codestylist
commited on
Commit
·
4013376
1
Parent(s):
0dc10c8
Upload trainer_state.json
Browse files- trainer_state.json +340 -0
trainer_state.json
ADDED
@@ -0,0 +1,340 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9991488731821041,
|
5 |
+
"global_step": 27000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.02,
|
12 |
+
"learning_rate": 0.0019629944861784404,
|
13 |
+
"loss": 0.0147,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.04,
|
18 |
+
"learning_rate": 0.0019259889723568812,
|
19 |
+
"loss": 0.0187,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.06,
|
24 |
+
"learning_rate": 0.0018889834585353218,
|
25 |
+
"loss": 0.0201,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.07,
|
30 |
+
"learning_rate": 0.0018519779447137624,
|
31 |
+
"loss": 0.0176,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.09,
|
36 |
+
"learning_rate": 0.001814972430892203,
|
37 |
+
"loss": 0.0177,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.11,
|
42 |
+
"learning_rate": 0.0017779669170706436,
|
43 |
+
"loss": 0.0175,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.13,
|
48 |
+
"learning_rate": 0.0017409614032490842,
|
49 |
+
"loss": 0.0177,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.15,
|
54 |
+
"learning_rate": 0.0017039558894275247,
|
55 |
+
"loss": 0.0185,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.17,
|
60 |
+
"learning_rate": 0.0016669503756059653,
|
61 |
+
"loss": 0.0179,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.19,
|
66 |
+
"learning_rate": 0.001629944861784406,
|
67 |
+
"loss": 0.0188,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.2,
|
72 |
+
"learning_rate": 0.0015929393479628465,
|
73 |
+
"loss": 0.0181,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.22,
|
78 |
+
"learning_rate": 0.0015559338341412869,
|
79 |
+
"loss": 0.0192,
|
80 |
+
"step": 6000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.24,
|
84 |
+
"learning_rate": 0.0015189283203197277,
|
85 |
+
"loss": 0.0172,
|
86 |
+
"step": 6500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.26,
|
90 |
+
"learning_rate": 0.0014819228064981683,
|
91 |
+
"loss": 0.0153,
|
92 |
+
"step": 7000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.28,
|
96 |
+
"learning_rate": 0.0014449172926766088,
|
97 |
+
"loss": 0.0154,
|
98 |
+
"step": 7500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.3,
|
102 |
+
"learning_rate": 0.0014079117788550494,
|
103 |
+
"loss": 0.0163,
|
104 |
+
"step": 8000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.31,
|
108 |
+
"learning_rate": 0.00137090626503349,
|
109 |
+
"loss": 0.0161,
|
110 |
+
"step": 8500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.33,
|
114 |
+
"learning_rate": 0.0013339007512119306,
|
115 |
+
"loss": 0.0149,
|
116 |
+
"step": 9000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.35,
|
120 |
+
"learning_rate": 0.0012968952373903712,
|
121 |
+
"loss": 0.016,
|
122 |
+
"step": 9500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.37,
|
126 |
+
"learning_rate": 0.0012598897235688118,
|
127 |
+
"loss": 0.015,
|
128 |
+
"step": 10000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.39,
|
132 |
+
"learning_rate": 0.0012228842097472524,
|
133 |
+
"loss": 0.0145,
|
134 |
+
"step": 10500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.41,
|
138 |
+
"learning_rate": 0.001185878695925693,
|
139 |
+
"loss": 0.0145,
|
140 |
+
"step": 11000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.43,
|
144 |
+
"learning_rate": 0.0011488731821041335,
|
145 |
+
"loss": 0.0143,
|
146 |
+
"step": 11500
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.44,
|
150 |
+
"learning_rate": 0.0011118676682825741,
|
151 |
+
"loss": 0.0136,
|
152 |
+
"step": 12000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.46,
|
156 |
+
"learning_rate": 0.0010748621544610147,
|
157 |
+
"loss": 0.0148,
|
158 |
+
"step": 12500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.48,
|
162 |
+
"learning_rate": 0.0010378566406394553,
|
163 |
+
"loss": 0.0141,
|
164 |
+
"step": 13000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.5,
|
168 |
+
"learning_rate": 0.001000851126817896,
|
169 |
+
"loss": 0.0132,
|
170 |
+
"step": 13500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.52,
|
174 |
+
"learning_rate": 0.0009638456129963365,
|
175 |
+
"loss": 0.0128,
|
176 |
+
