Step 28592
Browse files- all_results.json +14 -0
- config.json +2 -2
- eval_results.json +8 -0
- pytorch_model.bin +2 -2
- tokenizer.json +2 -16
- train_results.json +8 -0
- trainer_state.json +299 -62
- training_args.bin +2 -2
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"eval_accuracy": 0.9464938640594482,
|
4 |
+
"eval_loss": 0.30927810072898865,
|
5 |
+
"eval_runtime": 134.3304,
|
6 |
+
"eval_samples": 3009,
|
7 |
+
"eval_samples_per_second": 22.4,
|
8 |
+
"eval_steps_per_second": 1.407,
|
9 |
+
"train_loss": 0.1776402507509504,
|
10 |
+
"train_runtime": 7042.0183,
|
11 |
+
"train_samples": 21714,
|
12 |
+
"train_samples_per_second": 12.334,
|
13 |
+
"train_steps_per_second": 4.111
|
14 |
+
}
|
config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"_name_or_path": "bert-base-chinese",
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"classifier_dropout": null,
|
@@ -24,7 +24,7 @@
|
|
24 |
"pooler_type": "first_token_transform",
|
25 |
"position_embedding_type": "absolute",
|
26 |
"torch_dtype": "float32",
|
27 |
-
"transformers_version": "4.
|
28 |
"type_vocab_size": 2,
|
29 |
"use_cache": true,
|
30 |
"vocab_size": 21128
|
|
|
1 |
{
|
2 |
"_name_or_path": "bert-base-chinese",
|
3 |
"architectures": [
|
4 |
+
"BertForMultipleChoice"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"classifier_dropout": null,
|
|
|
24 |
"pooler_type": "first_token_transform",
|
25 |
"position_embedding_type": "absolute",
|
26 |
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.18.0",
|
28 |
"type_vocab_size": 2,
|
29 |
"use_cache": true,
|
30 |
"vocab_size": 21128
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eval_accuracy": 0.9464938640594482,
|
3 |
+
"eval_loss": 0.30927810072898865,
|
4 |
+
"eval_runtime": 134.3304,
|
5 |
+
"eval_samples": 3009,
|
6 |
+
"eval_samples_per_second": 22.4,
|
7 |
+
"eval_steps_per_second": 1.407
|
8 |
+
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8f62f85c3b9b343d4a3af5fc2b862807c8bfc411d34a21b043bd6d0702d7fa8
|
3 |
+
size 143720448
|
tokenizer.json
CHANGED
@@ -1,21 +1,7 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
5 |
-
"max_length": 384,
|
6 |
-
"strategy": "OnlySecond",
|
7 |
-
"stride": 128
|
8 |
-
},
|
9 |
-
"padding": {
|
10 |
-
"strategy": {
|
11 |
-
"Fixed": 384
|
12 |
-
},
|
13 |
-
"direction": "Right",
|
14 |
-
"pad_to_multiple_of": null,
|
15 |
-
"pad_id": 0,
|
16 |
-
"pad_type_id": 0,
|
17 |
-
"pad_token": "[PAD]"
|
18 |
-
},
|
19 |
"added_tokens": [
|
20 |
{
|
21 |
"id": 0,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"train_loss": 0.1776402507509504,
|
4 |
+
"train_runtime": 7042.0183,
|
5 |
+
"train_samples": 21714,
|
6 |
+
"train_samples_per_second": 12.334,
|
7 |
+
"train_steps_per_second": 4.111
|
8 |
+
}
|
trainer_state.json
CHANGED
@@ -1,130 +1,367 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
-
"epoch": 0.
|
12 |
-
"learning_rate":
|
13 |
-
"loss":
|
14 |
"step": 500
|
15 |
},
|
16 |
{
|
17 |
-
"epoch": 0.
|
18 |
-
"learning_rate":
|
19 |
-
"loss": 0.
|
20 |
"step": 1000
|
21 |
},
|
22 |
{
|
23 |
-
"epoch": 0.
|
24 |
-
"learning_rate":
|
25 |
-
"loss": 0.
|
26 |
"step": 1500
|
27 |
},
|
28 |
{
|
29 |
-
"epoch": 0.
|
30 |
-
"learning_rate":
|
31 |
-
"loss": 0.
|
32 |
"step": 2000
|
33 |
},
|
34 |
{
|
35 |
-
"epoch": 0.
|
36 |
-
"learning_rate":
|
37 |
-
"loss": 0.
|
38 |
"step": 2500
|
39 |
},
|
40 |
{
|
41 |
-
"epoch": 0.
|
42 |
-
"learning_rate":
|
43 |
-
"loss": 0.
|
44 |
"step": 3000
|
45 |
},
|
46 |
{
|
47 |
-
"epoch":
|
48 |
-
"learning_rate":
|
49 |
-
"loss": 0.
