Training in progress, epoch 15, 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 598439784
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18d6f02ce80cc4da6ff5dc5d729a22ffa9bbadd92d73c483add17bfa6d1a6124
|
| 3 |
size 598439784
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1196967418
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:769f7d258ccb85a2e7803b7507a411edf5732fe2da0915d07e26c7f6f5b4ae64
|
| 3 |
size 1196967418
|
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 sha256:0d7793d0691719328c173827f0542bcfde3dd39ca36616559c39213d0dbbfb87
|
| 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:b604cae0dd7b3123ee29a4c730cc8b904cfff86463b91424f3f841bb58fa2dcd
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.8181082820112143,
|
| 3 |
"best_model_checkpoint": "modernbert-medical-classifier/checkpoint-1196",
|
| 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,
|
|
@@ -217,6 +217,22 @@
|
|
| 217 |
"eval_samples_per_second": 12.703,
|
| 218 |
"eval_steps_per_second": 3.176,
|
| 219 |
"step": 1288
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 220 |
}
|
| 221 |
],
|
| 222 |
"logging_steps": 100,
|
|
@@ -236,7 +252,7 @@
|
|
| 236 |
"attributes": {}
|
| 237 |
}
|
| 238 |
},
|
| 239 |
-
"total_flos":
|
| 240 |
"train_batch_size": 4,
|
| 241 |
"trial_name": null,
|
| 242 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.8181082820112143,
|
| 3 |
"best_model_checkpoint": "modernbert-medical-classifier/checkpoint-1196",
|
| 4 |
+
"epoch": 15.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1380,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 217 |
"eval_samples_per_second": 12.703,
|
| 218 |
"eval_steps_per_second": 3.176,
|
| 219 |
"step": 1288
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 14.130434782608695,
|
| 223 |
+
"grad_norm": 0.04395654425024986,
|
| 224 |
+
"learning_rate": 2.173913043478261e-05,
|
| 225 |
+
"loss": 0.1728,
|
| 226 |
+
"step": 1300
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 15.0,
|
| 230 |
+
"eval_f1": 0.7634584417193113,
|
| 231 |
+
"eval_loss": 1.518917202949524,
|
| 232 |
+
"eval_runtime": 7.2313,
|
| 233 |
+
"eval_samples_per_second": 12.722,
|
| 234 |
+
"eval_steps_per_second": 3.181,
|
| 235 |
+
"step": 1380
|
| 236 |
}
|
| 237 |
],
|
| 238 |
"logging_steps": 100,
|
|
|
|
| 252 |
"attributes": {}
|
| 253 |
}
|
| 254 |
},
|
| 255 |
+
"total_flos": 9473999878980000.0,
|
| 256 |
"train_batch_size": 4,
|
| 257 |
"trial_name": null,
|
| 258 |
"trial_params": null
|