Training in progress, step 27, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 82460660
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bcad08300ab33773e7842beae8bc97e3b8f46b8304b3c34b61ed6271564656cb
|
3 |
size 82460660
|
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 sha256:26e775ec5d2f7a6bfc6850d2e1aad7fc89c1cf1b52e210dfc0be05b8df7fabb4
|
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 sha256:00dd6870748d6f432ed334cbec439196364896117466a0420ceec28dd8a722a6
|
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 sha256:3f4cb172acc239bdfcb1321474587dd4513dd004b0281034cdef9d5bfde0d5ff
|
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": 7,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -186,6 +186,48 @@
|
|
186 |
"eval_samples_per_second": 10.065,
|
187 |
"eval_steps_per_second": 2.544,
|
188 |
"step": 21
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
189 |
}
|
190 |
],
|
191 |
"logging_steps": 1,
|
@@ -200,12 +242,12 @@
|
|
200 |
"should_evaluate": false,
|
201 |
"should_log": false,
|
202 |
"should_save": true,
|
203 |
-
"should_training_stop":
|
204 |
},
|
205 |
"attributes": {}
|
206 |
}
|
207 |
},
|
208 |
-
"total_flos":
|
209 |
"train_batch_size": 2,
|
210 |
"trial_name": null,
|
211 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
"eval_steps": 7,
|
6 |
+
"global_step": 27,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
186 |
"eval_samples_per_second": 10.065,
|
187 |
"eval_steps_per_second": 2.544,
|
188 |
"step": 21
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.8148148148148148,
|
192 |
+
"grad_norm": NaN,
|
193 |
+
"learning_rate": 9.549150281252633e-06,
|
194 |
+
"loss": 0.0,
|
195 |
+
"step": 22
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.8518518518518519,
|
199 |
+
"grad_norm": NaN,
|
200 |
+
"learning_rate": 6.184665997806832e-06,
|
201 |
+
"loss": 0.0,
|
202 |
+
"step": 23
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 0.8888888888888888,
|
206 |
+
"grad_norm": NaN,
|
207 |
+
"learning_rate": 3.511175705587433e-06,
|
208 |
+
"loss": 0.0,
|
209 |
+
"step": 24
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.9259259259259259,
|
213 |
+
"grad_norm": NaN,
|
214 |
+
"learning_rate": 1.5708419435684462e-06,
|
215 |
+
"loss": 0.0,
|
216 |
+
"step": 25
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 0.9629629629629629,
|
220 |
+
"grad_norm": NaN,
|
221 |
+
"learning_rate": 3.9426493427611177e-07,
|
222 |
+
"loss": 0.0,
|
223 |
+
"step": 26
|
224 |
+
},
|
225 |
+
{
|
226 |
+
"epoch": 1.0,
|
227 |
+
"grad_norm": NaN,
|
228 |
+
"learning_rate": 0.0,
|
229 |
+
"loss": 0.0,
|
230 |
+
"step": 27
|
231 |
}
|
232 |
],
|
233 |
"logging_steps": 1,
|
|
|
242 |
"should_evaluate": false,
|
243 |
"should_log": false,
|
244 |
"should_save": true,
|
245 |
+
"should_training_stop": true
|
246 |
},
|
247 |
"attributes": {}
|
248 |
}
|
249 |
},
|
250 |
+
"total_flos": 6.03969416538882e+17,
|
251 |
"train_batch_size": 2,
|
252 |
"trial_name": null,
|
253 |
"trial_params": null
|