xuancoblab2023 commited on
Commit
b84a278
·
verified ·
1 Parent(s): 7821fe8

Training in progress, epoch 2

Browse files
logs/events.out.tfevents.1709751293.fcc57e6e3903.3035.9 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe65b50e68473a92662cbd1f1b1d6308016100b63527890735140728cb324a50
3
- size 5327
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f812b3769b1e6024025ddc3f1c6e08fad7031c6e28a24df7087220408b40d83
3
+ size 6010
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce241373183918d6ad27e7af40ca5934a857c49664e85bbdb7eacf2f106f064f
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc36708580d53291aa61ec07191f574387d3a684f33578a0286a962afc06539d
3
  size 17549312
run-9/checkpoint-792/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": "4.38.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-9/checkpoint-792/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc36708580d53291aa61ec07191f574387d3a684f33578a0286a962afc06539d
3
+ size 17549312
run-9/checkpoint-792/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aeed3d595994e0db69039072a618ce6994976d35727e3a13cd1d5efa03ca664
3
+ size 35122746
run-9/checkpoint-792/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:092ad374648752d939cb0bd17742b250258b4136202395e2f47247c14c3a55f2
3
+ size 14054
run-9/checkpoint-792/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4430703d9cef81d783d598559d22e6f165970487f940b3d419e0eb90c6fd357
3
+ size 1064
run-9/checkpoint-792/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-9/checkpoint-792/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-792/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-9/checkpoint-792/trainer_state.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5168316831683168,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-9/checkpoint-396",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 792,
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": 0.3266456127166748,
14
+ "learning_rate": 0.00047485708344336834,
15
+ "loss": 0.1574,
16
+ "step": 396
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5168316831683168,
21
+ "eval_f1": 0.18120805369127518,
22
+ "eval_loss": 0.15217570960521698,
23
+ "eval_precision": 0.5869565217391305,
24
+ "eval_recall": 0.10714285714285714,
25
+ "eval_runtime": 14.9861,
26
+ "eval_samples_per_second": 33.698,
27
+ "eval_steps_per_second": 1.068,
28
+ "step": 396
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 0.3928769528865814,
33
+ "learning_rate": 0.000395714236202807,
34
+ "loss": 0.1522,
35
+ "step": 792
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.504950495049505,
40
+ "eval_f1": 0.12587412587412586,
41
+ "eval_loss": 0.14909356832504272,
42
+ "eval_precision": 0.5294117647058824,
43
+ "eval_recall": 0.07142857142857142,
44
+ "eval_runtime": 15.144,
45
+ "eval_samples_per_second": 33.347,
46
+ "eval_steps_per_second": 1.057,
47
+ "step": 792
48
+ }
49
+ ],
50
+ "logging_steps": 500,
51
+ "max_steps": 2772,
52
+ "num_input_tokens_seen": 0,
53
+ "num_train_epochs": 7,
54
+ "save_steps": 500,
55
+ "total_flos": 1555686566280.0,
56
+ "train_batch_size": 24,
57
+ "trial_name": null,
58
+ "trial_params": {
59
+ "alpha": 0.17422929745790272,
60
+ "learning_rate": 0.0005539999306839298,
61
+ "num_train_epochs": 7,
62
+ "per_device_train_batch_size": 24,
63
+ "temperature": 12
64
+ }
65
+ }
run-9/checkpoint-792/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b73c802f5f517b25edfbe87e6b655b1a10931ee811a3ed96445c8dd0bf6c9d82
3
+ size 4920
run-9/checkpoint-792/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.json CHANGED
@@ -2,7 +2,7 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 31,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 33,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87c31c0ff5ab5419b10c4b045c98d73f4009f0b63f2ceac81514144c885ecd65
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b73c802f5f517b25edfbe87e6b655b1a10931ee811a3ed96445c8dd0bf6c9d82
3
  size 4920