shubingxl commited on
Commit
f10732e
1 Parent(s): ace3271

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:bff469111935cc2bc1cd9bbaf5589c2838a65a03465366366cfb8d67bd4fa733
3
  size 267835644
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d90babfab7f13cf0549f8366eee16f2fdd9bb5803022a856b8c5cf9166d8974
3
  size 267835644
run-9/checkpoint-1006/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "LABEL_0": 0,
19
+ "LABEL_1": 1,
20
+ "LABEL_2": 2
21
+ },
22
+ "max_position_embeddings": 512,
23
+ "model_type": "distilbert",
24
+ "n_heads": 12,
25
+ "n_layers": 6,
26
+ "pad_token_id": 0,
27
+ "problem_type": "single_label_classification",
28
+ "qa_dropout": 0.1,
29
+ "seq_classif_dropout": 0.2,
30
+ "sinusoidal_pos_embds": false,
31
+ "tie_weights_": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.35.2",
34
+ "vocab_size": 30522
35
+ }
run-9/checkpoint-1006/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d90babfab7f13cf0549f8366eee16f2fdd9bb5803022a856b8c5cf9166d8974
3
+ size 267835644
run-9/checkpoint-1006/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdcfc35d0237fc3b6a9fab0d89b91c20a14e25acc9a96459a8fc76cc43918889
3
+ size 535733434
run-9/checkpoint-1006/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9a6b57a2c579e7e8d28bae7183aa7ad8e4b8d2fe5fb8685f87203742427160c
3
+ size 14244
run-9/checkpoint-1006/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:176213dcb0723c4b69d2e33fe4fd6e858a814a9bc6cb895208e2b138fb17b821
3
+ size 1064
run-9/checkpoint-1006/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-1006/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-1006/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": 512,
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-9/checkpoint-1006/trainer_state.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1006,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.99,
13
+ "learning_rate": 3.0885759963845323e-06,
14
+ "loss": 0.8351,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.99,
19
+ "learning_rate": 3.6623430787168366e-08,
20
+ "loss": 0.6758,
21
+ "step": 1000
22
+ }
23
+ ],
24
+ "logging_steps": 500,
25
+ "max_steps": 1006,
26
+ "num_train_epochs": 2,
27
+ "save_steps": 500,
28
+ "total_flos": 1059559383550464.0,
29
+ "trial_name": null,
30
+ "trial_params": {
31
+ "learning_rate": 6.140528561981896e-06,
32
+ "per_device_train_batch_size": 32
33
+ }
34
+ }
run-9/checkpoint-1006/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0377ca28946d54cfb623a718d78b10b8168bbc702180279837f2d6fe696b520b
3
+ size 4600
run-9/checkpoint-1006/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec31_10-05-31_c2a715ec62ca/events.out.tfevents.1704022014.c2a715ec62ca.647.11 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:080b62e4b9d73f063f5c6c9ad57f407c6319bbede3ea4f0350ded2b3dadfa9ba
3
- size 5294
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:778a0bd443891fe77e17685b734de6fd908145c535dc8e396e0a9f9abe9422c7
3
+ size 5805