"step": 14000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.54,
|
180 |
+
"learning_rate": 0.0009268400991747771,
|
181 |
+
"loss": 0.0128,
|
182 |
+
"step": 14500
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.56,
|
186 |
+
"learning_rate": 0.0008898345853532175,
|
187 |
+
"loss": 0.0128,
|
188 |
+
"step": 15000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.57,
|
192 |
+
"learning_rate": 0.0008528290715316582,
|
193 |
+
"loss": 0.0123,
|
194 |
+
"step": 15500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.59,
|
198 |
+
"learning_rate": 0.0008158235577100988,
|
199 |
+
"loss": 0.0119,
|
200 |
+
"step": 16000
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.61,
|
204 |
+
"learning_rate": 0.0007788180438885394,
|
205 |
+
"loss": 0.0124,
|
206 |
+
"step": 16500
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.63,
|
210 |
+
"learning_rate": 0.00074181253006698,
|
211 |
+
"loss": 0.0116,
|
212 |
+
"step": 17000
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.65,
|
216 |
+
"learning_rate": 0.0007048070162454206,
|
217 |
+
"loss": 0.0118,
|
218 |
+
"step": 17500
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.67,
|
222 |
+
"learning_rate": 0.0006678015024238612,
|
223 |
+
"loss": 0.0114,
|
224 |
+
"step": 18000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.68,
|
228 |
+
"learning_rate": 0.0006307959886023018,
|
229 |
+
"loss": 0.0114,
|
230 |
+
"step": 18500
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.7,
|
234 |
+
"learning_rate": 0.0005937904747807424,
|
235 |
+
"loss": 0.0111,
|
236 |
+
"step": 19000
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.72,
|
240 |
+
"learning_rate": 0.0005567849609591829,
|
241 |
+
"loss": 0.0105,
|
242 |
+
"step": 19500
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.74,
|
246 |
+
"learning_rate": 0.0005197794471376235,
|
247 |
+
"loss": 0.0107,
|
248 |
+
"step": 20000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.76,
|
252 |
+
"learning_rate": 0.0004827739333160641,
|
253 |
+
"loss": 0.0102,
|
254 |
+
"step": 20500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.78,
|
258 |
+
"learning_rate": 0.0004457684194945047,
|
259 |
+
"loss": 0.0102,
|
260 |
+
"step": 21000
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 0.8,
|
264 |
+
"learning_rate": 0.0004087629056729453,
|
265 |
+
"loss": 0.0099,
|
266 |
+
"step": 21500
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 0.81,
|
270 |
+
"learning_rate": 0.0003717573918513859,
|
271 |
+
"loss": 0.0101,
|
272 |
+
"step": 22000
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 0.83,
|
276 |
+
"learning_rate": 0.0003347518780298264,
|
277 |
+
"loss": 0.0095,
|
278 |
+
"step": 22500
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 0.85,
|
282 |
+
"learning_rate": 0.00029774636420826705,
|
283 |
+
"loss": 0.0097,
|
284 |
+
"step": 23000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.87,
|
288 |
+
"learning_rate": 0.00026074085038670764,
|
289 |
+
"loss": 0.0094,
|
290 |
+
"step": 23500
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.89,
|
294 |
+
"learning_rate": 0.00022373533656514823,
|
295 |
+
"loss": 0.0094,
|
296 |
+
"step": 24000
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.91,
|
300 |
+
"learning_rate": 0.0001867298227435888,
|
301 |
+
"loss": 0.0095,
|
302 |
+
"step": 24500
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 0.93,
|
306 |
+
"learning_rate": 0.00014972430892202937,
|
307 |
+
"loss": 0.0089,
|
308 |
+
"step": 25000
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 0.94,
|
312 |
+
"learning_rate": 0.00011271879510046997,
|
313 |
+
"loss": 0.0087,
|
314 |
+
"step": 25500
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 0.96,
|
318 |
+
"learning_rate": 7.571328127891056e-05,
|
319 |
+
"loss": 0.009,
|
320 |
+
"step": 26000
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 0.98,
|
324 |
+
"learning_rate": 3.870776745735115e-05,
|
325 |
+
"loss": 0.0088,
|
326 |
+
"step": 26500
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 1.0,
|
330 |
+
"learning_rate": 1.702253635791733e-06,
|
331 |
+
"loss": 0.0088,
|
332 |
+
"step": 27000
|
333 |
+
}
|
334 |
+
],
|
335 |
+
"max_steps": 27023,
|
336 |
+
"num_train_epochs": 1,
|
337 |
+
"total_flos": 8.7701487353856e+16,
|
338 |
+
"trial_name": null,
|
339 |
+
"trial_params": null
|
340 |
+
}
|