Charlie911
commited on
Commit
•
f023eda
1
Parent(s):
4246813
Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +319 -0
trainer_state.json
ADDED
@@ -0,0 +1,319 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5561735261401557,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.01,
|
13 |
+
"learning_rate": 4.944382647385984e-05,
|
14 |
+
"loss": 2.044,
|
15 |
+
"step": 10
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.02,
|
19 |
+
"learning_rate": 4.888765294771969e-05,
|
20 |
+
"loss": 1.9144,
|
21 |
+
"step": 20
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.03,
|
25 |
+
"learning_rate": 4.833147942157953e-05,
|
26 |
+
"loss": 1.8029,
|
27 |
+
"step": 30
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.04,
|
31 |
+
"learning_rate": 4.777530589543938e-05,
|
32 |
+
"loss": 1.6849,
|
33 |
+
"step": 40
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.06,
|
37 |
+
"learning_rate": 4.721913236929923e-05,
|
38 |
+
"loss": 1.6895,
|
39 |
+
"step": 50
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.07,
|
43 |
+
"learning_rate": 4.671857619577308e-05,
|
44 |
+
"loss": 1.7024,
|
45 |
+
"step": 60
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.08,
|
49 |
+
"learning_rate": 4.6162402669632924e-05,
|
50 |
+
"loss": 1.6251,
|
51 |
+
"step": 70
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.09,
|
55 |
+
"learning_rate": 4.560622914349277e-05,
|
56 |
+
"loss": 1.5079,
|
57 |
+
"step": 80
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.1,
|
61 |
+
"learning_rate": 4.505005561735261e-05,
|
62 |
+
"loss": 1.5368,
|
63 |
+
"step": 90
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.11,
|
67 |
+
"learning_rate": 4.449388209121246e-05,
|
68 |
+
"loss": 1.3431,
|
69 |
+
"step": 100
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.12,
|
73 |
+
"learning_rate": 4.393770856507231e-05,
|
74 |
+
"loss": 1.4992,
|
75 |
+
"step": 110
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.13,
|
79 |
+
"learning_rate": 4.338153503893215e-05,
|
80 |
+
"loss": 1.335,
|
81 |
+
"step": 120
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.14,
|
85 |
+
"learning_rate": 4.2825361512791996e-05,
|
86 |
+
"loss": 1.3175,
|
87 |
+
"step": 130
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.16,
|
91 |
+
"learning_rate": 4.226918798665184e-05,
|
92 |
+
"loss": 1.3414,
|
93 |
+
"step": 140
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.17,
|
97 |
+
"learning_rate": 4.171301446051168e-05,
|
98 |
+
"loss": 1.215,
|
99 |
+
"step": 150
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.18,
|
103 |
+
"learning_rate": 4.1156840934371526e-05,
|
104 |
+
"loss": 1.278,
|
105 |
+
"step": 160
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.19,
|
109 |
+
"learning_rate": 4.0600667408231366e-05,
|
110 |
+
"loss": 1.2685,
|
111 |
+
"step": 170
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.2,
|
115 |
+
"learning_rate": 4.0044493882091214e-05,
|
116 |
+
"loss": 1.3019,
|
117 |
+
"step": 180
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.21,
|
121 |
+
"learning_rate": 3.948832035595106e-05,
|
122 |
+
"loss": 1.1352,
|
123 |
+
"step": 190
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.22,
|
127 |
+
"learning_rate": 3.89321468298109e-05,
|
128 |
+
"loss": 1.3311,
|
129 |
+
"step": 200
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.23,
|
133 |
+
"learning_rate": 3.837597330367075e-05,
|
134 |
+
"loss": 1.3117,
|
135 |
+
"step": 210
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.24,
|
139 |
+
"learning_rate": 3.781979977753059e-05,
|
140 |
+
"loss": 1.1897,
|
141 |
+
"step": 220
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.26,
|
145 |
+
"learning_rate": 3.726362625139044e-05,
|
146 |
+
"loss": 1.3223,
|
147 |
+
"step": 230
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.27,
|
151 |
+
"learning_rate": 3.670745272525028e-05,
|
152 |
+
"loss": 1.2783,
|
153 |
+
"step": 240
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.28,
|
157 |
+
"learning_rate": 3.615127919911012e-05,
|
158 |
+
"loss": 1.335,
|
159 |
+
"step": 250
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.29,
