Training in progress, step 1700, 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 159967880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0137ef99c1a7b8626424c1ce04ccdf9189cb06acd6d38d5f7e43a46d039a7703
|
3 |
size 159967880
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 80630623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:728eb538e59043c90e414bb1cc0d89ad5560107e49193b572a6ced9e91e48e35
|
3 |
size 80630623
|
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:bc21fea72dc0791f4dc549e7c6b2f79ab236ae3c9b25f0eae4230835b22335ac
|
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 sha256:80bd1a19eefcf2faa72604d45a7e0dd3eaa509be69eeefba41933c85d5335a1a
|
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":
|
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,
|
@@ -215,13 +215,26 @@
|
|
215 |
"eval_samples_per_second": 1.881,
|
216 |
"eval_steps_per_second": 0.245,
|
217 |
"step": 1600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
218 |
}
|
219 |
],
|
220 |
"logging_steps": 100,
|
221 |
"max_steps": 1804,
|
222 |
"num_train_epochs": 11,
|
223 |
"save_steps": 100,
|
224 |
-
"total_flos": 1.
|
225 |
"trial_name": null,
|
226 |
"trial_params": null
|
227 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 10.365853658536585,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 1700,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
215 |
"eval_samples_per_second": 1.881,
|
216 |
"eval_steps_per_second": 0.245,
|
217 |
"step": 1600
|
218 |
+
},
|
219 |
+
{
|
220 |
+
"epoch": 10.37,
|
221 |
+
"learning_rate": 0.0002,
|
222 |
+
"loss": 0.0195,
|
223 |
+
"step": 1700
|
224 |
+
},
|
225 |
+
{
|
226 |
+
"epoch": 10.37,
|
227 |
+
"eval_runtime": 37.1791,
|
228 |
+
"eval_samples_per_second": 1.856,
|
229 |
+
"eval_steps_per_second": 0.242,
|
230 |
+
"step": 1700
|
231 |
}
|
232 |
],
|
233 |
"logging_steps": 100,
|
234 |
"max_steps": 1804,
|
235 |
"num_train_epochs": 11,
|
236 |
"save_steps": 100,
|
237 |
+
"total_flos": 1.4212437116977152e+17,
|
238 |
"trial_name": null,
|
239 |
"trial_params": null
|
240 |
}
|