Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +432 -0
trainer_state.json
ADDED
@@ -0,0 +1,432 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9991235758106923,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 285,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.017528483786152498,
|
13 |
+
"grad_norm": 2.3260412216186523,
|
14 |
+
"learning_rate": 2e-05,
|
15 |
+
"loss": 0.4745,
|
16 |
+
"step": 5
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.035056967572304996,
|
20 |
+
"grad_norm": 2.4670772552490234,
|
21 |
+
"learning_rate": 2e-05,
|
22 |
+
"loss": 0.5049,
|
23 |
+
"step": 10
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.05258545135845749,
|
27 |
+
"grad_norm": 2.598940372467041,
|
28 |
+
"learning_rate": 2e-05,
|
29 |
+
"loss": 0.509,
|
30 |
+
"step": 15
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.07011393514460999,
|
34 |
+
"grad_norm": 2.3951876163482666,
|
35 |
+
"learning_rate": 2e-05,
|
36 |
+
"loss": 0.4642,
|
37 |
+
"step": 20
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.0876424189307625,
|
41 |
+
"grad_norm": 2.50634765625,
|
42 |
+
"learning_rate": 2e-05,
|
43 |
+
"loss": 0.4899,
|
44 |
+
"step": 25
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.10517090271691498,
|
48 |
+
"grad_norm": 2.51271390914917,
|
49 |
+
"learning_rate": 2e-05,
|
50 |
+
"loss": 0.5057,
|
51 |
+
"step": 30
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.12269938650306748,
|
55 |
+
"grad_norm": 2.2455062866210938,
|
56 |
+
"learning_rate": 2e-05,
|
57 |
+
"loss": 0.4374,
|
58 |
+
"step": 35
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.14022787028921999,
|
62 |
+
"grad_norm": 2.7102108001708984,
|
63 |
+
"learning_rate": 2e-05,
|
64 |
+
"loss": 0.4747,
|
65 |
+
"step": 40
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.15775635407537247,
|
69 |
+
"grad_norm": 2.5008888244628906,
|
70 |
+
"learning_rate": 2e-05,
|
71 |
+
"loss": 0.4686,
|
72 |
+
"step": 45
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.175284837861525,
|
76 |
+
"grad_norm": 2.638371467590332,
|
77 |
+
"learning_rate": 2e-05,
|
78 |
+
"loss": 0.4867,
|
79 |
+
"step": 50
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.19281332164767748,
|
83 |
+
"grad_norm": 2.447908878326416,
|
84 |
+
"learning_rate": 2e-05,
|
85 |
+
"loss": 0.4578,
|
86 |
+
"step": 55
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.21034180543382996,
|
90 |
+
"grad_norm": 3.2303571701049805,
|
91 |
+
"learning_rate": 2e-05,
|
92 |
+
"loss": 0.4797,
|
93 |
+
"step": 60
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.22787028921998248,
|
97 |
+
"grad_norm": 2.4729976654052734,
|
98 |
+
"learning_rate": 2e-05,
|
99 |
+
"loss": 0.4778,
|
100 |
+
"step": 65
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.24539877300613497,
|
104 |
+
"grad_norm": 2.7793662548065186,
|
105 |
+
"learning_rate": 2e-05,
|
106 |
+
"loss": 0.4679,
|
107 |
+
"step": 70
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.26292725679228746,
|
111 |
+
"grad_norm": 2.6131370067596436,
|
112 |
+
"learning_rate": 2e-05,
|
113 |
+
"loss": 0.4866,
|
114 |
+
"step": 75
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.28045574057843997,
|
118 |
+
"grad_norm": 2.5630428791046143,
|
119 |
+
"learning_rate": 2e-05,
|
120 |
+
"loss": 0.4802,
|
121 |
+
"step": 80
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.2979842243645925,
|
125 |
+
"grad_norm": 2.7526726722717285,
|
126 |
+
"learning_rate": 2e-05,
|
127 |
+
"loss": 0.4572,
|
128 |
+
"step": 85
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.31551270815074495,
|
132 |
+
"grad_norm": 2.934720993041992,
|
133 |
+
"learning_rate": 2e-05,
|
134 |
+
"loss": 0.4557,
|
135 |
+
"step": 90
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.33304119193689746,
|
139 |
+
"grad_norm": 2.7996726036071777,
|
140 |
+
"learning_rate": 2e-05,
|
141 |
+
"loss": 0.4692,
|
142 |
+
"step": 95
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.35056967572305,
|
146 |
+
"grad_norm": 3.004939079284668,
