Training in progress, step 19500, 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 861935749
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8dd07b6b596bb0c325d20b9e3d20e2158baa9b3dfa6d4d513ac628406e25341
|
3 |
size 861935749
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 430952617
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8df426bff3ed5a8c32d0abbdab33e5ccb26ed58197980c35ca0879c6fa3e6c8a
|
3 |
size 430952617
|
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 sha256:1c8176e1ec47946d472d181e26ad318f9c75250d767f89eec55c9b7cf80cdaec
|
3 |
size 14575
|
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:b1b96e24677cc20668bec0f40c911dcd14ada89e7e47ca87444a9b8a87373ae8
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 1.
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -229,13 +229,25 @@
|
|
229 |
"learning_rate": 8.886885442961896e-06,
|
230 |
"loss": 0.7192,
|
231 |
"step": 18500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
232 |
}
|
233 |
],
|
234 |
"logging_steps": 500,
|
235 |
"max_steps": 33276,
|
236 |
"num_train_epochs": 3,
|
237 |
"save_steps": 500,
|
238 |
-
"total_flos":
|
239 |
"trial_name": null,
|
240 |
"trial_params": null
|
241 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.7580238009376128,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 19500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
229 |
"learning_rate": 8.886885442961896e-06,
|
230 |
"loss": 0.7192,
|
231 |
"step": 18500
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 1.71,
|
235 |
+
"learning_rate": 8.58636855391273e-06,
|
236 |
+
"loss": 0.7622,
|
237 |
+
"step": 19000
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 1.76,
|
241 |
+
"learning_rate": 8.285851664863566e-06,
|
242 |
+
"loss": 0.6851,
|
243 |
+
"step": 19500
|
244 |
}
|
245 |
],
|
246 |
"logging_steps": 500,
|
247 |
"max_steps": 33276,
|
248 |
"num_train_epochs": 3,
|
249 |
"save_steps": 500,
|
250 |
+
"total_flos": 3.0570348730139136e+16,
|
251 |
"trial_name": null,
|
252 |
"trial_params": null
|
253 |
}
|