DreamyBeaver
commited on
Commit
•
1ac625c
1
Parent(s):
2b66be4
add all DistilBERT1 model files
Browse files- config.json +33 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -0
- trainer_state.json +73 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "Negative",
|
13 |
+
"1": "Positive"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"label2id": {
|
17 |
+
"Negative": 0,
|
18 |
+
"Positive": 1
|
19 |
+
},
|
20 |
+
"max_position_embeddings": 512,
|
21 |
+
"model_type": "distilbert",
|
22 |
+
"n_heads": 12,
|
23 |
+
"n_layers": 6,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"problem_type": "single_label_classification",
|
26 |
+
"qa_dropout": 0.1,
|
27 |
+
"seq_classif_dropout": 0.2,
|
28 |
+
"sinusoidal_pos_embds": false,
|
29 |
+
"tie_weights_": true,
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.27.4",
|
32 |
+
"vocab_size": 30522
|
33 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ec84c2f0f952550b58c77f24e7a9e2e22f0f65c93eee46c1e0f74e464dc8138
|
3 |
+
size 535701061
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f199e4fdffce5c83e85e08698509f156311a62cfba2f350b7f220bf7bf720ed
|
3 |
+
size 267855533
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86f0404e212b33c54e2d7fa17e310613dcbdc6e02640ff6dbe0e6e7bd9ec52e3
|
3 |
+
size 14575
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:480847c63183681bd2c27f7e8f3e7a7b7833a9deb49302dac82b9eeedcbee11c
|
3 |
+
size 627
|
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 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_lower_case": true,
|
4 |
+
"mask_token": "[MASK]",
|
5 |
+
"model_max_length": 512,
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"sep_token": "[SEP]",
|
8 |
+
"special_tokens_map_file": null,
|
9 |
+
"strip_accents": null,
|
10 |
+
"tokenize_chinese_chars": true,
|
11 |
+
"tokenizer_class": "DistilBertTokenizer",
|
12 |
+
"unk_token": "[UNK]"
|
13 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.20286166667938232,
|
3 |
+
"best_model_checkpoint": "model1/checkpoint-205",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"global_step": 1025,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"eval_accuracy": 0.931129476584022,
|
13 |
+
"eval_loss": 0.20286166667938232,
|
14 |
+
"eval_runtime": 7.2605,
|
15 |
+
"eval_samples_per_second": 149.99,
|
16 |
+
"eval_steps_per_second": 9.503,
|
17 |
+
"step": 205
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 2.0,
|
21 |
+
"eval_accuracy": 0.9357208448117539,
|
22 |
+
"eval_loss": 0.22182105481624603,
|
23 |
+
"eval_runtime": 7.6337,
|
24 |
+
"eval_samples_per_second": 142.657,
|
25 |
+
"eval_steps_per_second": 9.039,
|
26 |
+
"step": 410
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 2.44,
|
30 |
+
"learning_rate": 1.024390243902439e-05,
|
31 |
+
"loss": 0.1905,
|
32 |
+
"step": 500
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 3.0,
|
36 |
+
"eval_accuracy": 0.9357208448117539,
|
37 |
+
"eval_loss": 0.2710420787334442,
|
38 |
+
"eval_runtime": 7.705,
|
39 |
+
"eval_samples_per_second": 141.337,
|
40 |
+
"eval_steps_per_second": 8.955,
|
41 |
+
"step": 615
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 4.0,
|
45 |
+
"eval_accuracy": 0.9366391184573003,
|
46 |
+
"eval_loss": 0.29000386595726013,
|
47 |
+
"eval_runtime": 7.7216,
|
48 |
+
"eval_samples_per_second": 141.034,
|
49 |
+
"eval_steps_per_second": 8.936,
|
50 |
+
"step": 820
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 4.88,
|
54 |
+
"learning_rate": 4.878048780487805e-07,
|
55 |
+
"loss": 0.0358,
|
56 |
+
"step": 1000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 5.0,
|
60 |
+
"eval_accuracy": 0.9366391184573003,
|
61 |
+
"eval_loss": 0.30663052201271057,
|
62 |
+
"eval_runtime": 7.6339,
|
63 |
+
"eval_samples_per_second": 142.652,
|
64 |
+
"eval_steps_per_second": 9.039,
|
65 |
+
"step": 1025
|
66 |
+
}
|
67 |
+
],
|
68 |
+
"max_steps": 1025,
|
69 |
+
"num_train_epochs": 5,
|
70 |
+
"total_flos": 939897589526400.0,
|
71 |
+
"trial_name": null,
|
72 |
+
"trial_params": null
|
73 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b118a921ab6ca0db093022ec7285078dbf750a2d7daa95ef6f8cf5250ea0b49c
|
3 |
+
size 3579
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|