Training in progress, step 60
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +11 -0
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 83945296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:306da9e618b125071f1c0f30ad15bb43d7dfd0c21b124c364d9d7f4f10f2dce5
|
| 3 |
size 83945296
|
trainer_log.jsonl
CHANGED
|
@@ -53,3 +53,14 @@
|
|
| 53 |
{"current_steps": 49, "total_steps": 125, "loss": 0.1078, "lr": 7.660160382576683e-05, "epoch": 1.9358024691358025, "percentage": 39.2, "elapsed_time": "0:21:58", "remaining_time": "0:34:04"}
|
| 54 |
{"current_steps": 50, "total_steps": 125, "loss": 0.0999, "lr": 7.540376726232648e-05, "epoch": 1.9753086419753085, "percentage": 40.0, "elapsed_time": "0:22:23", "remaining_time": "0:33:35"}
|
| 55 |
{"current_steps": 50, "total_steps": 125, "eval_loss": 0.15381264686584473, "epoch": 1.9753086419753085, "percentage": 40.0, "elapsed_time": "0:22:45", "remaining_time": "0:34:07"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
{"current_steps": 49, "total_steps": 125, "loss": 0.1078, "lr": 7.660160382576683e-05, "epoch": 1.9358024691358025, "percentage": 39.2, "elapsed_time": "0:21:58", "remaining_time": "0:34:04"}
|
| 54 |
{"current_steps": 50, "total_steps": 125, "loss": 0.0999, "lr": 7.540376726232648e-05, "epoch": 1.9753086419753085, "percentage": 40.0, "elapsed_time": "0:22:23", "remaining_time": "0:33:35"}
|
| 55 |
{"current_steps": 50, "total_steps": 125, "eval_loss": 0.15381264686584473, "epoch": 1.9753086419753085, "percentage": 40.0, "elapsed_time": "0:22:45", "remaining_time": "0:34:07"}
|
| 56 |
+
{"current_steps": 51, "total_steps": 125, "loss": 0.2619, "lr": 7.4185944355262e-05, "epoch": 2.0148148148148146, "percentage": 40.8, "elapsed_time": "0:23:13", "remaining_time": "0:33:41"}
|
| 57 |
+
{"current_steps": 52, "total_steps": 125, "loss": 0.1388, "lr": 7.294909322337689e-05, "epoch": 2.054320987654321, "percentage": 41.6, "elapsed_time": "0:23:37", "remaining_time": "0:33:10"}
|
| 58 |
+
{"current_steps": 53, "total_steps": 125, "loss": 0.1172, "lr": 7.169418695587791e-05, "epoch": 2.093827160493827, "percentage": 42.4, "elapsed_time": "0:24:02", "remaining_time": "0:32:39"}
|
| 59 |
+
{"current_steps": 54, "total_steps": 125, "loss": 0.1775, "lr": 7.042221284679982e-05, "epoch": 2.1333333333333333, "percentage": 43.2, "elapsed_time": "0:24:30", "remaining_time": "0:32:13"}
|
| 60 |
+
{"current_steps": 55, "total_steps": 125, "loss": 0.0988, "lr": 6.91341716182545e-05, "epoch": 2.1728395061728394, "percentage": 44.0, "elapsed_time": "0:24:57", "remaining_time": "0:31:45"}
|
| 61 |
+
{"current_steps": 56, "total_steps": 125, "loss": 0.0882, "lr": 6.783107663311565e-05, "epoch": 2.212345679012346, "percentage": 44.8, "elapsed_time": "0:25:23", "remaining_time": "0:31:17"}
|
| 62 |
+
{"current_steps": 57, "total_steps": 125, "loss": 0.1304, "lr": 6.651395309775837e-05, "epoch": 2.251851851851852, "percentage": 45.6, "elapsed_time": "0:25:54", "remaining_time": "0:30:54"}
|
| 63 |
+
{"current_steps": 58, "total_steps": 125, "loss": 0.1219, "lr": 6.518383725548074e-05, "epoch": 2.291358024691358, "percentage": 46.4, "elapsed_time": "0:26:21", "remaining_time": "0:30:26"}
|
| 64 |
+
{"current_steps": 59, "total_steps": 125, "loss": 0.1535, "lr": 6.384177557124247e-05, "epoch": 2.330864197530864, "percentage": 47.2, "elapsed_time": "0:26:44", "remaining_time": "0:29:54"}
|
| 65 |
+
{"current_steps": 60, "total_steps": 125, "loss": 0.0806, "lr": 6.248882390836135e-05, "epoch": 2.3703703703703702, "percentage": 48.0, "elapsed_time": "0:27:06", "remaining_time": "0:29:21"}
|
| 66 |
+
{"current_steps": 60, "total_steps": 125, "eval_loss": 0.14715269207954407, "epoch": 2.3703703703703702, "percentage": 48.0, "elapsed_time": "0:27:28", "remaining_time": "0:29:45"}
|