Training in progress, step 1600, 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 160285149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dad3d06f0f980d4edd0f8032b0d5b2084cb4ed65a2b41d878824284e87b4394a
|
3 |
size 160285149
|
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 sha256:997a463cccc37ed909b6ca16f4417c673f1e6a3e05dc425808a13eea5f9dd965
|
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:feeaa9dcb687f34c537c5701e819b6bcadabf7b8c8429475390fcaf3b1c3a91e
|
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": 2.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -202,13 +202,26 @@
|
|
202 |
"eval_samples_per_second": 1.904,
|
203 |
"eval_steps_per_second": 0.239,
|
204 |
"step": 1500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
205 |
}
|
206 |
],
|
207 |
"logging_steps": 100,
|
208 |
"max_steps": 2025,
|
209 |
"num_train_epochs": 3,
|
210 |
"save_steps": 100,
|
211 |
-
"total_flos": 3.
|
212 |
"trial_name": null,
|
213 |
"trial_params": null
|
214 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.3703703703703702,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 1600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
202 |
"eval_samples_per_second": 1.904,
|
203 |
"eval_steps_per_second": 0.239,
|
204 |
"step": 1500
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 2.37,
|
208 |
+
"learning_rate": 0.0,
|
209 |
+
"loss": 8.3433,
|
210 |
+
"step": 1600
|
211 |
+
},
|
212 |
+
{
|
213 |
+
"epoch": 2.37,
|
214 |
+
"eval_runtime": 788.3781,
|
215 |
+
"eval_samples_per_second": 1.903,
|
216 |
+
"eval_steps_per_second": 0.238,
|
217 |
+
"step": 1600
|
218 |
}
|
219 |
],
|
220 |
"logging_steps": 100,
|
221 |
"max_steps": 2025,
|
222 |
"num_train_epochs": 3,
|
223 |
"save_steps": 100,
|
224 |
+
"total_flos": 3.33184638124032e+17,
|
225 |
"trial_name": null,
|
226 |
"trial_params": null
|
227 |
}
|