BayesTensor
commited on
Training in progress, epoch 2, 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 sha256:48deb9d50108a5e0b39844e65a5b8a35900a15e538d0bca0246c92e20eb8f3b3
|
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 sha256:56f44df2ce15e645a446644126bccd6f675b59d2bbbb924f8c3d372560683475
|
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 sha256:8d138cfe3a4adf21f048848ee35837c9a757a0a3616ff7adbb45b69aac247435
|
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:b0583b378b8c26d5f7f023d50a449b521e770802231ce3bd6f38e066ed663c29
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.2555762427123016,
|
3 |
"best_model_checkpoint": "modernbert-medical-classifier/checkpoint-92",
|
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,
|
@@ -16,6 +16,22 @@
|
|
16 |
"eval_samples_per_second": 12.619,
|
17 |
"eval_steps_per_second": 3.155,
|
18 |
"step": 92
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
}
|
20 |
],
|
21 |
"logging_steps": 100,
|
@@ -35,7 +51,7 @@
|
|
35 |
"attributes": {}
|
36 |
}
|
37 |
},
|
38 |
-
"total_flos":
|
39 |
"train_batch_size": 4,
|
40 |
"trial_name": null,
|
41 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.2555762427123016,
|
3 |
"best_model_checkpoint": "modernbert-medical-classifier/checkpoint-92",
|
4 |
+
"epoch": 2.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 184,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
16 |
"eval_samples_per_second": 12.619,
|
17 |
"eval_steps_per_second": 3.155,
|
18 |
"step": 92
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 1.0869565217391304,
|
22 |
+
"grad_norm": 27.595176696777344,
|
23 |
+
"learning_rate": 8.695652173913044e-06,
|
24 |
+
"loss": 1.2432,
|
25 |
+
"step": 100
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"eval_f1": 0.22693092661056924,
|
30 |
+
"eval_loss": 1.1348090171813965,
|
31 |
+
"eval_runtime": 7.2682,
|
32 |
+
"eval_samples_per_second": 12.658,
|
33 |
+
"eval_steps_per_second": 3.164,
|
34 |
+
"step": 184
|
35 |
}
|
36 |
],
|
37 |
"logging_steps": 100,
|
|
|
51 |
"attributes": {}
|
52 |
}
|
53 |
},
|
54 |
+
"total_flos": 1263208741236000.0,
|
55 |
"train_batch_size": 4,
|
56 |
"trial_name": null,
|
57 |
"trial_params": null
|