Kira-Floris commited on
Commit
59ac7bb
1 Parent(s): 1d73b59

Training in progress, epoch 3

Browse files
logs/events.out.tfevents.1719308784.852b1e905a9a.223.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d0dd7d13e83f491c7ae00077f7ae50c35d01e8db8af005bf686802773e305a0
3
- size 5962
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:497297a34128c670d01cba52de6849d5c675c9e51568c5569fc4dd5fb14de307
3
+ size 6496
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d0b6d2eecc75bbe6198fcb3b4edb95a144135c14e335038dd778367dfc1d9e1
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c42ba5a9fad098334a5ba5033735652b64d22092d486d7be95ef81de6daa4a3d
3
  size 17549312
run-3/checkpoint-1581/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": "4.41.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-3/checkpoint-1581/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c42ba5a9fad098334a5ba5033735652b64d22092d486d7be95ef81de6daa4a3d
3
+ size 17549312
run-3/checkpoint-1581/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d2f9c3f5aa6bad9da28e04154aeb2c96eebd25de092d85734c896af7d85a60a
3
+ size 35123898
run-3/checkpoint-1581/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a82df51000915659b456ad52af3debde383df68929936f84f551af1b1989186
3
+ size 14308
run-3/checkpoint-1581/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:568b24087791ab34ea4e61da448dba6d2a4d9a829136becdaa9e0c7cedc61e0b
3
+ size 1064
run-3/checkpoint-1581/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-3/checkpoint-1581/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-1581/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-3/checkpoint-1581/trainer_state.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8245412844036697,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-3/checkpoint-1581",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1581,
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": 31.228694915771484,
14
+ "learning_rate": 7.086160775881376e-05,
15
+ "loss": 2.5988,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8061926605504587,
21
+ "eval_loss": 1.924224615097046,
22
+ "eval_runtime": 2.5772,
23
+ "eval_samples_per_second": 338.351,
24
+ "eval_steps_per_second": 2.716,
25
+ "step": 527
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": 51.49909591674805,
30
+ "learning_rate": 5.9055073680756574e-05,
31
+ "loss": 1.2849,
32
+ "step": 1054
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.8176605504587156,
37
+ "eval_loss": 1.7333961725234985,
38
+ "eval_runtime": 2.54,
39
+ "eval_samples_per_second": 343.313,
40
+ "eval_steps_per_second": 2.756,
41
+ "step": 1054
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "grad_norm": 84.45722961425781,
46
+ "learning_rate": 4.72485396026994e-05,
47
+ "loss": 0.9617,
48
+ "step": 1581
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.8245412844036697,
53
+ "eval_loss": 1.7150405645370483,
54
+ "eval_runtime": 2.5578,
55
+ "eval_samples_per_second": 340.916,
56
+ "eval_steps_per_second": 2.737,
57
+ "step": 1581
58
+ }
59
+ ],
60
+ "logging_steps": 500,
61
+ "max_steps": 3689,
62
+ "num_input_tokens_seen": 0,
63
+ "num_train_epochs": 7,
64
+ "save_steps": 500,
65
+ "stateful_callbacks": {
66
+ "TrainerControl": {
67
+ "args": {
68
+ "should_epoch_stop": false,
69
+ "should_evaluate": false,
70
+ "should_log": false,
71
+ "should_save": true,
72
+ "should_training_stop": false
73
+ },
74
+ "attributes": {}
75
+ }
76
+ },
77
+ "total_flos": 24228458327580.0,
78
+ "train_batch_size": 128,
79
+ "trial_name": null,
80
+ "trial_params": {
81
+ "alpha": 0.1351029311037084,
82
+ "learning_rate": 8.264573854640023e-05,
83
+ "num_train_epochs": 7,
84
+ "temperature": 16
85
+ }
86
+ }
run-3/checkpoint-1581/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb39e5a6519b65bdbd04bcdb6f5e6f1991f6196e0c3617b3126fe14176729f26
3
+ size 5176
run-3/checkpoint-1581/vocab.txt ADDED
The diff for this file is too large to render. See raw diff