JunHyung1206
commited on
Commit
•
05a2a04
1
Parent(s):
97d162b
End of training
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- train_results.txt +6 -0
- trainer_state.json +437 -0
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"train_loss": 2.08123623193931,
|
4 |
+
"train_runtime": 3339.4615,
|
5 |
+
"train_samples": 42367,
|
6 |
+
"train_samples_per_second": 63.434,
|
7 |
+
"train_steps_per_second": 1.982
|
8 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"train_loss": 2.08123623193931,
|
4 |
+
"train_runtime": 3339.4615,
|
5 |
+
"train_samples": 42367,
|
6 |
+
"train_samples_per_second": 63.434,
|
7 |
+
"train_steps_per_second": 1.982
|
8 |
+
}
|
train_results.txt
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
epoch = 5.0
|
2 |
+
train_loss = 2.08123623193931
|
3 |
+
train_runtime = 3339.4615
|
4 |
+
train_samples = 42367
|
5 |
+
train_samples_per_second = 63.434
|
6 |
+
train_steps_per_second = 1.982
|
trainer_state.json
ADDED
@@ -0,0 +1,437 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0,
|
5 |
+
"global_step": 6620,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.08,
|
12 |
+
"learning_rate": 4.531722054380664e-06,
|
13 |
+
"loss": 6.5892,
|
14 |
+
"step": 100
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.15,
|
18 |
+
"learning_rate": 9.063444108761328e-06,
|
19 |
+
"loss": 3.0428,
|
20 |
+
"step": 200
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.23,
|
24 |
+
"learning_rate": 1.3595166163141995e-05,
|
25 |
+
"loss": 2.7571,
|
26 |
+
"step": 300
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.3,
|
30 |
+
"learning_rate": 1.8126888217522657e-05,
|
31 |
+
"loss": 2.6077,
|
32 |
+
"step": 400
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.38,
|
36 |
+
"learning_rate": 2.2658610271903327e-05,
|
37 |
+
"loss": 2.499,
|
38 |
+
"step": 500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.45,
|
42 |
+
"learning_rate": 2.719033232628399e-05,
|
43 |
+
"loss": 2.4479,
|
44 |
+
"step": 600
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.53,
|
48 |
+
"learning_rate": 2.9808660624370596e-05,
|
49 |
+
"loss": 2.4174,
|
50 |
+
"step": 700
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.6,
|
54 |
+
"learning_rate": 2.9305135951661632e-05,
|
55 |
+
"loss": 2.3734,
|
56 |
+
"step": 800
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.68,
|
60 |
+
"learning_rate": 2.8801611278952668e-05,
|
61 |
+
"loss": 2.3389,
|
62 |
+
"step": 900
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.76,
|
66 |
+
"learning_rate": 2.8298086606243708e-05,
|
67 |
+
"loss": 2.3199,
|
68 |
+
"step": 1000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.83,
|
72 |
+
"learning_rate": 2.7794561933534743e-05,
|
73 |
+
"loss": 2.3088,
|
74 |
+
"step": 1100
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.91,
|
78 |
+
"learning_rate": 2.729103726082578e-05,
|
79 |
+
"loss": 2.2918,
|
80 |
+
"step": 1200
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.98,
|
84 |
+
"learning_rate": 2.678751258811682e-05,
|
85 |
+
"loss": 2.2301,
|
86 |
+
"step": 1300
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 1.06,
|
90 |
+
"learning_rate": 2.6283987915407858e-05,
|
91 |
+
"loss": 2.1591,
|
92 |
+
"step": 1400
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 1.13,
|
96 |
+
"learning_rate": 2.5780463242698894e-05,
|
97 |
+
"loss": 2.1292,
|
98 |
+
"step": 1500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 1.21,
|
102 |
+
"learning_rate": 2.527693856998993e-05,
|
103 |
+
"loss": 2.1182,
|
104 |
+
"step": 1600
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 1.28,
|
108 |
+
"learning_rate": 2.477341389728097e-05,
|
109 |
+
"loss": 2.1251,
|
110 |
+
"step": 1700
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 1.36,
|
114 |
+
"learning_rate": 2.4269889224572005e-05,
|
115 |
+
"loss": 2.1086,
|
116 |
+
"step": 1800
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 1.44,
|
120 |
+
"learning_rate": 2.376636455186304e-05,
|
121 |
+
"loss": 2.1133,
|
122 |
+
"step": 1900
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 1.51,
|
126 |
+
"learning_rate": 2.3262839879154077e-05,
|
127 |
+
"loss": 2.1264,
|
128 |
+
