Training in progress, step 17000
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 1001681601
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:538229d82a05fff2d6cf4e6973c9d608c21e692faa19e9beea40fa506e4a0003
|
3 |
size 1001681601
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 551185105
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9684ff4172feb34ca3af08aa608bbd0322b13d127d5576c0f0b7f3d4aa7780e
|
3 |
size 551185105
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e24430e5241c54b45d28107fd4cebd580d985b0d386634de5afc57a4bff9a2e
|
3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36e7e2511bc0b0231776dcfd85d74704f83c0a638b6570fde25a007848fdecba
|
3 |
size 623
|
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,
|
@@ -204,11 +204,17 @@
|
|
204 |
"learning_rate": 3.125340909090909e-05,
|
205 |
"loss": 0.0312,
|
206 |
"step": 16500
|
|
|
|
|
|
|
|
|
|
|
|
|
207 |
}
|
208 |
],
|
209 |
"max_steps": 44000,
|
210 |
"num_train_epochs": 1,
|
211 |
-
"total_flos": 1.
|
212 |
"trial_name": null,
|
213 |
"trial_params": null
|
214 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.23060853522884506,
|
5 |
+
"global_step": 17000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
204 |
"learning_rate": 3.125340909090909e-05,
|
205 |
"loss": 0.0312,
|
206 |
"step": 16500
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.23,
|
210 |
+
"learning_rate": 3.068522727272727e-05,
|
211 |
+
"loss": 0.034,
|
212 |
+
"step": 17000
|
213 |
}
|
214 |
],
|
215 |
"max_steps": 44000,
|
216 |
"num_train_epochs": 1,
|
217 |
+
"total_flos": 1.7764172276170752e+16,
|
218 |
"trial_name": null,
|
219 |
"trial_params": null
|
220 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 551185105
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9684ff4172feb34ca3af08aa608bbd0322b13d127d5576c0f0b7f3d4aa7780e
|
3 |
size 551185105
|
runs/Oct19_12-48-30_40567d3bb726/events.out.tfevents.1666183950.40567d3bb726.23.0
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 sha256:2f4cc3970f5dcac3a026ad9c73d8a778b0a708c0ddee88b59c92d167a2ff9e3a
|
3 |
+
size 50990
|