xuancoblab2023 commited on
Commit
bc33312
·
verified ·
1 Parent(s): 90a34dc

Training in progress, epoch 1

Browse files
logs/events.out.tfevents.1709884441.6c1c016b0e3e.7263.33 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ec778dbbe55c07bda3ac658bcdc0a31429273a9925f03fd579dac8eb78ca6ff
3
- size 5315
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4b9a6060153cb2a7293359b832efc58cf73e7e27939dd3688cc043371ebb594
3
+ size 5985
logs/events.out.tfevents.1709884664.6c1c016b0e3e.7263.34 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48d9a4837757cd9a571be8b6ccdf2f1dd4cbc62677f98a2dcc170ad5a6342e6f
3
+ size 5315
logs/events.out.tfevents.1709884774.6c1c016b0e3e.7263.35 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70d5791ae2b88b6781804554621a7c54bde05be14346ca22256d8573126a26db
3
+ size 5314
logs/events.out.tfevents.1709884885.6c1c016b0e3e.7263.36 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7be28c056a2c9b6f9deea030bff74c00b5effddb693542601b02516d2e0b695c
3
+ size 5315
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56218f772328f5c26a9e20dba2e720b46b270c6093f3e718bcd0a5f543007533
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53d2c3417d0faa8cd46da4150dfc435b00c384e5622fa50daf8292d06fb48a20
3
  size 17549312
run-36/checkpoint-48/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-36/checkpoint-48/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53d2c3417d0faa8cd46da4150dfc435b00c384e5622fa50daf8292d06fb48a20
3
+ size 17549312
run-36/checkpoint-48/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:342140da4a006c86f9f1081603d11ac834e084c79b1e604414d953230d2c4116
3
+ size 35122746
run-36/checkpoint-48/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f731098665929ed6a815501631b54240caaac6508207c5c55cf0fe36ad39b17
3
+ size 14054
run-36/checkpoint-48/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c66e2d559655d432b08d1bd7c2e99ac509f6a007eb8c2c91c6974d17ed07ad47
3
+ size 1064
run-36/checkpoint-48/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-36/checkpoint-48/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-36/checkpoint-48/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-36/checkpoint-48/trainer_state.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7720156555772995,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-36/checkpoint-48",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 48,
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": 1.4985426664352417,
14
+ "learning_rate": 0.00025479667550083805,
15
+ "loss": 0.5846,
16
+ "step": 48
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7720156555772995,
21
+ "eval_f1": 0.8023748939779475,
22
+ "eval_loss": 0.4796183109283447,
23
+ "eval_precision": 0.7080838323353293,
24
+ "eval_recall": 0.9256360078277887,
25
+ "eval_runtime": 26.9949,
26
+ "eval_samples_per_second": 37.859,
27
+ "eval_steps_per_second": 0.593,
28
+ "step": 48
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 192,
33
+ "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 4,
35
+ "save_steps": 500,
36
+ "total_flos": 235695197280.0,
37
+ "train_batch_size": 64,
38
+ "trial_name": null,
39
+ "trial_params": {
40
+ "alpha": 0.9446546130666404,
41
+ "learning_rate": 0.00033972890066778403,
42
+ "num_train_epochs": 4,
43
+ "temperature": 23
44
+ }
45
+ }
run-36/checkpoint-48/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe203592d05041dc073425728d1182a1bebcfc0f3a53412e4a381b28f50ad18a
3
+ size 4920
run-36/checkpoint-48/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 sha256:58fea57f032e46adee993684d2bb27d6f7241d7a66f7ca178a5e2563440a0887
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe203592d05041dc073425728d1182a1bebcfc0f3a53412e4a381b28f50ad18a
3
  size 4920