|
50 |
"step": 3500
|
51 |
},
|
52 |
{
|
53 |
-
"epoch":
|
54 |
-
"learning_rate":
|
55 |
-
"loss": 0.
|
56 |
"step": 4000
|
57 |
},
|
58 |
{
|
59 |
-
"epoch":
|
60 |
-
"learning_rate":
|
61 |
-
"loss": 0.
|
62 |
"step": 4500
|
63 |
},
|
64 |
{
|
65 |
-
"epoch":
|
66 |
-
"learning_rate":
|
67 |
-
"loss": 0.
|
68 |
"step": 5000
|
69 |
},
|
70 |
{
|
71 |
-
"epoch":
|
72 |
-
"learning_rate":
|
73 |
-
"loss": 0.
|
74 |
"step": 5500
|
75 |
},
|
76 |
{
|
77 |
-
"epoch":
|
78 |
-
"learning_rate":
|
79 |
-
"loss": 0.
|
80 |
"step": 6000
|
81 |
},
|
82 |
{
|
83 |
-
"epoch":
|
84 |
-
"learning_rate":
|
85 |
-
"loss": 0.
|
86 |
"step": 6500
|
87 |
},
|
88 |
{
|
89 |
-
"epoch":
|
90 |
-
"learning_rate":
|
91 |
-
"loss": 0.
|
92 |
"step": 7000
|
93 |
},
|
94 |
{
|
95 |
-
"epoch":
|
96 |
-
"learning_rate":
|
97 |
-
"loss": 0.
|
98 |
"step": 7500
|
99 |
},
|
100 |
{
|
101 |
-
"epoch":
|
102 |
-
"learning_rate":
|
103 |
-
"loss": 0.
|
104 |
"step": 8000
|
105 |
},
|
106 |
{
|
107 |
-
"epoch":
|
108 |
-
"learning_rate": 3.
|
109 |
-
"loss": 0.
|
110 |
"step": 8500
|
111 |
},
|
112 |
{
|
113 |
-
"epoch":
|
114 |
-
"learning_rate":
|
115 |
-
"loss": 0.
|
116 |
"step": 9000
|
117 |
},
|
118 |
{
|
119 |
-
"epoch":
|
120 |
-
"learning_rate":
|
121 |
-
"loss": 0.
|
122 |
"step": 9500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
123 |
}
|
124 |
],
|
125 |
-
"max_steps":
|
126 |
-
"num_train_epochs":
|
127 |
-
"total_flos":
|
128 |
"trial_name": null,
|
129 |
"trial_params": null
|
130 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.0,
|
5 |
+
"global_step": 28952,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
+
"epoch": 0.07,
|
12 |
+
"learning_rate": 4.913650179607627e-05,
|
13 |
+
"loss": 0.3611,
|
14 |
"step": 500
|
15 |
},
|
16 |
{
|
17 |
+
"epoch": 0.14,
|
18 |
+
"learning_rate": 4.827300359215253e-05,
|
19 |
+
"loss": 0.2469,
|
20 |
"step": 1000
|
21 |
},
|
22 |
{
|
23 |
+
"epoch": 0.21,
|
24 |
+
"learning_rate": 4.740950538822879e-05,
|
25 |
+
"loss": 0.307,
|
26 |
"step": 1500
|
27 |
},
|
28 |
{
|
29 |
+
"epoch": 0.28,
|
30 |
+
"learning_rate": 4.6546007184305056e-05,
|
31 |
+
"loss": 0.3492,
|
32 |
"step": 2000
|
33 |
},
|
34 |
{
|
35 |
+
"epoch": 0.35,
|
36 |
+
"learning_rate": 4.568250898038132e-05,
|
37 |
+
"loss": 0.2257,
|
38 |
"step": 2500
|
39 |
},
|
40 |
{
|
41 |
+
"epoch": 0.41,
|
42 |
+
"learning_rate": 4.4819010776457586e-05,
|
43 |
+
"loss": 0.293,
|
44 |
"step": 3000
|
45 |
},
|
46 |
{
|
47 |
+
"epoch": 0.48,
|
48 |
+
"learning_rate": 4.395551257253385e-05,
|
49 |
+
"loss": 0.3023,
|
50 |
"step": 3500
|
51 |
},
|
52 |
{
|
53 |
+
"epoch": 0.55,
|
54 |
+
"learning_rate": 4.3092014368610116e-05,
|
55 |
+
"loss": 0.2834,
|
56 |
"step": 4000
|
57 |
},
|
58 |
{
|
59 |
+
"epoch": 0.62,
|
60 |
+
"learning_rate": 4.2228516164686374e-05,
|
61 |
+
"loss": 0.3275,
|
62 |
"step": 4500
|
63 |
},
|
64 |
{
|
65 |
+
"epoch": 0.69,
|
66 |
+
"learning_rate": 4.136501796076264e-05,
|
67 |
+
"loss": 0.2694,
|
68 |
"step": 5000
|
69 |
},
|
70 |
{
|
71 |
+
"epoch": 0.76,
|
72 |
+
"learning_rate": 4.0501519756838904e-05,
|
73 |
+
"loss": 0.2631,
|
74 |
"step": 5500
|
75 |
},
|
76 |
{
|
77 |
+
"epoch": 0.83,
|
78 |
+
"learning_rate": 3.963802155291517e-05,
|
79 |
+
"loss": 0.2773,
|
80 |
"step": 6000
|
81 |
},
|
82 |
{
|
83 |
+
"epoch": 0.9,
|
84 |
+
"learning_rate": 3.8774523348991434e-05,
|
85 |
+
"loss": 0.3141,
|
86 |
"step": 6500
|
87 |
},
|
88 |
{
|
89 |
+
"epoch": 0.97,
|
90 |
+
"learning_rate": 3.79110251450677e-05,
|
91 |
+
"loss": 0.2893,
|
92 |
"step": 7000
|
93 |
},
|
94 |
{
|
95 |
+
"epoch": 1.04,
|
96 |
+
"learning_rate": 3.7047526941143964e-05,
|
97 |
+
"loss": 0.2038,
|
