harrisr-smu commited on
Commit
b2dff7c
1 Parent(s): 8f75c56

Training in progress, epoch 2

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff3df08caa0c5e98037019b5d56d98eaa6fe11a9bcdae02bfbde5be20fba20e5
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9db56facae27dd63938bd4469b97730b0ab6154ca8cd3069e58cdb8013b6d695
3
  size 267832560
run-1/checkpoint-4276/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.40.0",
24
+ "vocab_size": 30522
25
+ }
run-1/checkpoint-4276/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9db56facae27dd63938bd4469b97730b0ab6154ca8cd3069e58cdb8013b6d695
3
+ size 267832560
run-1/checkpoint-4276/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b11cbcf44667def11d2afb1efce3e267427bb4ee8dbaafcfc9dd1620eda5d4fe
3
+ size 535724410
run-1/checkpoint-4276/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70dd6d26b7ec719adb2efc3d744beb6b194b378e61179c8981fdd0990b55269c
3
+ size 13990
run-1/checkpoint-4276/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b19a08284f66a3fccb98b6e0f736dc09a9e803be34a009bc6bf38070fd2a3e67
3
+ size 1064
run-1/checkpoint-4276/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-1/checkpoint-4276/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-4276/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": 1000000000000000019884624838656,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-1/checkpoint-4276/trainer_state.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4209858842371305,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-4276",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4276,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.23386342376052385,
13
+ "grad_norm": 3.146369218826294,
14
+ "learning_rate": 1.653715321124928e-06,
15
+ "loss": 0.6079,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.4677268475210477,
20
+ "grad_norm": 5.078900337219238,
21
+ "learning_rate": 1.5725712916291023e-06,
22
+ "loss": 0.6126,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.7015902712815716,
27
+ "grad_norm": 7.2771897315979,
28
+ "learning_rate": 1.4914272621332766e-06,
29
+ "loss": 0.5551,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.9354536950420954,
34
+ "grad_norm": 22.494115829467773,
35
+ "learning_rate": 1.4102832326374508e-06,
36
+ "loss": 0.523,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 1.0,
41
+ "eval_loss": 0.5956234335899353,
42
+ "eval_matthews_correlation": 0.3084289905217366,
43
+ "eval_runtime": 31.6888,
44
+ "eval_samples_per_second": 32.914,
45
+ "eval_steps_per_second": 2.083,
46
+ "step": 2138
47
+ },
48
+ {
49
+ "epoch": 1.1693171188026192,
50
+ "grad_norm": 14.600356101989746,
51
+ "learning_rate": 1.329139203141625e-06,
52
+ "loss": 0.501,
53
+ "step": 2500
54
+ },
55
+ {
56
+ "epoch": 1.4031805425631432,
57
+ "grad_norm": 20.79261589050293,
58
+ "learning_rate": 1.2479951736457994e-06,
59
+ "loss": 0.5081,
60
+ "step": 3000
61
+ },
62
+ {
63
+ "epoch": 1.637043966323667,
64
+ "grad_norm": 26.76811981201172,
65
+ "learning_rate": 1.1668511441499738e-06,
66
+ "loss": 0.4969,
67
+ "step": 3500
68
+ },
69
+ {
70
+ "epoch": 1.8709073900841908,
71
+ "grad_norm": 24.809595108032227,
72
+ "learning_rate": 1.0857071146541479e-06,
73
+ "loss": 0.5316,
74
+ "step": 4000
75
+ },
76
+ {
77
+ "epoch": 2.0,
78
+ "eval_loss": 0.5633124113082886,
79
+ "eval_matthews_correlation": 0.4209858842371305,
80
+ "eval_runtime": 30.8324,
81
+ "eval_samples_per_second": 33.828,
82
+ "eval_steps_per_second": 2.141,
83
+ "step": 4276
84
+ }
85
+ ],
86
+ "logging_steps": 500,
87
+ "max_steps": 10690,
88
+ "num_input_tokens_seen": 0,
89
+ "num_train_epochs": 5,
90
+ "save_steps": 500,
91
+ "total_flos": 65361794770440.0,
92
+ "train_batch_size": 4,
93
+ "trial_name": null,
94
+ "trial_params": {
95
+ "learning_rate": 1.7348593506207536e-06,
96
+ "num_train_epochs": 5,
97
+ "per_device_train_batch_size": 4,
98
+ "seed": 22
99
+ }
100
+ }
run-1/checkpoint-4276/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b505570bfabe2b3954b5c415db50fe70c16c7616859b303999126f730738b08
3
+ size 5048
run-1/checkpoint-4276/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Apr23_21-08-52_949a71f95aca/events.out.tfevents.1713915632.949a71f95aca.1272.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6cd1541b8f500be6968b250517007aad975c46818332b10b5fac09afa0274ac6
3
- size 5829
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9abd83113159af6f977bdce33bd735007fc0b25c931a2d285cbd67d9f165b3ab
3
+ size 7008