xuancoblab2023 commited on
Commit
c373dbd
·
verified ·
1 Parent(s): 595e582

Training in progress, epoch 2

Browse files
logs/events.out.tfevents.1709746175.d65e8524b0f6.5185.14 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a36c15ac89416287bf2319b3413bb8f2d29c141f4b1c07c30185076e2f38a5e
3
- size 5315
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ecec07a177dcf2b6ae665ae520fd099fa27d68685668142e0573a93c11a0919
3
+ size 5985
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32a315d0e64fc541e14e05d225bcdb90de882cba681a13f42653e417c410152c
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6287accce550c04130735f44b7faaf36649a796166215bf057d366cd9a32f86
3
  size 17549312
run-14/checkpoint-98/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-14/checkpoint-98/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6287accce550c04130735f44b7faaf36649a796166215bf057d366cd9a32f86
3
+ size 17549312
run-14/checkpoint-98/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e610c58d53c03b5ea6ad70510648396fcf240c7eb502ad70506efde2e90c8d85
3
+ size 35122746
run-14/checkpoint-98/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9027a30c627c64d9028bcf149a72b8a747f24575e2c498c808500edb8b9f3a45
3
+ size 14054
run-14/checkpoint-98/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a08af08c173ebda9532700061b899bc36f96b7a543c91b07d8e199f04902b6d
3
+ size 1064
run-14/checkpoint-98/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-14/checkpoint-98/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-14/checkpoint-98/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-14/checkpoint-98/trainer_state.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8023483365949119,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-14/checkpoint-98",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 98,
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": 1.3073023557662964,
14
+ "learning_rate": 0.00021800841920007835,
15
+ "loss": 0.5666,
16
+ "step": 49
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7720156555772995,
21
+ "eval_f1": 0.8010247651579846,
22
+ "eval_loss": 0.48246321082115173,
23
+ "eval_precision": 0.7106060606060606,
24
+ "eval_recall": 0.9178082191780822,
25
+ "eval_runtime": 28.2754,
26
+ "eval_samples_per_second": 36.145,
27
+ "eval_steps_per_second": 1.132,
28
+ "step": 49
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 3.786695957183838,
33
+ "learning_rate": 0.00016350631440005875,
34
+ "loss": 0.4698,
35
+ "step": 98
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.8023483365949119,
40
+ "eval_f1": 0.8212389380530973,
41
+ "eval_loss": 0.436308890581131,
42
+ "eval_precision": 0.7495961227786753,
43
+ "eval_recall": 0.9080234833659491,
44
+ "eval_runtime": 28.7331,
45
+ "eval_samples_per_second": 35.569,
46
+ "eval_steps_per_second": 1.114,
47
+ "step": 98
48
+ }
49
+ ],
50
+ "logging_steps": 500,
51
+ "max_steps": 245,
52
+ "num_input_tokens_seen": 0,
53
+ "num_train_epochs": 5,
54
+ "save_steps": 500,
55
+ "total_flos": 471390394560.0,
56
+ "train_batch_size": 63,
57
+ "trial_name": null,
58
+ "trial_params": {
59
+ "alpha": 0.8444228810359851,
60
+ "learning_rate": 0.00027251052400009793,
61
+ "num_train_epochs": 5,
62
+ "per_device_train_batch_size": 63,
63
+ "temperature": 21
64
+ }
65
+ }
run-14/checkpoint-98/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a93046ce295ef56d7e5753c2ad419c6bb89f07af26dc70719f2b8f995444c3d
3
+ size 4920
run-14/checkpoint-98/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": 33,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 31,
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 sha256:3d01e2bf0e73fdbed582c60f36735fc786a4b6ef0e80eba37e34c67dae9d5508
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a93046ce295ef56d7e5753c2ad419c6bb89f07af26dc70719f2b8f995444c3d
3
  size 4920