|
163 |
+
"learning_rate": 3.559510567296997e-05,
|
164 |
+
"loss": 1.2529,
|
165 |
+
"step": 260
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.3,
|
169 |
+
"learning_rate": 3.503893214682981e-05,
|
170 |
+
"loss": 1.1731,
|
171 |
+
"step": 270
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.31,
|
175 |
+
"learning_rate": 3.4482758620689657e-05,
|
176 |
+
"loss": 1.1722,
|
177 |
+
"step": 280
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.32,
|
181 |
+
"learning_rate": 3.3926585094549504e-05,
|
182 |
+
"loss": 1.2023,
|
183 |
+
"step": 290
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.33,
|
187 |
+
"learning_rate": 3.3370411568409345e-05,
|
188 |
+
"loss": 1.1299,
|
189 |
+
"step": 300
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.34,
|
193 |
+
"learning_rate": 3.281423804226919e-05,
|
194 |
+
"loss": 1.2606,
|
195 |
+
"step": 310
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.36,
|
199 |
+
"learning_rate": 3.2258064516129034e-05,
|
200 |
+
"loss": 1.0815,
|
201 |
+
"step": 320
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.37,
|
205 |
+
"learning_rate": 3.170189098998888e-05,
|
206 |
+
"loss": 1.3171,
|
207 |
+
"step": 330
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.38,
|
211 |
+
"learning_rate": 3.114571746384872e-05,
|
212 |
+
"loss": 1.1747,
|
213 |
+
"step": 340
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.39,
|
217 |
+
"learning_rate": 3.058954393770856e-05,
|
218 |
+
"loss": 1.1978,
|
219 |
+
"step": 350
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.4,
|
223 |
+
"learning_rate": 3.003337041156841e-05,
|
224 |
+
"loss": 1.0724,
|
225 |
+
"step": 360
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.41,
|
229 |
+
"learning_rate": 2.9477196885428255e-05,
|
230 |
+
"loss": 1.3055,
|
231 |
+
"step": 370
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.42,
|
235 |
+
"learning_rate": 2.8921023359288102e-05,
|
236 |
+
"loss": 1.14,
|
237 |
+
"step": 380
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.43,
|
241 |
+
"learning_rate": 2.8364849833147943e-05,
|
242 |
+
"loss": 1.1491,
|
243 |
+
"step": 390
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.44,
|
247 |
+
"learning_rate": 2.7808676307007788e-05,
|
248 |
+
"loss": 0.9949,
|
249 |
+
"step": 400
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.46,
|
253 |
+
"learning_rate": 2.7252502780867635e-05,
|
254 |
+
"loss": 1.1629,
|
255 |
+
"step": 410
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.47,
|
259 |
+
"learning_rate": 2.6696329254727476e-05,
|
260 |
+
"loss": 1.1127,
|
261 |
+
"step": 420
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.48,
|
265 |
+
"learning_rate": 2.6140155728587317e-05,
|
266 |
+
"loss": 1.2377,
|
267 |
+
"step": 430
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.49,
|
271 |
+
"learning_rate": 2.5583982202447165e-05,
|
272 |
+
"loss": 1.1743,
|
273 |
+
"step": 440
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.5,
|
277 |
+
"learning_rate": 2.502780867630701e-05,
|
278 |
+
"loss": 1.1584,
|
279 |
+
"step": 450
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.51,
|
283 |
+
"learning_rate": 2.4471635150166853e-05,
|
284 |
+
"loss": 1.3628,
|
285 |
+
"step": 460
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.52,
|
289 |
+
"learning_rate": 2.3915461624026697e-05,
|
290 |
+
"loss": 1.0802,
|
291 |
+
"step": 470
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.53,
|
295 |
+
"learning_rate": 2.335928809788654e-05,
|
296 |
+
"loss": 1.1615,
|
297 |
+
"step": 480
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.55,
|
301 |
+
"learning_rate": 2.2803114571746386e-05,
|
302 |
+
"loss": 1.2211,
|
303 |
+
"step": 490
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.56,
|
307 |
+
"learning_rate": 2.224694104560623e-05,
|
308 |
+
"loss": 1.1019,
|
309 |
+
"step": 500
|
310 |
+
}
|
311 |
+
],
|
312 |
+
"logging_steps": 10,
|
313 |
+
"max_steps": 899,
|
314 |
+
"num_train_epochs": 1,
|
315 |
+
"save_steps": 500,
|
316 |
+
"total_flos": 6.433444984592794e+16,
|
317 |
+
"trial_name": null,
|
318 |
+
"trial_params": null
|
319 |
+
}
|