Jeremiah Zhou
commited on
Commit
•
9f2f7be
1
Parent(s):
54d18a6
End of training
Browse files- all_results.json +21 -0
- eval_results.json +16 -0
- runs/Jun21_16-23-38_mewtwo/events.out.tfevents.1655842915.mewtwo +3 -0
- train_results.json +8 -0
- trainer_state.json +490 -0
all_results.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"epoch_mm": 3.0,
|
4 |
+
"eval_accuracy": 0.8468670402445236,
|
5 |
+
"eval_accuracy_mm": 0.8500813669650122,
|
6 |
+
"eval_loss": 0.42516547441482544,
|
7 |
+
"eval_loss_mm": 0.40559157729148865,
|
8 |
+
"eval_runtime": 43.5968,
|
9 |
+
"eval_runtime_mm": 46.1873,
|
10 |
+
"eval_samples": 9815,
|
11 |
+
"eval_samples_mm": 9832,
|
12 |
+
"eval_samples_per_second": 225.131,
|
13 |
+
"eval_samples_per_second_mm": 212.872,
|
14 |
+
"eval_steps_per_second": 28.144,
|
15 |
+
"eval_steps_per_second_mm": 26.609,
|
16 |
+
"train_loss": 0.36166443611320753,
|
17 |
+
"train_runtime": 13822.4675,
|
18 |
+
"train_samples": 392702,
|
19 |
+
"train_samples_per_second": 85.231,
|
20 |
+
"train_steps_per_second": 2.663
|
21 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"epoch_mm": 3.0,
|
4 |
+
"eval_accuracy": 0.8468670402445236,
|
5 |
+
"eval_accuracy_mm": 0.8500813669650122,
|
6 |
+
"eval_loss": 0.42516547441482544,
|
7 |
+
"eval_loss_mm": 0.40559157729148865,
|
8 |
+
"eval_runtime": 43.5968,
|
9 |
+
"eval_runtime_mm": 46.1873,
|
10 |
+
"eval_samples": 9815,
|
11 |
+
"eval_samples_mm": 9832,
|
12 |
+
"eval_samples_per_second": 225.131,
|
13 |
+
"eval_samples_per_second_mm": 212.872,
|
14 |
+
"eval_steps_per_second": 28.144,
|
15 |
+
"eval_steps_per_second_mm": 26.609
|
16 |
+
}
|
runs/Jun21_16-23-38_mewtwo/events.out.tfevents.1655842915.mewtwo
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83f24bcab71b499ddcfdbb65d3058ef5b2177e2e0e7ec466d77dd6e0aaba3e3f
|
3 |
+
size 369
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_loss": 0.36166443611320753,
|
4 |
+
"train_runtime": 13822.4675,
|
5 |
+
"train_samples": 392702,
|
6 |
+
"train_samples_per_second": 85.231,
|
7 |
+
"train_steps_per_second": 2.663
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,490 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8468670402445236,
|
3 |
+
"best_model_checkpoint": "./fine-tune/bert-base-uncased/mnli/checkpoint-24544",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 36816,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.04,
|
12 |
+
"learning_rate": 1.9728378965667103e-05,
|
13 |
+
"loss": 0.8292,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.08,
|
18 |
+
"learning_rate": 1.9456757931334205e-05,
|
19 |
+
"loss": 0.6558,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.12,
|
24 |
+
"learning_rate": 1.9185136897001307e-05,
|
25 |
+
"loss": 0.6054,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.16,
|
30 |
+
"learning_rate": 1.8913515862668405e-05,
|
31 |
+
"loss": 0.5619,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.2,
|
36 |
+
"learning_rate": 1.8641894828335507e-05,
|
37 |
+
"loss": 0.5573,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.24,
|
42 |
+
"learning_rate": 1.837027379400261e-05,
|
43 |
+
"loss": 0.5536,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.29,
|
48 |
+
"learning_rate": 1.809865275966971e-05,
|
49 |
+
"loss": 0.5338,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.33,
|
54 |
+
"learning_rate": 1.7827031725336812e-05,
|
55 |
+
"loss": 0.5171,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.37,
|
60 |
+
"learning_rate": 1.7555410691003914e-05,
|
61 |
+
"loss": 0.5018,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.41,
|
66 |
+
"learning_rate": 1.7283789656671015e-05,
|
67 |
+
"loss": 0.5067,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.45,
|
72 |
+
"learning_rate": 1.7012168622338114e-05,
