Training in progress, step 20000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +51 -3
- pytorch_model.bin +1 -1
- runs/Jun16_15-16-02_9a4f5f66b33d/events.out.tfevents.1686930096.9a4f5f66b33d.224.0 +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3871543575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c879f385b422df3fca5228513f3bae4387ed9e62fd092ebca498251ff96dd82
|
3 |
size 3871543575
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1944201353
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24a7fb993881a603ce7c7932d42c04cd7697ed7fbc569bff9d0a019e4b731376
|
3 |
size 1944201353
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdfd1692f8c3e07bd7f0386306b8a4dc7984bed19ffb5f1fb77db39dc898e24a
|
3 |
size 14575
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a64456a544b4e3b448418c8f8b53a190245445274955bebd8d3b8522bf98ccb
|
3 |
size 557
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7240fa7db242cb3d6601e7b6ac5c0a2f2bebee276959a658a3c866c5e8a6d292
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -198,11 +198,59 @@
|
|
198 |
"learning_rate": 3.1271392346753284e-05,
|
199 |
"loss": 1.4551,
|
200 |
"step": 16000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
201 |
}
|
202 |
],
|
203 |
"max_steps": 38148,
|
204 |
"num_train_epochs": 1,
|
205 |
-
"total_flos":
|
206 |
"trial_name": null,
|
207 |
"trial_params": null
|
208 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5242683834708665,
|
5 |
+
"global_step": 20000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
198 |
"learning_rate": 3.1271392346753284e-05,
|
199 |
"loss": 1.4551,
|
200 |
"step": 16000
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.43,
|
204 |
+
"learning_rate": 3.0269864639674983e-05,
|
205 |
+
"loss": 1.4527,
|
206 |
+
"step": 16500
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.45,
|
210 |
+
"learning_rate": 2.9259403172138987e-05,
|
211 |
+
"loss": 1.4356,
|
212 |
+
"step": 17000
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.46,
|
216 |
+
"learning_rate": 2.82437623590975e-05,
|
217 |
+
"loss": 1.4362,
|
218 |
+
"step": 17500
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.47,
|
222 |
+
"learning_rate": 2.7220593841620623e-05,
|
223 |
+
"loss": 1.432,
|
224 |
+
"step": 18000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.48,
|
228 |
+
"learning_rate": 2.6193660852983415e-05,
|
229 |
+
"loss": 1.4234,
|
230 |
+
"step": 18500
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.5,
|
234 |
+
"learning_rate": 2.516676307917844e-05,
|
235 |
+
"loss": 1.436,
|
236 |
+
"step": 19000
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.51,
|
240 |
+
"learning_rate": 2.4137526132994945e-05,
|
241 |
+
"loss": 1.4238,
|
242 |
+
"step": 19500
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.52,
|
246 |
+
"learning_rate": 2.3109751299304977e-05,
|
247 |
+
"loss": 1.41,
|
248 |
+
"step": 20000
|
249 |
}
|
250 |
],
|
251 |
"max_steps": 38148,
|
252 |
"num_train_epochs": 1,
|
253 |
+
"total_flos": 2.203967601635328e+16,
|
254 |
"trial_name": null,
|
255 |
"trial_params": null
|
256 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1944201353
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24a7fb993881a603ce7c7932d42c04cd7697ed7fbc569bff9d0a019e4b731376
|
3 |
size 1944201353
|
runs/Jun16_15-16-02_9a4f5f66b33d/events.out.tfevents.1686930096.9a4f5f66b33d.224.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3ddbc9058e2a8a8eb81aba89a2cdbd4db12323f86913da6db85e0ef1ec52a4e
|
3 |
+
size 6998
|