kweinmeister
commited on
Upload folder using huggingface_hub
Browse files- config.json +35 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- trainer_state.json +117 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert/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": "4.44.2",
|
34 |
+
"vocab_size": 30522
|
35 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd2329ab5ce3b93f0caa99a4430e9453d497df2fd777b2ead0d6c245dfca8272
|
3 |
+
size 267835644
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8d9dbd49c988e1a2552f46312c6309589777d6f25c1fd93fe658227093ef799
|
3 |
+
size 535733434
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78053ce5a30e6b47a1e7f04171a66edd54501be4b9c272de3ce27de6492d29c5
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:545fb5c5cc23106f0ac26d94d16d0879fc06d04ac2ce217bd348afc2cdc2b686
|
3 |
+
size 1064
|
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 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 6365,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.3927729772191673,
|
13 |
+
"grad_norm": 2.493880033493042,
|
14 |
+
"learning_rate": 4.6072270227808326e-05,
|
15 |
+
"loss": 0.7773,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.7855459544383346,
|
20 |
+
"grad_norm": 3.362963914871216,
|
21 |
+
"learning_rate": 4.2144540455616656e-05,
|
22 |
+
"loss": 0.6407,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 1.178318931657502,
|
27 |
+
"grad_norm": 3.4124033451080322,
|
28 |
+
"learning_rate": 3.821681068342498e-05,
|
29 |
+
"loss": 0.5413,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 1.5710919088766693,
|
34 |
+
"grad_norm": 5.418175220489502,
|
35 |
+
"learning_rate": 3.42890809112333e-05,
|
36 |
+
"loss": 0.4516,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 1.9638648860958368,
|
41 |
+
"grad_norm": 4.3173418045043945,
|
42 |
+
"learning_rate": 3.0361351139041634e-05,
|
43 |
+
"loss": 0.442,
|
44 |
+
"step": 2500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 2.356637863315004,
|
48 |
+
"grad_norm": 4.252607345581055,
|
49 |
+
"learning_rate": 2.6433621366849964e-05,
|
50 |
+
"loss": 0.3087,
|
51 |
+
"step": 3000
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 2.7494108405341713,
|
55 |
+
"grad_norm": 4.939857482910156,
|
56 |
+
"learning_rate": 2.2505891594658287e-05,
|
57 |
+
"loss": 0.2938,
|
58 |
+
"step": 3500
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 3.1421838177533385,
|
62 |
+
"grad_norm": 3.5636911392211914,
|
63 |
+
"learning_rate": 1.8578161822466618e-05,
|
64 |
+
"loss": 0.2533,
|
65 |
+
"step": 4000
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 3.534956794972506,
|
69 |
+
"grad_norm": 4.615169048309326,
|
70 |
+
"learning_rate": 1.4650432050274943e-05,
|
71 |
+
"loss": 0.1909,
|
72 |
+
"step": 4500
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 3.927729772191673,
|
76 |
+
"grad_norm": 4.99422025680542,
|
77 |
+
"learning_rate": 1.0722702278083268e-05,
|
78 |
+
"loss": 0.1856,
|
79 |
+
"step": 5000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 4.32050274941084,
|
83 |
+
"grad_norm": 4.294362545013428,
|
84 |
+
"learning_rate": 6.794972505891594e-06,
|
85 |
+
"loss": 0.1385,
|
86 |
+
"step": 5500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 4.713275726630008,
|
90 |
+
"grad_norm": 5.682995319366455,
|
91 |
+
"learning_rate": 2.8672427336999217e-06,
|
92 |
+
"loss": 0.1274,
|
93 |
+
"step": 6000
|
94 |
+
}
|
95 |
+
],
|
96 |
+
"logging_steps": 500,
|
97 |
+
"max_steps": 6365,
|
98 |
+
"num_input_tokens_seen": 0,
|
99 |
+
"num_train_epochs": 5,
|
100 |
+
"save_steps": 500,
|
101 |
+
"stateful_callbacks": {
|
102 |
+
"TrainerControl": {
|
103 |
+
"args": {
|
104 |
+
"should_epoch_stop": false,
|
105 |
+
"should_evaluate": false,
|
106 |
+
"should_log": false,
|
107 |
+
"should_save": true,
|
108 |
+
"should_training_stop": true
|
109 |
+
},
|
110 |
+
"attributes": {}
|
111 |
+
}
|
112 |
+
},
|
113 |
+
"total_flos": 2.69683595364672e+16,
|
114 |
+
"train_batch_size": 128,
|
115 |
+
"trial_name": null,
|
116 |
+
"trial_params": null
|
117 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa1d4ae3b2cf9e6fd3e3cf4f179d37486b9b64ec19f402e7a7f3e1aa9edde9bd
|
3 |
+
size 5176
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|