|
73 |
+
"loss": 0.4993,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.49,
|
78 |
+
"learning_rate": 1.6740547588005215e-05,
|
79 |
+
"loss": 0.4905,
|
80 |
+
"step": 6000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.53,
|
84 |
+
"learning_rate": 1.6468926553672317e-05,
|
85 |
+
"loss": 0.4898,
|
86 |
+
"step": 6500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.57,
|
90 |
+
"learning_rate": 1.619730551933942e-05,
|
91 |
+
"loss": 0.4841,
|
92 |
+
"step": 7000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.61,
|
96 |
+
"learning_rate": 1.592568448500652e-05,
|
97 |
+
"loss": 0.4821,
|
98 |
+
"step": 7500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.65,
|
102 |
+
"learning_rate": 1.5654063450673622e-05,
|
103 |
+
"loss": 0.4732,
|
104 |
+
"step": 8000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.69,
|
108 |
+
"learning_rate": 1.5382442416340724e-05,
|
109 |
+
"loss": 0.4688,
|
110 |
+
"step": 8500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.73,
|
114 |
+
"learning_rate": 1.5110821382007822e-05,
|
115 |
+
"loss": 0.4662,
|
116 |
+
"step": 9000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.77,
|
120 |
+
"learning_rate": 1.4839200347674924e-05,
|
121 |
+
"loss": 0.4646,
|
122 |
+
"step": 9500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.81,
|
126 |
+
"learning_rate": 1.4567579313342026e-05,
|
127 |
+
"loss": 0.4537,
|
128 |
+
"step": 10000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.86,
|
132 |
+
"learning_rate": 1.4295958279009128e-05,
|
133 |
+
"loss": 0.4627,
|
134 |
+
"step": 10500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.9,
|
138 |
+
"learning_rate": 1.402433724467623e-05,
|
139 |
+
"loss": 0.4577,
|
140 |
+
"step": 11000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.94,
|
144 |
+
"learning_rate": 1.3752716210343331e-05,
|
145 |
+
"loss": 0.4552,
|
146 |
+
"step": 11500
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.98,
|
150 |
+
"learning_rate": 1.3481095176010431e-05,
|
151 |
+
"loss": 0.4526,
|
152 |
+
"step": 12000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 1.0,
|
156 |
+
"eval_accuracy": 0.8388181355068772,
|
157 |
+
"eval_loss": 0.4244438111782074,
|
158 |
+
"eval_runtime": 45.7305,
|
159 |
+
"eval_samples_per_second": 214.627,
|
160 |
+
"eval_steps_per_second": 26.831,
|
161 |
+
"step": 12272
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 1.02,
|
165 |
+
"learning_rate": 1.3209474141677531e-05,
|
166 |
+
"loss": 0.4053,
|
167 |
+
"step": 12500
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 1.06,
|
171 |
+
"learning_rate": 1.2937853107344633e-05,
|
172 |
+
"loss": 0.3513,
|
173 |
+
"step": 13000
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 1.1,
|
177 |
+
"learning_rate": 1.2666232073011735e-05,
|
178 |
+
"loss": 0.3396,
|
179 |
+
"step": 13500
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 1.14,
|
183 |
+
"learning_rate": 1.2394611038678836e-05,
|
184 |
+
"loss": 0.3435,
|
185 |
+
"step": 14000
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 1.18,
|
189 |
+
"learning_rate": 1.2122990004345938e-05,
|
190 |
+
"loss": 0.3269,
|
191 |
+
"step": 14500
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 1.22,
|
195 |
+
"learning_rate": 1.185136897001304e-05,
|
196 |
+
"loss": 0.3443,
|
197 |
+
"step": 15000
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 1.26,
|
201 |
+
"learning_rate": 1.157974793568014e-05,
|
202 |
+
"loss": 0.3308,
|
203 |
+
"step": 15500
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 1.3,
|
207 |
+
"learning_rate": 1.130812690134724e-05,
|
208 |
+
"loss": 0.3367,
|
209 |
+
"step": 16000
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 1.34,
|
213 |
+
"learning_rate": 1.1036505867014341e-05,
|
214 |
+
"loss": 0.3431,
