Training in progress, epoch 2
Browse files
model-00001-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4938985352
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd87545dcb1f4724762ff563e1a43176a134265d4e05e7cc9527901efde54cfb
|
| 3 |
size 4938985352
|
model-00002-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4947390880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81c31fa938a369c2c865ec780eb7286e4446aae2a25781e3083ca5207ecce180
|
| 3 |
size 4947390880
|
model-00003-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3590488816
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4463a0daaf5486941ca8d07af558578b0ec6557f04a30ae5a3f0f2915371671
|
| 3 |
size 3590488816
|
trainer_log.jsonl
CHANGED
|
@@ -16,3 +16,12 @@
|
|
| 16 |
{"current_steps": 150, "total_steps": 237, "loss": 0.4852, "lr": 5e-06, "epoch": 1.8779342723004695, "percentage": 63.29, "elapsed_time": "2:18:38", "remaining_time": "1:20:24"}
|
| 17 |
{"current_steps": 159, "total_steps": 237, "eval_loss": 0.49927353858947754, "epoch": 1.9906103286384975, "percentage": 67.09, "elapsed_time": "2:28:46", "remaining_time": "1:12:59"}
|
| 18 |
{"current_steps": 160, "total_steps": 237, "loss": 0.4861, "lr": 5e-06, "epoch": 2.003129890453834, "percentage": 67.51, "elapsed_time": "2:30:08", "remaining_time": "1:12:15"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
{"current_steps": 150, "total_steps": 237, "loss": 0.4852, "lr": 5e-06, "epoch": 1.8779342723004695, "percentage": 63.29, "elapsed_time": "2:18:38", "remaining_time": "1:20:24"}
|
| 17 |
{"current_steps": 159, "total_steps": 237, "eval_loss": 0.49927353858947754, "epoch": 1.9906103286384975, "percentage": 67.09, "elapsed_time": "2:28:46", "remaining_time": "1:12:59"}
|
| 18 |
{"current_steps": 160, "total_steps": 237, "loss": 0.4861, "lr": 5e-06, "epoch": 2.003129890453834, "percentage": 67.51, "elapsed_time": "2:30:08", "remaining_time": "1:12:15"}
|
| 19 |
+
{"current_steps": 170, "total_steps": 237, "loss": 0.4562, "lr": 5e-06, "epoch": 2.128325508607199, "percentage": 71.73, "elapsed_time": "2:39:15", "remaining_time": "1:02:45"}
|
| 20 |
+
{"current_steps": 180, "total_steps": 237, "loss": 0.4555, "lr": 5e-06, "epoch": 2.2535211267605635, "percentage": 75.95, "elapsed_time": "2:48:20", "remaining_time": "0:53:18"}
|
| 21 |
+
{"current_steps": 190, "total_steps": 237, "loss": 0.4537, "lr": 5e-06, "epoch": 2.378716744913928, "percentage": 80.17, "elapsed_time": "2:57:28", "remaining_time": "0:43:54"}
|
| 22 |
+
{"current_steps": 200, "total_steps": 237, "loss": 0.4522, "lr": 5e-06, "epoch": 2.5039123630672924, "percentage": 84.39, "elapsed_time": "3:06:34", "remaining_time": "0:34:30"}
|
| 23 |
+
{"current_steps": 210, "total_steps": 237, "loss": 0.4489, "lr": 5e-06, "epoch": 2.629107981220657, "percentage": 88.61, "elapsed_time": "3:15:41", "remaining_time": "0:25:09"}
|
| 24 |
+
{"current_steps": 220, "total_steps": 237, "loss": 0.4501, "lr": 5e-06, "epoch": 2.7543035993740217, "percentage": 92.83, "elapsed_time": "3:24:47", "remaining_time": "0:15:49"}
|
| 25 |
+
{"current_steps": 230, "total_steps": 237, "loss": 0.4499, "lr": 5e-06, "epoch": 2.8794992175273864, "percentage": 97.05, "elapsed_time": "3:33:52", "remaining_time": "0:06:30"}
|
| 26 |
+
{"current_steps": 237, "total_steps": 237, "eval_loss": 0.4867970049381256, "epoch": 2.967136150234742, "percentage": 100.0, "elapsed_time": "3:42:38", "remaining_time": "0:00:00"}
|
| 27 |
+
{"current_steps": 237, "total_steps": 237, "epoch": 2.967136150234742, "percentage": 100.0, "elapsed_time": "3:43:40", "remaining_time": "0:00:00"}
|