Commit
•
612a16b
1
Parent(s):
f90ea6c
Training in progress, step 11000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 498615900
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2d9fb3b6451701ab0f2b4824a5375c62006fafa087665c750e5619e2afc89a5
|
3 |
size 498615900
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 997351674
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7780208e680819257b41d50d9dbf64fedfef08bbc5208d0f983c6de4437369bb
|
3 |
size 997351674
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff74a6d71562ab6f97231e9e623c95eb7bdf04875ef1e5eba2c042d1af40b2d6
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:884b5db9dd691ce707dfb4a94a86e37c81019d23d8b0ae7bb40693c59676428e
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.7624731472235634,
|
3 |
"best_model_checkpoint": "training_dir/checkpoint-6000",
|
4 |
-
"epoch": 1.
|
5 |
"eval_steps": 1000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -197,6 +197,25 @@
|
|
197 |
"eval_samples_per_second": 48.038,
|
198 |
"eval_steps_per_second": 6.005,
|
199 |
"step": 10000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
200 |
}
|
201 |
],
|
202 |
"logging_steps": 1000,
|
@@ -216,7 +235,7 @@
|
|
216 |
"attributes": {}
|
217 |
}
|
218 |
},
|
219 |
-
"total_flos": 2.
|
220 |
"train_batch_size": 8,
|
221 |
"trial_name": null,
|
222 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.7624731472235634,
|
3 |
"best_model_checkpoint": "training_dir/checkpoint-6000",
|
4 |
+
"epoch": 1.7225180081428124,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 11000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
197 |
"eval_samples_per_second": 48.038,
|
198 |
"eval_steps_per_second": 6.005,
|
199 |
"step": 10000
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 1.7225180081428124,
|
203 |
+
"grad_norm": 44.26694107055664,
|
204 |
+
"learning_rate": 8.342803030303031e-06,
|
205 |
+
"loss": 0.3903,
|
206 |
+
"step": 11000
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 1.7225180081428124,
|
210 |
+
"eval_accuracy": 0.7552447552447552,
|
211 |
+
"eval_f1": 0.7447143825904207,
|
212 |
+
"eval_loss": 0.9456614255905151,
|
213 |
+
"eval_precision": 0.7531489883387709,
|
214 |
+
"eval_recall": 0.7552447552447552,
|
215 |
+
"eval_runtime": 47.5072,
|
216 |
+
"eval_samples_per_second": 48.161,
|
217 |
+
"eval_steps_per_second": 6.02,
|
218 |
+
"step": 11000
|
219 |
}
|
220 |
],
|
221 |
"logging_steps": 1000,
|
|
|
235 |
"attributes": {}
|
236 |
}
|
237 |
},
|
238 |
+
"total_flos": 2.2525788225157308e+16,
|
239 |
"train_batch_size": 8,
|
240 |
"trial_name": null,
|
241 |
"trial_params": null
|