Training in progress, step 50, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 83945296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0dc74eb4f1664d79e8ca2ad4c0dcaf65b8ebee3025e61594d69d01fb996247d
|
3 |
size 83945296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 42545748
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fa94faad5f7c2fac41c1d3489928c35288395f9537c10cdb8f345784281ca99
|
3 |
size 42545748
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74d3fe4297fd36d6939c92e784b1ab4781c227d97ebf023707e527bcbb1c9fe4
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d102a8b779e588307a5ff1ccea3e1e9ce6254fd84338a3b83b04cad35c2649e7
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 1000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -157,13 +157,163 @@
|
|
157 |
"learning_rate": 0.00016421052631578948,
|
158 |
"loss": 1.7079,
|
159 |
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
160 |
}
|
161 |
],
|
162 |
"logging_steps": 1,
|
163 |
"max_steps": 100,
|
164 |
"num_train_epochs": 1,
|
165 |
"save_steps": 25,
|
166 |
-
"total_flos":
|
167 |
"trial_name": null,
|
168 |
"trial_params": null
|
169 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0012437810945273632,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 50,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
157 |
"learning_rate": 0.00016421052631578948,
|
158 |
"loss": 1.7079,
|
159 |
"step": 25
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.0,
|
163 |
+
"learning_rate": 0.00016210526315789473,
|
164 |
+
"loss": 1.4506,
|
165 |
+
"step": 26
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.0,
|
169 |
+
"learning_rate": 0.00016,
|
170 |
+
"loss": 1.673,
|
171 |
+
"step": 27
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.0,
|
175 |
+
"learning_rate": 0.00015789473684210527,
|
176 |
+
"loss": 1.5159,
|
177 |
+
"step": 28
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.0,
|
181 |
+
"learning_rate": 0.00015578947368421052,
|
182 |
+
"loss": 1.8044,
|
183 |
+
"step": 29
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.0,
|
187 |
+
"learning_rate": 0.0001536842105263158,
|
188 |
+
"loss": 1.311,
|
189 |
+
"step": 30
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.0,
|
193 |
+
"learning_rate": 0.00015157894736842108,
|
194 |
+
"loss": 1.5876,
|
195 |
+
"step": 31
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.0,
|
199 |
+
"learning_rate": 0.00014947368421052633,
|
200 |
+
"loss": 1.5843,
|
201 |
+
"step": 32
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.0,
|
205 |
+
"learning_rate": 0.00014736842105263158,
|
206 |
+
"loss": 1.7256,
|
207 |
+
"step": 33
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.0,
|
211 |
+
"learning_rate": 0.00014526315789473686,
|
212 |
+
"loss": 1.5446,
|
213 |
+
"step": 34
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.0,
|
217 |
+
"learning_rate": 0.0001431578947368421,
|
218 |
+
"loss": 1.9188,
|
219 |
+
"step": 35
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.0,
|
223 |
+
"learning_rate": 0.00014105263157894736,
|
224 |
+
"loss": 1.6284,
|
225 |
+
"step": 36
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.0,
|
229 |
+
"learning_rate": 0.00013894736842105264,
|
230 |
+
"loss": 1.6446,
|
231 |
+
"step": 37
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.0,
|
235 |
+
"learning_rate": 0.0001368421052631579,
|
236 |
+
"loss": 1.5255,
|
237 |
+
"step": 38
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.0,
|
241 |
+
"learning_rate": 0.00013473684210526317,
|
242 |
+
"loss": 1.4796,
|
243 |
+
"step": 39
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.0,
|
247 |
+
"learning_rate": 0.00013263157894736842,
|
248 |
+
"loss": 1.8069,
|
249 |
+
"step": 40
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.0,
|
253 |
+
"learning_rate": 0.0001305263157894737,
|
254 |
+
"loss": 1.5269,
|
255 |
+
"step": 41
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.0,
|
259 |
+
"learning_rate": 0.00012842105263157895,
|
260 |
+
"loss": 1.3387,
|
261 |
+
"step": 42
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.0,
|
265 |
+
"learning_rate": 0.0001263157894736842,
|
266 |
+
"loss": 1.3193,
|
267 |
+
"step": 43
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.0,
|
271 |
+
"learning_rate": 0.00012421052631578949,
|
272 |
+
"loss": 1.6728,
|
273 |
+
"step": 44
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.0,
|
277 |
+
"learning_rate": 0.00012210526315789474,
|
278 |
+
"loss": 1.5991,
|
279 |
+
"step": 45
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.0,
|
283 |
+
"learning_rate": 0.00012,
|
284 |
+
"loss": 1.6619,
|
285 |
+
"step": 46
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.0,
|
289 |
+
"learning_rate": 0.00011789473684210525,
|
290 |
+
"loss": 1.4312,
|
291 |
+
"step": 47
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.0,
|
295 |
+
"learning_rate": 0.00011578947368421053,
|
296 |
+
"loss": 1.4846,
|
297 |
+
"step": 48
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.0,
|
301 |
+
"learning_rate": 0.0001136842105263158,
|
302 |
+
"loss": 1.3929,
|
303 |
+
"step": 49
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.0,
|
307 |
+
"learning_rate": 0.00011157894736842105,
|
308 |
+
"loss": 1.647,
|
309 |
+
"step": 50
|
310 |
}
|
311 |
],
|
312 |
"logging_steps": 1,
|
313 |
"max_steps": 100,
|
314 |
"num_train_epochs": 1,
|
315 |
"save_steps": 25,
|
316 |
+
"total_flos": 2841070876655616.0,
|
317 |
"trial_name": null,
|
318 |
"trial_params": null
|
319 |
}
|