98 |
"step": 7500
|
99 |
},
|
100 |
{
|
101 |
+
"epoch": 1.11,
|
102 |
+
"learning_rate": 3.618402873722023e-05,
|
103 |
+
"loss": 0.2157,
|
104 |
"step": 8000
|
105 |
},
|
106 |
{
|
107 |
+
"epoch": 1.17,
|
108 |
+
"learning_rate": 3.5320530533296494e-05,
|
109 |
+
"loss": 0.2771,
|
110 |
"step": 8500
|
111 |
},
|
112 |
{
|
113 |
+
"epoch": 1.24,
|
114 |
+
"learning_rate": 3.445703232937276e-05,
|
115 |
+
"loss": 0.2511,
|
116 |
"step": 9000
|
117 |
},
|
118 |
{
|
119 |
+
"epoch": 1.31,
|
120 |
+
"learning_rate": 3.3593534125449024e-05,
|
121 |
+
"loss": 0.2678,
|
122 |
"step": 9500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 1.38,
|
126 |
+
"learning_rate": 3.273003592152529e-05,
|
127 |
+
"loss": 0.1795,
|
128 |
+
"step": 10000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.45,
|
132 |
+
"learning_rate": 3.186653771760155e-05,
|
133 |
+
"loss": 0.2357,
|
134 |
+
"step": 10500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 1.52,
|
138 |
+
"learning_rate": 3.100303951367781e-05,
|
139 |
+
"loss": 0.2187,
|
140 |
+
"step": 11000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 1.59,
|
144 |
+
"learning_rate": 3.0139541309754078e-05,
|
145 |
+
"loss": 0.2315,
|
146 |
+
"step": 11500
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 1.66,
|
150 |
+
"learning_rate": 2.9276043105830343e-05,
|
151 |
+
"loss": 0.2478,
|
152 |
+
"step": 12000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 1.73,
|
156 |
+
"learning_rate": 2.8412544901906608e-05,
|
157 |
+
"loss": 0.2444,
|
158 |
+
"step": 12500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 1.8,
|
162 |
+
"learning_rate": 2.7549046697982873e-05,
|
163 |
+
"loss": 0.3056,
|
164 |
+
"step": 13000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 1.87,
|
168 |
+
"learning_rate": 2.668554849405913e-05,
|
169 |
+
"loss": 0.2881,
|
170 |
+
"step": 13500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 1.93,
|
174 |
+
"learning_rate": 2.5822050290135396e-05,
|
175 |
+
"loss": 0.3426,
|
176 |
+
"step": 14000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 2.0,
|
180 |
+
"learning_rate": 2.495855208621166e-05,
|
181 |
+
"loss": 0.1894,
|
182 |
+
"step": 14500
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 2.07,
|
186 |
+
"learning_rate": 2.4095053882287926e-05,
|
187 |
+
"loss": 0.1381,
|
188 |
+
"step": 15000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 2.14,
|
192 |
+
"learning_rate": 2.3231555678364188e-05,
|
193 |
+
"loss": 0.1359,
|
194 |
+
"step": 15500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 2.21,
|
198 |
+
"learning_rate": 2.2368057474440453e-05,
|
199 |
+
"loss": 0.1179,
|
200 |
+
"step": 16000
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 2.28,
|
204 |
+
"learning_rate": 2.1504559270516718e-05,
|
205 |
+
"loss": 0.1048,
|
206 |
+
"step": 16500
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 2.35,
|
210 |
+
"learning_rate": 2.0641061066592983e-05,
|
211 |
+
"loss": 0.141,
|
212 |
+
"step": 17000
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 2.42,
|
216 |
+
"learning_rate": 1.9777562862669248e-05,
|
217 |
+
"loss": 0.1726,
|
218 |
+
"step": 17500
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 2.49,
|
222 |
+
"learning_rate": 1.8914064658745513e-05,
|
223 |
+
"loss": 0.1307,
|
224 |
+
"step": 18000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 2.56,
|
228 |
+
"learning_rate": 1.8050566454821775e-05,
|
229 |
+
"loss": 0.1875,
|
230 |
+
"step": 18500
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 2.63,
|
234 |
+
"learning_rate": 1.718706825089804e-05,
|
235 |
+
"loss": 0.0803,
|
236 |
+
"step": 19000
