Hugging Face's logo

Tech-oriented
/
bert-base-uncased-finetuned-sst2

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Tech-oriented commited on
Commit
ef64ada
•
1 Parent(s): 62a7cf8

Training in progress, epoch 3

Browse files
Files changed (16) hide show
  1. run-5/checkpoint-844/config.json +27 -0
  2. run-5/checkpoint-844/model.safetensors +3 -0
  3. run-5/checkpoint-844/optimizer.pt +3 -0
  4. run-5/checkpoint-844/rng_state.pth +3 -0
  5. run-5/checkpoint-844/scheduler.pt +3 -0
  6. run-5/checkpoint-844/special_tokens_map.json +7 -0
  7. run-5/checkpoint-844/tokenizer.json +0 -0
  8. run-5/checkpoint-844/tokenizer_config.json +55 -0
  9. run-5/checkpoint-844/trainer_state.json +69 -0
  10. run-5/checkpoint-844/training_args.bin +3 -0
  11. run-5/checkpoint-844/vocab.txt +0 -0
  12. runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709493558.90708aaa767a.21824.13 +3 -0
  13. runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709493609.90708aaa767a.21824.14 +3 -0
  14. runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709493662.90708aaa767a.21824.15 +3 -0
  15. runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709493715.90708aaa767a.21824.16 +3 -0
  16. runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709496301.90708aaa767a.21824.17 +3 -0
run-5/checkpoint-844/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "problem_type": "single_label_classification",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.2",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
+ }
run-5/checkpoint-844/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1c0fc03a58376e33e9a3eea7c0c22a2349418a9eeaad8039a3b0c7e833c3c8d
3
+ size 437958648
run-5/checkpoint-844/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bea2652f6107b05b847fccb74f9ca65324ac15f459930540b37f0c7ee13341d8
3
+ size 876038394
run-5/checkpoint-844/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43f71bf733902c6b017a2b1bdd66efd88c19004224b69e8587093a4c4f1b3620
3
+ size 14244
run-5/checkpoint-844/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fba50869e248a2abab7ce5518338dc7aaadceb6781ccfedbaa93a02ba143a408
3
+ size 1064
run-5/checkpoint-844/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-5/checkpoint-844/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-844/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-5/checkpoint-844/trainer_state.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9162844036697247,
3
+ "best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-5/checkpoint-844",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 844,
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
+ "eval_accuracy": 0.9002293577981652,
14
+ "eval_loss": 0.24879497289657593,
15
+ "eval_runtime": 2.3485,
16
+ "eval_samples_per_second": 371.303,
17
+ "eval_steps_per_second": 23.419,
18
+ "step": 211
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.9059633027522935,
23
+ "eval_loss": 0.2516523599624634,
24
+ "eval_runtime": 2.3894,
25
+ "eval_samples_per_second": 364.945,
26
+ "eval_steps_per_second": 23.018,
27
+ "step": 422
28
+ },
29
+ {
30
+ "epoch": 2.37,
31
+ "grad_norm": 0.7729095220565796,
32
+ "learning_rate": 2.651478911079213e-05,
33
+ "loss": 0.2165,
34
+ "step": 500
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "eval_accuracy": 0.9139908256880734,
39
+ "eval_loss": 0.3265123963356018,
40
+ "eval_runtime": 2.3971,
41
+ "eval_samples_per_second": 363.775,
42
+ "eval_steps_per_second": 22.944,
43
+ "step": 633
44
+ },
45
+ {
46
+ "epoch": 4.0,
47
+ "eval_accuracy": 0.9162844036697247,
48
+ "eval_loss": 0.3921748995780945,
49
+ "eval_runtime": 2.3998,
50
+ "eval_samples_per_second": 363.361,
51
+ "eval_steps_per_second": 22.918,
52
+ "step": 844
53
+ }
54
+ ],
55
+ "logging_steps": 500,
56
+ "max_steps": 844,
57
+ "num_input_tokens_seen": 0,
58
+ "num_train_epochs": 4,
59
+ "save_steps": 500,
60
+ "total_flos": 335486123357640.0,
61
+ "train_batch_size": 32,
62
+ "trial_name": null,
63
+ "trial_params": {
64
+ "learning_rate": 6.50537267718272e-05,
65
+ "num_train_epochs": 4,
66
+ "per_device_train_batch_size": 32,
67
+ "seed": 2
68
+ }
69
+ }
run-5/checkpoint-844/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ade228fc6bd95046697574a73a36f3413a1273363ebbb392ad60a58f2443b9d
3
+ size 4920
run-5/checkpoint-844/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709493558.90708aaa767a.21824.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3a4c6c3ce1380fd5a1d2a3ced927f003025e6fe2b20fa3e0601a27aa2ed7614
3
+ size 4947
runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709493609.90708aaa767a.21824.14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:391d79151cff6aaa2a2cce1fadf1029d310e3aa25d6165b20a96df3d827179eb
3
+ size 4946
runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709493662.90708aaa767a.21824.15 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c3048b6789f9d63985678c49d821b51e6806e93065a290ee6298aa64398fd0c
3
+ size 4947
runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709493715.90708aaa767a.21824.16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87f3ad9233f2046988e020e7b1fa8a7330dbb3ac809a794ce01e33e1d3b05402
3
+ size 5579
runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709496301.90708aaa767a.21824.17 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3039e955db62b7dcacdf6491e2ac1f97cfd2f058fbb64b62df28d18918bd6b3e
3
+ size 6479