"step": 2000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.59,
|
132 |
+
"learning_rate": 2.2759315206445116e-05,
|
133 |
+
"loss": 2.0956,
|
134 |
+
"step": 2100
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 1.66,
|
138 |
+
"learning_rate": 2.2255790533736152e-05,
|
139 |
+
"loss": 2.101,
|
140 |
+
"step": 2200
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 1.74,
|
144 |
+
"learning_rate": 2.175226586102719e-05,
|
145 |
+
"loss": 2.0663,
|
146 |
+
"step": 2300
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 1.81,
|
150 |
+
"learning_rate": 2.124874118831823e-05,
|
151 |
+
"loss": 2.0977,
|
152 |
+
"step": 2400
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 1.89,
|
156 |
+
"learning_rate": 2.0745216515609266e-05,
|
157 |
+
"loss": 2.0523,
|
158 |
+
"step": 2500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 1.96,
|
162 |
+
"learning_rate": 2.0241691842900302e-05,
|
163 |
+
"loss": 2.0876,
|
164 |
+
"step": 2600
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 2.04,
|
168 |
+
"learning_rate": 1.973816717019134e-05,
|
169 |
+
"loss": 2.0181,
|
170 |
+
"step": 2700
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 2.11,
|
174 |
+
"learning_rate": 1.9234642497482378e-05,
|
175 |
+
"loss": 1.9481,
|
176 |
+
"step": 2800
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 2.19,
|
180 |
+
"learning_rate": 1.8731117824773413e-05,
|
181 |
+
"loss": 1.9403,
|
182 |
+
"step": 2900
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 2.27,
|
186 |
+
"learning_rate": 1.822759315206445e-05,
|
187 |
+
"loss": 1.9469,
|
188 |
+
"step": 3000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 2.34,
|
192 |
+
"learning_rate": 1.772406847935549e-05,
|
193 |
+
"loss": 1.9364,
|
194 |
+
"step": 3100
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 2.42,
|
198 |
+
"learning_rate": 1.7220543806646525e-05,
|
199 |
+
"loss": 1.9218,
|
200 |
+
"step": 3200
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 2.49,
|
204 |
+
"learning_rate": 1.6717019133937564e-05,
|
205 |
+
"loss": 1.9458,
|
206 |
+
"step": 3300
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 2.57,
|
210 |
+
"learning_rate": 1.6213494461228603e-05,
|
211 |
+
"loss": 1.9348,
|
212 |
+
"step": 3400
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 2.64,
|
216 |
+
"learning_rate": 1.570996978851964e-05,
|
217 |
+
"loss": 1.9478,
|
218 |
+
"step": 3500
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 2.72,
|
222 |
+
"learning_rate": 1.5206445115810675e-05,
|
223 |
+
"loss": 1.9566,
|
224 |
+
"step": 3600
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 2.79,
|
228 |
+
"learning_rate": 1.4702920443101713e-05,
|
229 |
+
"loss": 1.9388,
|
230 |
+
"step": 3700
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 2.87,
|
234 |
+
"learning_rate": 1.419939577039275e-05,
|
235 |
+
"loss": 1.9387,
|
236 |
+
"step": 3800
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 2.95,
|
240 |
+
"learning_rate": 1.3695871097683786e-05,
|
241 |
+
"loss": 1.9306,
|
242 |
+
"step": 3900
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 3.02,
|
246 |
+
"learning_rate": 1.3192346424974824e-05,
|
247 |
+
"loss": 1.8913,
|
248 |
+
"step": 4000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 3.1,
|
252 |
+
"learning_rate": 1.2688821752265861e-05,
|
253 |
+
"loss": 1.8345,
|
254 |
+
"step": 4100
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 3.17,
|
258 |
+
"learning_rate": 1.2185297079556899e-05,
|
259 |
+
"loss": 1.8017,
|
260 |
+
"step": 4200
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 3.25,
|
264 |
+
"learning_rate": 1.1681772406847936e-05,
|
265 |
+
"loss": 1.8287,
|
266 |
+
"step": 4300
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 3.32,
|
270 |
+
"learning_rate": 1.1178247734138972e-05,
|
271 |
+
"loss": 1.8169,
|
272 |
+
"step": 4400
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 3.4,
|
276 |
+
"learning_rate": 1.067472306143001e-05,
|
277 |
+
"loss": 1.8346,
|
278 |
+
"step": 4500
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 3.47,
|
282 |
+
"learning_rate": 1.0171198388721048e-05,
|
283 |
+
"loss": 1.8293,
|
284 |
+
"step": 4600