|
147 |
+
"learning_rate": 2e-05,
|
148 |
+
"loss": 0.4786,
|
149 |
+
"step": 100
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.36809815950920244,
|
153 |
+
"grad_norm": 2.67604660987854,
|
154 |
+
"learning_rate": 2e-05,
|
155 |
+
"loss": 0.4955,
|
156 |
+
"step": 105
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.38562664329535495,
|
160 |
+
"grad_norm": 2.9146041870117188,
|
161 |
+
"learning_rate": 2e-05,
|
162 |
+
"loss": 0.4509,
|
163 |
+
"step": 110
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.40315512708150747,
|
167 |
+
"grad_norm": 2.9048011302948,
|
168 |
+
"learning_rate": 2e-05,
|
169 |
+
"loss": 0.4457,
|
170 |
+
"step": 115
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.42068361086765993,
|
174 |
+
"grad_norm": 2.4492969512939453,
|
175 |
+
"learning_rate": 2e-05,
|
176 |
+
"loss": 0.4572,
|
177 |
+
"step": 120
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.43821209465381245,
|
181 |
+
"grad_norm": 2.833976984024048,
|
182 |
+
"learning_rate": 2e-05,
|
183 |
+
"loss": 0.4538,
|
184 |
+
"step": 125
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.45574057843996496,
|
188 |
+
"grad_norm": 2.866576671600342,
|
189 |
+
"learning_rate": 2e-05,
|
190 |
+
"loss": 0.4817,
|
191 |
+
"step": 130
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.4732690622261174,
|
195 |
+
"grad_norm": 3.0097880363464355,
|
196 |
+
"learning_rate": 2e-05,
|
197 |
+
"loss": 0.4555,
|
198 |
+
"step": 135
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.49079754601226994,
|
202 |
+
"grad_norm": 2.912531852722168,
|
203 |
+
"learning_rate": 2e-05,
|
204 |
+
"loss": 0.5023,
|
205 |
+
"step": 140
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.5083260297984225,
|
209 |
+
"grad_norm": 2.936351776123047,
|
210 |
+
"learning_rate": 2e-05,
|
211 |
+
"loss": 0.48,
|
212 |
+
"step": 145
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.5258545135845749,
|
216 |
+
"grad_norm": 2.962674856185913,
|
217 |
+
"learning_rate": 2e-05,
|
218 |
+
"loss": 0.4526,
|
219 |
+
"step": 150
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.5433829973707275,
|
223 |
+
"grad_norm": 2.743187189102173,
|
224 |
+
"learning_rate": 2e-05,
|
225 |
+
"loss": 0.4774,
|
226 |
+
"step": 155
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.5609114811568799,
|
230 |
+
"grad_norm": 2.742067575454712,
|
231 |
+
"learning_rate": 2e-05,
|
232 |
+
"loss": 0.4789,
|
233 |
+
"step": 160
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.5784399649430324,
|
237 |
+
"grad_norm": 3.111201047897339,
|
238 |
+
"learning_rate": 2e-05,
|
239 |
+
"loss": 0.4877,
|
240 |
+
"step": 165
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.595968448729185,
|
244 |
+
"grad_norm": 2.6774637699127197,
|
245 |
+
"learning_rate": 2e-05,
|
246 |
+
"loss": 0.4867,
|
247 |
+
"step": 170
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.6134969325153374,
|
251 |
+
"grad_norm": 3.2346479892730713,
|
252 |
+
"learning_rate": 2e-05,
|
253 |
+
"loss": 0.4781,
|
254 |
+
"step": 175
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.6310254163014899,
|
258 |
+
"grad_norm": 2.714986801147461,
|
259 |
+
"learning_rate": 2e-05,
|
260 |
+
"loss": 0.5008,
|
261 |
+
"step": 180
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.6485539000876425,
|
265 |
+
"grad_norm": 2.6662895679473877,
|
266 |
+
"learning_rate": 2e-05,
|
267 |
+
"loss": 0.4053,
|
268 |
+
"step": 185
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.6660823838737949,
|
272 |
+
"grad_norm": 3.0469818115234375,
|
273 |
+
"learning_rate": 2e-05,
|
274 |
+
"loss": 0.4482,
|
275 |
+
"step": 190
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.6836108676599474,
|
279 |
+
"grad_norm": 2.78334379196167,
|
280 |
+
"learning_rate": 2e-05,
|
281 |
+
"loss": 0.4731,
|
282 |
+
"step": 195
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.7011393514461,
|
286 |
+
"grad_norm": 2.9470932483673096,
|
287 |
+
"learning_rate": 2e-05,
|
288 |
+
"loss": 0.444,
|
289 |
+
