Training in progress, step 3600, 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 sha256:8e850ab811c07088db6a10f86cfa452f4b43572ddf4faf9d984978e526aa1dd6
|
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 127492797
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11ac9aba55afbd01330c8f8be5eaa007e2abcc10837b1087604d9ef08d1ddb38
|
3 |
size 127492797
|
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 sha256:382288faa7eb6a4be2221e059ad8686313f2990080de2ec1c8339aa39829284b
|
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 sha256:43e3cf8d56a3f083d00cc85544d76ada2f884a1018c8752332d96f2799911117
|
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": 10.
|
5 |
"eval_steps": 200,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -228,13 +228,26 @@
|
|
228 |
"eval_samples_per_second": 7.919,
|
229 |
"eval_steps_per_second": 0.516,
|
230 |
"step": 3400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
231 |
}
|
232 |
],
|
233 |
"logging_steps": 200,
|
234 |
"max_steps": 3936,
|
235 |
"num_train_epochs": 12,
|
236 |
"save_steps": 200,
|
237 |
-
"total_flos": 1.
|
238 |
"trial_name": null,
|
239 |
"trial_params": null
|
240 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 10.975609756097562,
|
5 |
"eval_steps": 200,
|
6 |
+
"global_step": 3600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
228 |
"eval_samples_per_second": 7.919,
|
229 |
"eval_steps_per_second": 0.516,
|
230 |
"step": 3400
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 10.98,
|
234 |
+
"learning_rate": 0.0002,
|
235 |
+
"loss": 0.0271,
|
236 |
+
"step": 3600
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 10.98,
|
240 |
+
"eval_runtime": 34.8248,
|
241 |
+
"eval_samples_per_second": 7.925,
|
242 |
+
"eval_steps_per_second": 0.517,
|
243 |
+
"step": 3600
|
244 |
}
|
245 |
],
|
246 |
"logging_steps": 200,
|
247 |
"max_steps": 3936,
|
248 |
"num_train_epochs": 12,
|
249 |
"save_steps": 200,
|
250 |
+
"total_flos": 1.159845700435968e+18,
|
251 |
"trial_name": null,
|
252 |
"trial_params": null
|
253 |
}
|