+ "save_steps": 500,
37
+ "total_flos": 524775664440.0,
38
+ "train_batch_size": 32,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "alpha": 0.9213962687632572,
42
+ "learning_rate": 0.0007680787302994168,
43
+ "num_train_epochs": 9,
44
+ "temperature": 25
45
+ }
46
+ }
run-30/checkpoint-214/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c21d2a5115c4ec711667a681f6c70624e61496610806db95b0db67741a26789
3
+ size 5048
run-30/checkpoint-214/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:958d2eb44240d1dcf28e632e2052856986195085c97b366e1fc6588f903c1326
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c21d2a5115c4ec711667a681f6c70624e61496610806db95b0db67741a26789
3
  size 5048