"step": 200
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.7186678352322524,
|
293 |
+
"grad_norm": 3.256516218185425,
|
294 |
+
"learning_rate": 2e-05,
|
295 |
+
"loss": 0.4826,
|
296 |
+
"step": 205
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.7361963190184049,
|
300 |
+
"grad_norm": 3.080620765686035,
|
301 |
+
"learning_rate": 2e-05,
|
302 |
+
"loss": 0.4561,
|
303 |
+
"step": 210
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.7537248028045574,
|
307 |
+
"grad_norm": 3.4312586784362793,
|
308 |
+
"learning_rate": 2e-05,
|
309 |
+
"loss": 0.4471,
|
310 |
+
"step": 215
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.7712532865907099,
|
314 |
+
"grad_norm": 2.649163246154785,
|
315 |
+
"learning_rate": 2e-05,
|
316 |
+
"loss": 0.4449,
|
317 |
+
"step": 220
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.7887817703768624,
|
321 |
+
"grad_norm": 2.7402210235595703,
|
322 |
+
"learning_rate": 2e-05,
|
323 |
+
"loss": 0.469,
|
324 |
+
"step": 225
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.8063102541630149,
|
328 |
+
"grad_norm": 3.1415464878082275,
|
329 |
+
"learning_rate": 2e-05,
|
330 |
+
"loss": 0.4706,
|
331 |
+
"step": 230
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.8238387379491674,
|
335 |
+
"grad_norm": 3.1218481063842773,
|
336 |
+
"learning_rate": 2e-05,
|
337 |
+
"loss": 0.4754,
|
338 |
+
"step": 235
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.8413672217353199,
|
342 |
+
"grad_norm": 3.197633743286133,
|
343 |
+
"learning_rate": 2e-05,
|
344 |
+
"loss": 0.4614,
|
345 |
+
"step": 240
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.8588957055214724,
|
349 |
+
"grad_norm": 2.9509947299957275,
|
350 |
+
"learning_rate": 2e-05,
|
351 |
+
"loss": 0.5037,
|
352 |
+
"step": 245
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.8764241893076249,
|
356 |
+
"grad_norm": 3.126260995864868,
|
357 |
+
"learning_rate": 2e-05,
|
358 |
+
"loss": 0.4472,
|
359 |
+
"step": 250
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.8939526730937774,
|
363 |
+
"grad_norm": 3.562556028366089,
|
364 |
+
"learning_rate": 2e-05,
|
365 |
+
"loss": 0.4515,
|
366 |
+
"step": 255
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.9114811568799299,
|
370 |
+
"grad_norm": 3.086526870727539,
|
371 |
+
"learning_rate": 2e-05,
|
372 |
+
"loss": 0.5097,
|
373 |
+
"step": 260
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.9290096406660824,
|
377 |
+
"grad_norm": 3.190669059753418,
|
378 |
+
"learning_rate": 2e-05,
|
379 |
+
"loss": 0.462,
|
380 |
+
"step": 265
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.9465381244522348,
|
384 |
+
"grad_norm": 3.133270263671875,
|
385 |
+
"learning_rate": 2e-05,
|
386 |
+
"loss": 0.445,
|
387 |
+
"step": 270
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.9640666082383874,
|
391 |
+
"grad_norm": 3.3561840057373047,
|
392 |
+
"learning_rate": 2e-05,
|
393 |
+
"loss": 0.4711,
|
394 |
+
"step": 275
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.9815950920245399,
|
398 |
+
"grad_norm": 3.056903123855591,
|
399 |
+
"learning_rate": 2e-05,
|
400 |
+
"loss": 0.5028,
|
401 |
+
"step": 280
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.9991235758106923,
|
405 |
+
"grad_norm": 2.7743754386901855,
|
406 |
+
"learning_rate": 2e-05,
|
407 |
+
"loss": 0.4612,
|
408 |
+
"step": 285
|
409 |
+
}
|
410 |
+
],
|
411 |
+
"logging_steps": 5,
|
412 |
+
"max_steps": 285,
|
413 |
+
"num_input_tokens_seen": 0,
|
414 |
+
"num_train_epochs": 1,
|
415 |
+
"save_steps": 285,
|
416 |
+
"stateful_callbacks": {
|
417 |
+
"TrainerControl": {
|
418 |
+
"args": {
|
419 |
+
"should_epoch_stop": false,
|
420 |
+
"should_evaluate": false,
|
421 |
+
"should_log": false,
|
422 |
+
"should_save": true,
|
423 |
+
"should_training_stop": true
|
424 |
+
},
|
425 |
+
"attributes": {}
|
426 |
+
}
|
427 |
+
},
|
428 |
+
"total_flos": 1.111992390689751e+17,
|
429 |
+
"train_batch_size": 2,
|
430 |
+
"trial_name": null,
|
431 |
+
"trial_params": null
|
432 |
+
}
|