Training in progress, step 800, 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 250422888
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0b07e3916893c629f5be06fa44003b017c775f7861a7f3f1c3b440e109116be
|
3 |
size 250422888
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 126034975
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9547435fdfbd1e4a654ff47695d06dea3644a2f4f8d4f39941f12abff744457d
|
3 |
size 126034975
|
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:a1c7191996a29a392618080702381b78721d13a7789749f412463abf2ff0546d
|
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:de7840bcb72f2f480fd301578d289cdfa174589e831b0d33e5772f3956b6beae
|
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": 11.
|
5 |
"eval_steps": 50,
|
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": 7.855,
|
203 |
"eval_steps_per_second": 0.561,
|
204 |
"step": 750
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
205 |
}
|
206 |
],
|
207 |
"logging_steps": 50,
|
208 |
"max_steps": 804,
|
209 |
"num_train_epochs": 12,
|
210 |
"save_steps": 50,
|
211 |
-
"total_flos": 2.
|
212 |
"trial_name": null,
|
213 |
"trial_params": null
|
214 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 11.940298507462687,
|
5 |
"eval_steps": 50,
|
6 |
+
"global_step": 800,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
202 |
"eval_samples_per_second": 7.855,
|
203 |
"eval_steps_per_second": 0.561,
|
204 |
"step": 750
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 11.94,
|
208 |
+
"learning_rate": 0.0002,
|
209 |
+
"loss": 0.02,
|
210 |
+
"step": 800
|
211 |
+
},
|
212 |
+
{
|
213 |
+
"epoch": 11.94,
|
214 |
+
"eval_runtime": 7.1335,
|
215 |
+
"eval_samples_per_second": 7.85,
|
216 |
+
"eval_steps_per_second": 0.561,
|
217 |
+
"step": 800
|
218 |
}
|
219 |
],
|
220 |
"logging_steps": 50,
|
221 |
"max_steps": 804,
|
222 |
"num_train_epochs": 12,
|
223 |
"save_steps": 50,
|
224 |
+
"total_flos": 2.563731333316608e+17,
|
225 |
"trial_name": null,
|
226 |
"trial_params": null
|
227 |
}
|