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 3.55,
|
288 |
+
"learning_rate": 9.667673716012085e-06,
|
289 |
+
"loss": 1.8318,
|
290 |
+
"step": 4700
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 3.63,
|
294 |
+
"learning_rate": 9.164149043303123e-06,
|
295 |
+
"loss": 1.8386,
|
296 |
+
"step": 4800
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 3.7,
|
300 |
+
"learning_rate": 8.660624370594159e-06,
|
301 |
+
"loss": 1.8319,
|
302 |
+
"step": 4900
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 3.78,
|
306 |
+
"learning_rate": 8.157099697885196e-06,
|
307 |
+
"loss": 1.8239,
|
308 |
+
"step": 5000
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 3.78,
|
312 |
+
"eval_bleu1": 29.625,
|
313 |
+
"eval_bleu2": 17.4903,
|
314 |
+
"eval_bleu3": 10.6018,
|
315 |
+
"eval_bleu4": 6.0498,
|
316 |
+
"eval_gen_len": 50.697,
|
317 |
+
"eval_loss": 2.5957541465759277,
|
318 |
+
"eval_rouge1": 35.6403,
|
319 |
+
"eval_rouge2": 13.1314,
|
320 |
+
"eval_rougeL": 23.8946,
|
321 |
+
"eval_runtime": 71.4256,
|
322 |
+
"eval_samples_per_second": 6.006,
|
323 |
+
"eval_steps_per_second": 0.056,
|
324 |
+
"step": 5000
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 3.85,
|
328 |
+
"learning_rate": 7.653575025176234e-06,
|
329 |
+
"loss": 1.8312,
|
330 |
+
"step": 5100
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"epoch": 3.93,
|
334 |
+
"learning_rate": 7.1500503524672715e-06,
|
335 |
+
"loss": 1.8377,
|
336 |
+
"step": 5200
|
337 |
+
},
|
338 |
+
{
|
339 |
+
"epoch": 4.0,
|
340 |
+
"learning_rate": 6.646525679758308e-06,
|
341 |
+
"loss": 1.8329,
|
342 |
+
"step": 5300
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 4.08,
|
346 |
+
"learning_rate": 6.143001007049345e-06,
|
347 |
+
"loss": 1.7546,
|
348 |
+
"step": 5400
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"epoch": 4.15,
|
352 |
+
"learning_rate": 5.6394763343403835e-06,
|
353 |
+
"loss": 1.7407,
|
354 |
+
"step": 5500
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 4.23,
|
358 |
+
"learning_rate": 5.13595166163142e-06,
|
359 |
+
"loss": 1.756,
|
360 |
+
"step": 5600
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 4.31,
|
364 |
+
"learning_rate": 4.632426988922458e-06,
|
365 |
+
"loss": 1.762,
|
366 |
+
"step": 5700
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 4.38,
|
370 |
+
"learning_rate": 4.1289023162134946e-06,
|
371 |
+
"loss": 1.7451,
|
372 |
+
"step": 5800
|
373 |
+
},
|
374 |
+
{
|
375 |
+
"epoch": 4.46,
|
376 |
+
"learning_rate": 3.625377643504532e-06,
|
377 |
+
"loss": 1.751,
|
378 |
+
"step": 5900
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"epoch": 4.53,
|
382 |
+
"learning_rate": 3.121852970795569e-06,
|
383 |
+
"loss": 1.765,
|
384 |
+
"step": 6000
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 4.61,
|
388 |
+
"learning_rate": 2.618328298086606e-06,
|
389 |
+
"loss": 1.7543,
|
390 |
+
"step": 6100
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 4.68,
|
394 |
+
"learning_rate": 2.1148036253776437e-06,
|
395 |
+
"loss": 1.7748,
|
396 |
+
"step": 6200
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 4.76,
|
400 |
+
"learning_rate": 1.6112789526686809e-06,
|
401 |
+
"loss": 1.7505,
|
402 |
+
"step": 6300
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 4.83,
|
406 |
+
"learning_rate": 1.107754279959718e-06,
|
407 |
+
"loss": 1.7806,
|
408 |
+
"step": 6400
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 4.91,
|
412 |
+
"learning_rate": 6.042296072507553e-07,
|
413 |
+
"loss": 1.7503,
|
414 |
+
"step": 6500
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 4.98,
|
418 |
+
"learning_rate": 1.0070493454179255e-07,
|
419 |
+
"loss": 1.7687,
|
420 |
+
"step": 6600
|
421 |
+
},
|
422 |
+
{
|
423 |
+
"epoch": 5.0,
|
424 |
+
"step": 6620,
|
425 |
+
"total_flos": 4.347230642786304e+16,
|
426 |
+
"train_loss": 2.08123623193931,
|
427 |
+
"train_runtime": 3339.4615,
|
428 |
+
"train_samples_per_second": 63.434,
|
429 |
+
"train_steps_per_second": 1.982
|
430 |
+
}
|
431 |
+
],
|
432 |
+
"max_steps": 6620,
|
433 |
+
"num_train_epochs": 5,
|
434 |
+
"total_flos": 4.347230642786304e+16,
|
435 |
+
"trial_name": null,
|
436 |
+
"trial_params": null
|
437 |
+
}
|