Training in progress, step 960, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 40036040
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6cc3be11ba62ed932e5ba062221a599333547d99a3430e34a7aa1e2675b68c42
|
3 |
size 40036040
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 20524127
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d70ad7c2f47ec9cc0847b096720542445a3c71f383dae4fdda1bfc858d60d33
|
3 |
size 20524127
|
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:cb03a94214794d8ed500d90fca9e455d6a98b3eb0914a5acdce52e4d2823a8b7
|
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 sha256:0b1031cec1b3d5c56120bdee603429b1488cc4efbb04feaeb164186c47f9797d
|
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": 60,
|
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": 1.92,
|
203 |
"eval_steps_per_second": 0.24,
|
204 |
"step": 900
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
205 |
}
|
206 |
],
|
207 |
"logging_steps": 60,
|
208 |
"max_steps": 1011,
|
209 |
"num_train_epochs": 3,
|
210 |
"save_steps": 60,
|
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": 2.8444444444444446,
|
5 |
"eval_steps": 60,
|
6 |
+
"global_step": 960,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
202 |
"eval_samples_per_second": 1.92,
|
203 |
"eval_steps_per_second": 0.24,
|
204 |
"step": 900
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 2.84,
|
208 |
+
"learning_rate": 0.0002,
|
209 |
+
"loss": 0.5142,
|
210 |
+
"step": 960
|
211 |
+
},
|
212 |
+
{
|
213 |
+
"epoch": 2.84,
|
214 |
+
"eval_runtime": 312.6866,
|
215 |
+
"eval_samples_per_second": 1.919,
|
216 |
+
"eval_steps_per_second": 0.24,
|
217 |
+
"step": 960
|
218 |
}
|
219 |
],
|
220 |
"logging_steps": 60,
|
221 |
"max_steps": 1011,
|
222 |
"num_train_epochs": 3,
|
223 |
"save_steps": 60,
|
224 |
+
"total_flos": 1.5945703889043456e+17,
|
225 |
"trial_name": null,
|
226 |
"trial_params": null
|
227 |
}
|