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 2.69,
|
240 |
+
"learning_rate": 1.6323570046974305e-05,
|
241 |
+
"loss": 0.1028,
|
242 |
+
"step": 19500
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 2.76,
|
246 |
+
"learning_rate": 1.5460071843050566e-05,
|
247 |
+
"loss": 0.1484,
|
248 |
+
"step": 20000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 2.83,
|
252 |
+
"learning_rate": 1.4596573639126831e-05,
|
253 |
+
"loss": 0.1042,
|
254 |
+
"step": 20500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 2.9,
|
258 |
+
"learning_rate": 1.3733075435203096e-05,
|
259 |
+
"loss": 0.1325,
|
260 |
+
"step": 21000
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 2.97,
|
264 |
+
"learning_rate": 1.286957723127936e-05,
|
265 |
+
"loss": 0.1005,
|
266 |
+
"step": 21500
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 3.04,
|
270 |
+
"learning_rate": 1.2006079027355625e-05,
|
271 |
+
"loss": 0.0656,
|
272 |
+
"step": 22000
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 3.11,
|
276 |
+
"learning_rate": 1.1142580823431888e-05,
|
277 |
+
"loss": 0.0533,
|
278 |
+
"step": 22500
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 3.18,
|
282 |
+
"learning_rate": 1.0279082619508151e-05,
|
283 |
+
"loss": 0.0527,
|
284 |
+
"step": 23000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 3.25,
|
288 |
+
"learning_rate": 9.415584415584416e-06,
|
289 |
+
"loss": 0.0241,
|
290 |
+
"step": 23500
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 3.32,
|
294 |
+
"learning_rate": 8.55208621166068e-06,
|
295 |
+
"loss": 0.0463,
|
296 |
+
"step": 24000
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 3.38,
|
300 |
+
"learning_rate": 7.688588007736943e-06,
|
301 |
+
"loss": 0.0746,
|
302 |
+
"step": 24500
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 3.45,
|
306 |
+
"learning_rate": 6.825089803813209e-06,
|
307 |
+
"loss": 0.0723,
|
308 |
+
"step": 25000
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 3.52,
|
312 |
+
"learning_rate": 5.961591599889472e-06,
|
313 |
+
"loss": 0.044,
|
314 |
+
"step": 25500
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 3.59,
|
318 |
+
"learning_rate": 5.098093395965737e-06,
|
319 |
+
"loss": 0.0451,
|
320 |
+
"step": 26000
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 3.66,
|
324 |
+
"learning_rate": 4.2345951920420006e-06,
|
325 |
+
"loss": 0.0695,
|
326 |
+
"step": 26500
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 3.73,
|
330 |
+
"learning_rate": 3.371096988118265e-06,
|
331 |
+
"loss": 0.0228,
|
332 |
+
"step": 27000
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 3.8,
|
336 |
+
"learning_rate": 2.507598784194529e-06,
|
337 |
+
"loss": 0.0257,
|
338 |
+
"step": 27500
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 3.87,
|
342 |
+
"learning_rate": 1.644100580270793e-06,
|
343 |
+
"loss": 0.0158,
|
344 |
+
"step": 28000
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 3.94,
|
348 |
+
"learning_rate": 7.806023763470573e-07,
|
349 |
+
"loss": 0.0432,
|
350 |
+
"step": 28500
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 4.0,
|
354 |
+
"step": 28952,
|
355 |
+
"total_flos": 9.075809388129869e+16,
|
356 |
+
"train_loss": 0.1776402507509504,
|
357 |
+
"train_runtime": 7042.0183,
|
358 |
+
"train_samples_per_second": 12.334,
|
359 |
+
"train_steps_per_second": 4.111
|
360 |
}
|
361 |
],
|
362 |
+
"max_steps": 28952,
|
363 |
+
"num_train_epochs": 4,
|
364 |
+
"total_flos": 9.075809388129869e+16,
|
365 |
"trial_name": null,
|
366 |
"trial_params": null
|
367 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc04f9294df23795653d167d6ac3debb3207bdd8002b4db84878c01887fcd2ef
|
3 |
+
size 3055
|