|
215 |
+
"step": 16500
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 1.39,
|
219 |
+
"learning_rate": 1.0764884832681443e-05,
|
220 |
+
"loss": 0.3446,
|
221 |
+
"step": 17000
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 1.43,
|
225 |
+
"learning_rate": 1.0493263798348545e-05,
|
226 |
+
"loss": 0.3328,
|
227 |
+
"step": 17500
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 1.47,
|
231 |
+
"learning_rate": 1.0221642764015647e-05,
|
232 |
+
"loss": 0.3335,
|
233 |
+
"step": 18000
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 1.51,
|
237 |
+
"learning_rate": 9.950021729682747e-06,
|
238 |
+
"loss": 0.328,
|
239 |
+
"step": 18500
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 1.55,
|
243 |
+
"learning_rate": 9.678400695349848e-06,
|
244 |
+
"loss": 0.3367,
|
245 |
+
"step": 19000
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"epoch": 1.59,
|
249 |
+
"learning_rate": 9.40677966101695e-06,
|
250 |
+
"loss": 0.3386,
|
251 |
+
"step": 19500
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 1.63,
|
255 |
+
"learning_rate": 9.13515862668405e-06,
|
256 |
+
"loss": 0.3418,
|
257 |
+
"step": 20000
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 1.67,
|
261 |
+
"learning_rate": 8.863537592351152e-06,
|
262 |
+
"loss": 0.3388,
|
263 |
+
"step": 20500
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 1.71,
|
267 |
+
"learning_rate": 8.591916558018254e-06,
|
268 |
+
"loss": 0.3359,
|
269 |
+
"step": 21000
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 1.75,
|
273 |
+
"learning_rate": 8.320295523685355e-06,
|
274 |
+
"loss": 0.3405,
|
275 |
+
"step": 21500
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 1.79,
|
279 |
+
"learning_rate": 8.048674489352455e-06,
|
280 |
+
"loss": 0.335,
|
281 |
+
"step": 22000
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 1.83,
|
285 |
+
"learning_rate": 7.777053455019557e-06,
|
286 |
+
"loss": 0.3356,
|
287 |
+
"step": 22500
|
288 |
+
},
|
289 |
+
{
|
290 |
+
"epoch": 1.87,
|
291 |
+
"learning_rate": 7.505432420686659e-06,
|
292 |
+
"loss": 0.3453,
|
293 |
+
"step": 23000
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 1.91,
|
297 |
+
"learning_rate": 7.23381138635376e-06,
|
298 |
+
"loss": 0.3237,
|
299 |
+
"step": 23500
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 1.96,
|
303 |
+
"learning_rate": 6.962190352020861e-06,
|
304 |
+
"loss": 0.3299,
|
305 |
+
"step": 24000
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 2.0,
|
309 |
+
"learning_rate": 6.690569317687963e-06,
|
310 |
+
"loss": 0.3344,
|
311 |
+
"step": 24500
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 2.0,
|
315 |
+
"eval_accuracy": 0.8468670402445236,
|
316 |
+
"eval_loss": 0.42516547441482544,
|
317 |
+
"eval_runtime": 45.6234,
|
318 |
+
"eval_samples_per_second": 215.131,
|
319 |
+
"eval_steps_per_second": 26.894,
|
320 |
+
"step": 24544
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 2.04,
|
324 |
+
"learning_rate": 6.418948283355063e-06,
|
325 |
+
"loss": 0.2376,
|
326 |
+
"step": 25000
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 2.08,
|
330 |
+
"learning_rate": 6.147327249022165e-06,
|
331 |
+
"loss": 0.2293,
|
332 |
+
"step": 25500
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 2.12,
|
336 |
+
"learning_rate": 5.8757062146892665e-06,
|
337 |
+
"loss": 0.2354,
|
338 |
+
"step": 26000
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 2.16,
|
342 |
+
"learning_rate": 5.6040851803563665e-06,
|
343 |
+
"loss": 0.232,
|
344 |
+
"step": 26500
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 2.2,
|
348 |
+
"learning_rate": 5.332464146023468e-06,
|
349 |
+
"loss": 0.2385,
|
350 |
+
"step": 27000
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 2.24,
|
354 |
+
