avsolatorio
commited on
Commit
•
df32995
1
Parent(s):
667a9da
Training in progress, step 10000, 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 567860028
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f06716d5e39e3844b62b76246c7392c6c734c0213938b108fb5a9eacfdd9fde
|
3 |
size 567860028
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1135783354
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e7d10ccae7d40970506ebff49a96c6ffba1d50c51f47b4f62114311af953d83
|
3 |
size 1135783354
|
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 sha256:6b7e320b5a2475507aebb5f1ef7a9c98d12600ef0165cc1de949f181761d986b
|
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 sha256:28e35c5a0c1eb4f922a2e3785d5afca45020e4d0fc6713cc20aea6ed31f143e1
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "doc-topic-model_eval-01_train-02/checkpoint-
|
4 |
-
"epoch": 4.
|
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,
|
@@ -241,6 +241,32 @@
|
|
241 |
"eval_samples_per_second": 573.27,
|
242 |
"eval_steps_per_second": 2.262,
|
243 |
"step": 9000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
244 |
}
|
245 |
],
|
246 |
"logging_steps": 500,
|
@@ -269,7 +295,7 @@
|
|
269 |
"attributes": {}
|
270 |
}
|
271 |
},
|
272 |
-
"total_flos":
|
273 |
"train_batch_size": 4,
|
274 |
"trial_name": null,
|
275 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.03805249184370041,
|
3 |
+
"best_model_checkpoint": "doc-topic-model_eval-01_train-02/checkpoint-10000",
|
4 |
+
"epoch": 4.930966469428008,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 10000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
241 |
"eval_samples_per_second": 573.27,
|
242 |
"eval_steps_per_second": 2.262,
|
243 |
"step": 9000
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 4.684418145956608,
|
247 |
+
"grad_norm": 0.4473079442977905,
|
248 |
+
"learning_rate": 1.906311637080868e-05,
|
249 |
+
"loss": 0.0336,
|
250 |
+
"step": 9500
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 4.930966469428008,
|
254 |
+
"grad_norm": 0.4554208219051361,
|
255 |
+
"learning_rate": 1.90138067061144e-05,
|
256 |
+
"loss": 0.0337,
|
257 |
+
"step": 10000
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 4.930966469428008,
|
261 |
+
"eval_accuracy": 0.9872131751633431,
|
262 |
+
"eval_f1": 0.5864882207351728,
|
263 |
+
"eval_loss": 0.03805249184370041,
|
264 |
+
"eval_precision": 0.7368421052631579,
|
265 |
+
"eval_recall": 0.48709554625047585,
|
266 |
+
"eval_runtime": 14.2923,
|
267 |
+
"eval_samples_per_second": 567.44,
|
268 |
+
"eval_steps_per_second": 2.239,
|
269 |
+
"step": 10000
|
270 |
}
|
271 |
],
|
272 |
"logging_steps": 500,
|
|
|
295 |
"attributes": {}
|
296 |
}
|
297 |
},
|
298 |
+
"total_flos": 225936279463716.0,
|
299 |
"train_batch_size": 4,
|
300 |
"trial_name": null,
|
301 |
"trial_params": null
|