Commit
•
3cc3e88
1
Parent(s):
907e07f
Training in progress, step 12000, 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 267835644
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a908ddb4e1d0cb01ff53d6d4956579766f00d9bef503b98c5bec7c6dc8b5b3f
|
3 |
size 267835644
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 535733434
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b29f0f01286b776ce5d34976c5047f77bd8b668153ee2e8a06d87389a148cabe
|
3 |
size 535733434
|
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 sha256:7e1b0bf54794dbc1aa0f801e685ac358890e80baa7b67e058aa2ff95290be389
|
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:c7b9276fef8f7eda277dcd2d635a37b8e237abadc5a5e9f8450094c074a687d1
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "training_dir/checkpoint-
|
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,
|
@@ -216,6 +216,25 @@
|
|
216 |
"eval_samples_per_second": 87.688,
|
217 |
"eval_steps_per_second": 10.961,
|
218 |
"step": 11000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
219 |
}
|
220 |
],
|
221 |
"logging_steps": 1000,
|
@@ -235,7 +254,7 @@
|
|
235 |
"attributes": {}
|
236 |
}
|
237 |
},
|
238 |
-
"total_flos": 1.
|
239 |
"train_batch_size": 8,
|
240 |
"trial_name": null,
|
241 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.7260786855980778,
|
3 |
+
"best_model_checkpoint": "training_dir/checkpoint-12000",
|
4 |
+
"epoch": 1.2715905478435943,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 12000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
216 |
"eval_samples_per_second": 87.688,
|
217 |
"eval_steps_per_second": 10.961,
|
218 |
"step": 11000
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 1.2715905478435943,
|
222 |
+
"grad_norm": 3.347665548324585,
|
223 |
+
"learning_rate": 8.774901459465218e-06,
|
224 |
+
"loss": 0.4096,
|
225 |
+
"step": 12000
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 1.2715905478435943,
|
229 |
+
"eval_accuracy": 0.7338286713286714,
|
230 |
+
"eval_f1": 0.7260786855980778,
|
231 |
+
"eval_loss": 0.8679103851318359,
|
232 |
+
"eval_precision": 0.7338714881942328,
|
233 |
+
"eval_recall": 0.7338286713286714,
|
234 |
+
"eval_runtime": 26.1513,
|
235 |
+
"eval_samples_per_second": 87.491,
|
236 |
+
"eval_steps_per_second": 10.936,
|
237 |
+
"step": 12000
|
238 |
}
|
239 |
],
|
240 |
"logging_steps": 1000,
|
|
|
254 |
"attributes": {}
|
255 |
}
|
256 |
},
|
257 |
+
"total_flos": 1.1650955583502656e+16,
|
258 |
"train_batch_size": 8,
|
259 |
"trial_name": null,
|
260 |
"trial_params": null
|