Training in progress, epoch 3, 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 737722356
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:580d8e77c729fb4984bb9c9f51741452e2c136d0b60a11bba8b9f64157672a12
|
3 |
size 737722356
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1475564538
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:147b8b3258a91181e6bb5318fa147074f926aa9b71090481f152f0ad3e713204
|
3 |
size 1475564538
|
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:d6a056d1576b9dd130e0a0e9c22395f596c7172e1bbcd7620c2ad7b8513a2fc3
|
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:c742a8bcd183a765dd0e9c362a3881e8009e8d1f29a5268e888484a18d7415ea
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.2747629944426283,
|
3 |
"best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-366",
|
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,
|
@@ -46,6 +46,29 @@
|
|
46 |
"eval_samples_per_second": 7.044,
|
47 |
"eval_steps_per_second": 3.522,
|
48 |
"step": 366
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
49 |
}
|
50 |
],
|
51 |
"logging_steps": 100,
|
@@ -65,7 +88,7 @@
|
|
65 |
"attributes": {}
|
66 |
}
|
67 |
},
|
68 |
-
"total_flos":
|
69 |
"train_batch_size": 2,
|
70 |
"trial_name": null,
|
71 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.2747629944426283,
|
3 |
"best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-366",
|
4 |
+
"epoch": 3.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 549,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
46 |
"eval_samples_per_second": 7.044,
|
47 |
"eval_steps_per_second": 3.522,
|
48 |
"step": 366
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 2.185792349726776,
|
52 |
+
"grad_norm": 2.9179580211639404,
|
53 |
+
"learning_rate": 4.562841530054645e-05,
|
54 |
+
"loss": 1.077,
|
55 |
+
"step": 400
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 2.73224043715847,
|
59 |
+
"grad_norm": 2.744880199432373,
|
60 |
+
"learning_rate": 4.453551912568306e-05,
|
61 |
+
"loss": 1.086,
|
62 |
+
"step": 500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 3.0,
|
66 |
+
"eval_f1": 0.2747629944426283,
|
67 |
+
"eval_loss": 1.1455310583114624,
|
68 |
+
"eval_runtime": 13.0518,
|
69 |
+
"eval_samples_per_second": 7.049,
|
70 |
+
"eval_steps_per_second": 3.524,
|
71 |
+
"step": 549
|
72 |
}
|
73 |
],
|
74 |
"logging_steps": 100,
|
|
|
88 |
"attributes": {}
|
89 |
}
|
90 |
},
|
91 |
+
"total_flos": 1463080730670000.0,
|
92 |
"train_batch_size": 2,
|
93 |
"trial_name": null,
|
94 |
"trial_params": null
|