"learning_rate": 5.06084311169057e-06,
|
355 |
+
"loss": 0.2289,
|
356 |
+
"step": 27500
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 2.28,
|
360 |
+
"learning_rate": 4.789222077357671e-06,
|
361 |
+
"loss": 0.2395,
|
362 |
+
"step": 28000
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 2.32,
|
366 |
+
"learning_rate": 4.5176010430247726e-06,
|
367 |
+
"loss": 0.2259,
|
368 |
+
"step": 28500
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 2.36,
|
372 |
+
"learning_rate": 4.2459800086918734e-06,
|
373 |
+
"loss": 0.2372,
|
374 |
+
"step": 29000
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 2.4,
|
378 |
+
"learning_rate": 3.974358974358974e-06,
|
379 |
+
"loss": 0.238,
|
380 |
+
"step": 29500
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 2.44,
|
384 |
+
"learning_rate": 3.702737940026076e-06,
|
385 |
+
"loss": 0.2312,
|
386 |
+
"step": 30000
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 2.49,
|
390 |
+
"learning_rate": 3.431116905693177e-06,
|
391 |
+
"loss": 0.242,
|
392 |
+
"step": 30500
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 2.53,
|
396 |
+
"learning_rate": 3.1594958713602786e-06,
|
397 |
+
"loss": 0.228,
|
398 |
+
"step": 31000
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 2.57,
|
402 |
+
"learning_rate": 2.8878748370273795e-06,
|
403 |
+
"loss": 0.2323,
|
404 |
+
"step": 31500
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 2.61,
|
408 |
+
"learning_rate": 2.6162538026944812e-06,
|
409 |
+
"loss": 0.2315,
|
410 |
+
"step": 32000
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 2.65,
|
414 |
+
"learning_rate": 2.344632768361582e-06,
|
415 |
+
"loss": 0.2226,
|
416 |
+
"step": 32500
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 2.69,
|
420 |
+
"learning_rate": 2.0730117340286834e-06,
|
421 |
+
"loss": 0.2307,
|
422 |
+
"step": 33000
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 2.73,
|
426 |
+
"learning_rate": 1.8013906996957845e-06,
|
427 |
+
"loss": 0.23,
|
428 |
+
"step": 33500
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 2.77,
|
432 |
+
"learning_rate": 1.5297696653628858e-06,
|
433 |
+
"loss": 0.2299,
|
434 |
+
"step": 34000
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 2.81,
|
438 |
+
"learning_rate": 1.258148631029987e-06,
|
439 |
+
"loss": 0.2365,
|
440 |
+
"step": 34500
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 2.85,
|
444 |
+
"learning_rate": 9.865275966970884e-07,
|
445 |
+
"loss": 0.2229,
|
446 |
+
"step": 35000
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 2.89,
|
450 |
+
"learning_rate": 7.149065623641896e-07,
|
451 |
+
"loss": 0.2276,
|
452 |
+
"step": 35500
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 2.93,
|
456 |
+
"learning_rate": 4.432855280312908e-07,
|
457 |
+
"loss": 0.2293,
|
458 |
+
"step": 36000
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 2.97,
|
462 |
+
"learning_rate": 1.7166449369839202e-07,
|
463 |
+
"loss": 0.2307,
|
464 |
+
"step": 36500
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 3.0,
|
468 |
+
"eval_accuracy": 0.8445236882322975,
|
469 |
+
"eval_loss": 0.49744442105293274,
|
470 |
+
"eval_runtime": 45.9152,
|
471 |
+
"eval_samples_per_second": 213.764,
|
472 |
+
"eval_steps_per_second": 26.723,
|
473 |
+
"step": 36816
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 3.0,
|
477 |
+
"step": 36816,
|
478 |
+
"total_flos": 7.74938740264658e+16,
|
479 |
+
"train_loss": 0.36166443611320753,
|
480 |
+
"train_runtime": 13822.4675,
|
481 |
+
"train_samples_per_second": 85.231,
|
482 |
+
"train_steps_per_second": 2.663
|
483 |
+
}
|
484 |
+
],
|
485 |
+
"max_steps": 36816,
|
486 |
+
"num_train_epochs": 3,
|
487 |
+
"total_flos": 7.74938740264658e+16,
|
488 |
+
"trial_name": null,
|
489 |
+
"trial_params": null
|
490 |
+
}
|