BayesTensor
commited on
Training in progress, epoch 10, 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 sha256:9664ff48de2c2e6c9ca3642b524d3308178c1945fc8aab8a3eab01731d2730f6
|
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 sha256:16b8332f41ae3acd6c91294995f037ced886eb9ddfa7c184941e4ab892a2cc3c
|
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 sha256:9afbf853352cfbcfea61884ff6a2ddcd2aee1ce8618589cf5b56912c1b160011
|
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 sha256:68fdc733a943ea0ce7bcbe589b5f3b75914e40153fa8062399cf2cf49a1d80de
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.6268890955591723,
|
3 |
"best_model_checkpoint": "modernbert-medical-classifier/checkpoint-644",
|
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,
|
@@ -144,6 +144,22 @@
|
|
144 |
"eval_samples_per_second": 12.622,
|
145 |
"eval_steps_per_second": 3.155,
|
146 |
"step": 828
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
147 |
}
|
148 |
],
|
149 |
"logging_steps": 100,
|
@@ -163,7 +179,7 @@
|
|
163 |
"attributes": {}
|
164 |
}
|
165 |
},
|
166 |
-
"total_flos":
|
167 |
"train_batch_size": 4,
|
168 |
"trial_name": null,
|
169 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.6268890955591723,
|
3 |
"best_model_checkpoint": "modernbert-medical-classifier/checkpoint-644",
|
4 |
+
"epoch": 10.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 920,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
144 |
"eval_samples_per_second": 12.622,
|
145 |
"eval_steps_per_second": 3.155,
|
146 |
"step": 828
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 9.782608695652174,
|
150 |
+
"grad_norm": 5.040703296661377,
|
151 |
+
"learning_rate": 1.352657004830918e-05,
|
152 |
+
"loss": 0.6745,
|
153 |
+
"step": 900
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 10.0,
|
157 |
+
"eval_f1": 0.6229138501039525,
|
158 |
+
"eval_loss": 1.4749873876571655,
|
159 |
+
"eval_runtime": 7.3224,
|
160 |
+
"eval_samples_per_second": 12.564,
|
161 |
+
"eval_steps_per_second": 3.141,
|
162 |
+
"step": 920
|
163 |
}
|
164 |
],
|
165 |
"logging_steps": 100,
|
|
|
179 |
"attributes": {}
|
180 |
}
|
181 |
},
|
182 |
+
"total_flos": 6316043706180000.0,
|
183 |
"train_batch_size": 4,
|
184 |
"trial_name": null,
|
185 |
"trial_params": null
|