BayesTensor
commited on
Training in progress, epoch 19, 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 598442860
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:deb8bc8088d7528688e5fc30c19122ba34b0b3fc791659ee1e77fe7bb7ac68ea
|
3 |
size 598442860
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1196973562
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4bcaa4be638eed342c9858fdc71ea4b8324afce83dfbbccb782915f3198e075a
|
3 |
size 1196973562
|
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:c013855f1f203be97dafecaefb623110a70641991f8c85f3b86fa91a81df5017
|
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 sha256:91d901b8e24ff445bb3da4dc7139a20d48de041e98a6d37b448bd10822dc47b7
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "modernbert-medical-classifier/checkpoint-
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -281,6 +281,22 @@
|
|
281 |
"eval_samples_per_second": 12.552,
|
282 |
"eval_steps_per_second": 3.138,
|
283 |
"step": 1656
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
284 |
}
|
285 |
],
|
286 |
"logging_steps": 100,
|
@@ -300,7 +316,7 @@
|
|
300 |
"attributes": {}
|
301 |
}
|
302 |
},
|
303 |
-
"total_flos": 1.
|
304 |
"train_batch_size": 4,
|
305 |
"trial_name": null,
|
306 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.6820012787723785,
|
3 |
+
"best_model_checkpoint": "modernbert-medical-classifier/checkpoint-1748",
|
4 |
+
"epoch": 19.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 1748,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
281 |
"eval_samples_per_second": 12.552,
|
282 |
"eval_steps_per_second": 3.138,
|
283 |
"step": 1656
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 18.47826086956522,
|
287 |
+
"grad_norm": 0.0006457903073169291,
|
288 |
+
"learning_rate": 5.797101449275363e-06,
|
289 |
+
"loss": 0.0479,
|
290 |
+
"step": 1700
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 19.0,
|
294 |
+
"eval_f1": 0.6820012787723785,
|
295 |
+
"eval_loss": 3.2783100605010986,
|
296 |
+
"eval_runtime": 7.3182,
|
297 |
+
"eval_samples_per_second": 12.571,
|
298 |
+
"eval_steps_per_second": 3.143,
|
299 |
+
"step": 1748
|
300 |
}
|
301 |
],
|
302 |
"logging_steps": 100,
|
|
|
316 |
"attributes": {}
|
317 |
}
|
318 |
},
|
319 |
+
"total_flos": 1.2000483041742e+16,
|
320 |
"train_batch_size": 4,
|
321 |
"trial_name": null,
|
322 |
"trial_params": null
|