Training in progress, step 30, 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 619632
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d7e1956e00bca6a37ff14db2a30da9b68b0412270804d15c373d573d895130e
|
3 |
size 619632
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1324026
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f68e5fcfec47e208e5db613b7916aebe5eb47e922e21e87d04bd4b90ef71e6c0
|
3 |
size 1324026
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14512
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f1b42cbd14e4887332cb62e946119f0bcf0d9a9fcacc80ed8b66010e166bbd7
|
3 |
size 14512
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14512
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c8d2f6e87f5b671dfa031e06947209073b518165329eeb9867cd4aaa16776ca
|
3 |
size 14512
|
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:b3e333deca01a6860a16a4bea1a2ebeb14f960dad45973fb2bf65501096c51e2
|
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": 10,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -171,6 +171,84 @@
|
|
171 |
"eval_samples_per_second": 92.192,
|
172 |
"eval_steps_per_second": 23.048,
|
173 |
"step": 20
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
174 |
}
|
175 |
],
|
176 |
"logging_steps": 1,
|
@@ -190,7 +268,7 @@
|
|
190 |
"attributes": {}
|
191 |
}
|
192 |
},
|
193 |
-
"total_flos":
|
194 |
"train_batch_size": 2,
|
195 |
"trial_name": null,
|
196 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.7565011820330969,
|
5 |
"eval_steps": 10,
|
6 |
+
"global_step": 30,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
171 |
"eval_samples_per_second": 92.192,
|
172 |
"eval_steps_per_second": 23.048,
|
173 |
"step": 20
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 0.5295508274231678,
|
177 |
+
"grad_norm": 0.23226885497570038,
|
178 |
+
"learning_rate": 5e-05,
|
179 |
+
"loss": 11.9191,
|
180 |
+
"step": 21
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 0.5547675334909378,
|
184 |
+
"grad_norm": 0.23677287995815277,
|
185 |
+
"learning_rate": 4.5871032726383386e-05,
|
186 |
+
"loss": 11.9191,
|
187 |
+
"step": 22
|
188 |
+
},
|
189 |
+
{
|
190 |
+
"epoch": 0.5799842395587076,
|
191 |
+
"grad_norm": 0.24115414917469025,
|
192 |
+
"learning_rate": 4.17702704859633e-05,
|
193 |
+
"loss": 11.9169,
|
194 |
+
"step": 23
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.6052009456264775,
|
198 |
+
"grad_norm": 0.23872853815555573,
|
199 |
+
"learning_rate": 3.772572564296005e-05,
|
200 |
+
"loss": 11.9193,
|
201 |
+
"step": 24
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.6304176516942475,
|
205 |
+
"grad_norm": 0.24184449017047882,
|
206 |
+
"learning_rate": 3.3765026539765834e-05,
|
207 |
+
"loss": 11.9191,
|
208 |
+
"step": 25
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"epoch": 0.6556343577620173,
|
212 |
+
"grad_norm": 0.2603144645690918,
|
213 |
+
"learning_rate": 2.991522876735154e-05,
|
214 |
+
"loss": 11.9174,
|
215 |
+
"step": 26
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 0.6808510638297872,
|
219 |
+
"grad_norm": 0.26540812849998474,
|
220 |
+
"learning_rate": 2.6202630348146324e-05,
|
221 |
+
"loss": 11.916,
|
222 |
+
"step": 27
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 0.7060677698975572,
|
226 |
+
"grad_norm": 0.2523845136165619,
|
227 |
+
"learning_rate": 2.2652592093878666e-05,
|
228 |
+
"loss": 11.9157,
|
229 |
+
"step": 28
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"epoch": 0.731284475965327,
|
233 |
+
"grad_norm": 0.24367552995681763,
|
234 |
+
"learning_rate": 1.928936436551661e-05,
|
235 |
+
"loss": 11.9162,
|
236 |
+
"step": 29
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.7565011820330969,
|
240 |
+
"grad_norm": 0.25121253728866577,
|
241 |
+
"learning_rate": 1.6135921418712956e-05,
|
242 |
+
"loss": 11.9183,
|
243 |
+
"step": 30
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.7565011820330969,
|
247 |
+
"eval_loss": 11.915938377380371,
|
248 |
+
"eval_runtime": 2.9116,
|
249 |
+
"eval_samples_per_second": 92.045,
|
250 |
+
"eval_steps_per_second": 23.011,
|
251 |
+
"step": 30
|
252 |
}
|
253 |
],
|
254 |
"logging_steps": 1,
|
|
|
268 |
"attributes": {}
|
269 |
}
|
270 |
},
|
271 |
+
"total_flos": 487493216501760.0,
|
272 |
"train_batch_size": 2,
|
273 |
"trial_name": null,
|
274 |
"trial_params": null
|