Commit
•
a0d9b26
1
Parent(s):
07fdfc3
Upload 10 files
Browse files- config.json +27 -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_config.json +57 -0
- trainer_state.json +245 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "../bert/bert-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"problem_type": "single_label_classification",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.40.1",
|
24 |
+
"type_vocab_size": 2,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 28996
|
27 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ff713d03fdc64edd6aa6e48b4ef2175551684d939feb6db2228272aea7a23d6
|
3 |
+
size 433270768
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4d639e13af570c5183e56a5c4d6cff2a89b4daa2999ab20641a115751e16f3d
|
3 |
+
size 866662650
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3209d1c30481708b0335f5ae4346170cd516f721cbb47c8fc80bcedaa1106274
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46771f4187a1f7ac7feb66e2a691bff939803d481ac434f77c3d0df884f076d9
|
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_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": false,
|
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 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,245 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 7299,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.20550760378133992,
|
13 |
+
"grad_norm": 0.022213317453861237,
|
14 |
+
"learning_rate": 1.8629949308124403e-05,
|
15 |
+
"loss": 0.1893,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.20550760378133992,
|
20 |
+
"eval_accuracy": 0.9274409044193217,
|
21 |
+
"eval_loss": 0.384206622838974,
|
22 |
+
"eval_runtime": 66.4904,
|
23 |
+
"eval_samples_per_second": 73.168,
|
24 |
+
"eval_steps_per_second": 9.159,
|
25 |
+
"step": 500
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 0.41101520756267984,
|
29 |
+
"grad_norm": 0.016410009935498238,
|
30 |
+
"learning_rate": 1.7259898616248804e-05,
|
31 |
+
"loss": 0.0675,
|
32 |
+
"step": 1000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.41101520756267984,
|
36 |
+
"eval_accuracy": 0.994655704008222,
|
37 |
+
"eval_loss": 0.028500495478510857,
|
38 |
+
"eval_runtime": 66.4366,
|
39 |
+
"eval_samples_per_second": 73.228,
|
40 |
+
"eval_steps_per_second": 9.167,
|
41 |
+
"step": 1000
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 0.6165228113440198,
|
45 |
+
"grad_norm": 0.013172637671232224,
|
46 |
+
"learning_rate": 1.58898479243732e-05,
|
47 |
+
"loss": 0.0519,
|
48 |
+
"step": 1500
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 0.6165228113440198,
|
52 |
+
"eval_accuracy": 0.9852004110996917,
|
53 |
+
"eval_loss": 0.06652244180440903,
|
54 |
+
"eval_runtime": 37.1596,
|
55 |
+
"eval_samples_per_second": 130.922,
|
56 |
+
"eval_steps_per_second": 16.389,
|
57 |
+
"step": 1500
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.8220304151253597,
|
61 |
+
"grad_norm": 93.64683532714844,
|
62 |
+
"learning_rate": 1.4519797232497603e-05,
|
63 |
+
"loss": 0.0287,
|
64 |
+
"step": 2000
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 0.8220304151253597,
|
68 |
+
"eval_accuracy": 0.9891058581706064,
|
69 |
+
"eval_loss": 0.05017192289233208,
|
70 |
+
"eval_runtime": 31.6255,
|
71 |
+
"eval_samples_per_second": 153.832,
|
72 |
+
"eval_steps_per_second": 19.257,
|
73 |
+
"step": 2000
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 1.0275380189066996,
|
77 |
+
"grad_norm": 0.004394204821437597,
|
78 |
+
"learning_rate": 1.3149746540622004e-05,
|
79 |
+
"loss": 0.0334,
|
80 |
+
"step": 2500
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 1.0275380189066996,
|
84 |
+
"eval_accuracy": 0.9905447070914697,
|
85 |
+
"eval_loss": 0.04894111305475235,
|
86 |
+
"eval_runtime": 47.4094,
|
87 |
+
"eval_samples_per_second": 102.617,
|
88 |
+
"eval_steps_per_second": 12.846,
|
89 |
+
"step": 2500
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 1.2330456226880395,
|
93 |
+
"grad_norm": 0.0032397848553955555,
|
94 |
+
"learning_rate": 1.1779695848746405e-05,
|
95 |
+
"loss": 0.0218,
|
96 |
+
"step": 3000
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 1.2330456226880395,
|
100 |
+
"eval_accuracy": 0.9819116135662899,
|
101 |
+
"eval_loss": 0.10269968956708908,
|
102 |
+
"eval_runtime": 45.531,
|
103 |
+
"eval_samples_per_second": 106.85,
|
104 |
+
"eval_steps_per_second": 13.375,
|
105 |
+
"step": 3000
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 1.4385532264693794,
|
109 |
+
"grad_norm": 0.0003408812917768955,
|
110 |
+
"learning_rate": 1.0409645156870804e-05,
|
111 |
+
"loss": 0.0102,
|
112 |
+
"step": 3500
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 1.4385532264693794,
|
116 |
+
"eval_accuracy": 0.9944501541623844,
|
117 |
+
"eval_loss": 0.04378344491124153,
|
118 |
+
"eval_runtime": 45.7881,
|
119 |
+
"eval_samples_per_second": 106.25,
|
120 |
+
"eval_steps_per_second": 13.3,
|
121 |
+
"step": 3500
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 1.6440608302507194,
|
125 |
+
"grad_norm": 0.0026256833225488663,
|
126 |
+
"learning_rate": 9.039594464995205e-06,
|
127 |
+
"loss": 0.0038,
|
128 |
+
"step": 4000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.6440608302507194,
|
132 |
+
"eval_accuracy": 0.9704008221993834,
|
133 |
+
"eval_loss": 0.19674982130527496,
|
134 |
+
"eval_runtime": 45.5104,
|
135 |
+
"eval_samples_per_second": 106.899,
|
136 |
+
"eval_steps_per_second": 13.382,
|
137 |
+
"step": 4000
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 1.8495684340320593,
|
141 |
+
"grad_norm": 0.0002484402502886951,
|
142 |
+
"learning_rate": 7.669543773119606e-06,
|
143 |
+
"loss": 0.012,
|
144 |
+
"step": 4500
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 1.8495684340320593,
|
148 |
+
"eval_accuracy": 0.9852004110996917,
|
149 |
+
"eval_loss": 0.07537884265184402,
|
150 |
+
"eval_runtime": 45.1736,
|
151 |
+
"eval_samples_per_second": 107.696,
|
152 |
+
"eval_steps_per_second": 13.481,
|
153 |
+
"step": 4500
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 2.055076037813399,
|
157 |
+
"grad_norm": 0.0006908943178132176,
|
158 |
+
"learning_rate": 6.299493081244007e-06,
|
159 |
+
"loss": 0.0061,
|
160 |
+
"step": 5000
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 2.055076037813399,
|
164 |
+
"eval_accuracy": 0.9730729701952724,
|
165 |
+
"eval_loss": 0.166794553399086,
|
166 |
+
"eval_runtime": 45.1304,
|
167 |
+
"eval_samples_per_second": 107.799,
|
168 |
+
"eval_steps_per_second": 13.494,
|
169 |
+
"step": 5000
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 2.260583641594739,
|
173 |
+
"grad_norm": 0.00021314685000106692,
|
174 |
+
"learning_rate": 4.929442389368407e-06,
|
175 |
+
"loss": 0.003,
|
176 |
+
"step": 5500
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 2.260583641594739,
|
180 |
+
"eval_accuracy": 0.9954779033915725,
|
181 |
+
"eval_loss": 0.03057803027331829,
|
182 |
+
"eval_runtime": 45.2961,
|
183 |
+
"eval_samples_per_second": 107.404,
|
184 |
+
"eval_steps_per_second": 13.445,
|
185 |
+
"step": 5500
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 2.466091245376079,
|
189 |
+
"grad_norm": 0.00010584539995761588,
|
190 |
+
"learning_rate": 3.5593916974928076e-06,
|
191 |
+
"loss": 0.0,
|
192 |
+
"step": 6000
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 2.466091245376079,
|
196 |
+
"eval_accuracy": 0.9926002055498458,
|
197 |
+
"eval_loss": 0.05110383406281471,
|
198 |
+
"eval_runtime": 45.54,
|
199 |
+
"eval_samples_per_second": 106.829,
|
200 |
+
"eval_steps_per_second": 13.373,
|
201 |
+
"step": 6000
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 2.671598849157419,
|
205 |
+
"grad_norm": 9.755617793416604e-05,
|
206 |
+
"learning_rate": 2.189341005617208e-06,
|
207 |
+
"loss": 0.0,
|
208 |
+
"step": 6500
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"epoch": 2.671598849157419,
|
212 |
+
"eval_accuracy": 0.9921891058581707,
|
213 |
+
"eval_loss": 0.05986848846077919,
|
214 |
+
"eval_runtime": 45.0163,
|
215 |
+
"eval_samples_per_second": 108.072,
|
216 |
+
"eval_steps_per_second": 13.528,
|
217 |
+
"step": 6500
|
218 |
+
},
|
219 |
+
{
|
220 |
+
"epoch": 2.877106452938759,
|
221 |
+
"grad_norm": 0.00011223769251955673,
|
222 |
+
"learning_rate": 8.192903137416085e-07,
|
223 |
+
"loss": 0.0003,
|
224 |
+
"step": 7000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 2.877106452938759,
|
228 |
+
"eval_accuracy": 0.9868448098663926,
|
229 |
+
"eval_loss": 0.09568490833044052,
|
230 |
+
"eval_runtime": 45.1871,
|
231 |
+
"eval_samples_per_second": 107.663,
|
232 |
+
"eval_steps_per_second": 13.477,
|
233 |
+
"step": 7000
|
234 |
+
}
|
235 |
+
],
|
236 |
+
"logging_steps": 500,
|
237 |
+
"max_steps": 7299,
|
238 |
+
"num_input_tokens_seen": 0,
|
239 |
+
"num_train_epochs": 3,
|
240 |
+
"save_steps": 500,
|
241 |
+
"total_flos": 1.195019939840466e+16,
|
242 |
+
"train_batch_size": 8,
|
243 |
+
"trial_name": null,
|
244 |
+
"trial_params": null
|
245 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:facd0955eff232fdd93c4b50b52e66a804de2814fc50eba14e5ddc14fde2bfdc
|
3 |
+
size 4984
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|