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 80792096
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38144148d2ded6167d7940765337cfb89d236d2d68da478e99f05a2cbdc3d0ae
|
| 3 |
size 80792096
|
trainer_log.jsonl
CHANGED
|
@@ -53,3 +53,14 @@
|
|
| 53 |
{"current_steps": 49, "total_steps": 125, "loss": 0.0197, "lr": 7.660160382576683e-05, "epoch": 1.9358024691358025, "percentage": 39.2, "elapsed_time": "0:34:34", "remaining_time": "0:53:37"}
|
| 54 |
{"current_steps": 50, "total_steps": 125, "loss": 0.0186, "lr": 7.540376726232648e-05, "epoch": 1.9753086419753085, "percentage": 40.0, "elapsed_time": "0:35:17", "remaining_time": "0:52:56"}
|
| 55 |
{"current_steps": 50, "total_steps": 125, "eval_loss": 0.02130674570798874, "epoch": 1.9753086419753085, "percentage": 40.0, "elapsed_time": "0:35:45", "remaining_time": "0:53:38"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
{"current_steps": 49, "total_steps": 125, "loss": 0.0197, "lr": 7.660160382576683e-05, "epoch": 1.9358024691358025, "percentage": 39.2, "elapsed_time": "0:34:34", "remaining_time": "0:53:37"}
|
| 54 |
{"current_steps": 50, "total_steps": 125, "loss": 0.0186, "lr": 7.540376726232648e-05, "epoch": 1.9753086419753085, "percentage": 40.0, "elapsed_time": "0:35:17", "remaining_time": "0:52:56"}
|
| 55 |
{"current_steps": 50, "total_steps": 125, "eval_loss": 0.02130674570798874, "epoch": 1.9753086419753085, "percentage": 40.0, "elapsed_time": "0:35:45", "remaining_time": "0:53:38"}
|
| 56 |
+
{"current_steps": 51, "total_steps": 125, "loss": 0.0359, "lr": 7.4185944355262e-05, "epoch": 2.0148148148148146, "percentage": 40.8, "elapsed_time": "0:36:25", "remaining_time": "0:52:50"}
|
| 57 |
+
{"current_steps": 52, "total_steps": 125, "loss": 0.0188, "lr": 7.294909322337689e-05, "epoch": 2.054320987654321, "percentage": 41.6, "elapsed_time": "0:37:02", "remaining_time": "0:52:00"}
|
| 58 |
+
{"current_steps": 53, "total_steps": 125, "loss": 0.0161, "lr": 7.169418695587791e-05, "epoch": 2.093827160493827, "percentage": 42.4, "elapsed_time": "0:37:40", "remaining_time": "0:51:10"}
|
| 59 |
+
{"current_steps": 54, "total_steps": 125, "loss": 0.0178, "lr": 7.042221284679982e-05, "epoch": 2.1333333333333333, "percentage": 43.2, "elapsed_time": "0:38:20", "remaining_time": "0:50:24"}
|
| 60 |
+
{"current_steps": 55, "total_steps": 125, "loss": 0.0138, "lr": 6.91341716182545e-05, "epoch": 2.1728395061728394, "percentage": 44.0, "elapsed_time": "0:38:54", "remaining_time": "0:49:31"}
|
| 61 |
+
{"current_steps": 56, "total_steps": 125, "loss": 0.0159, "lr": 6.783107663311565e-05, "epoch": 2.212345679012346, "percentage": 44.8, "elapsed_time": "0:39:50", "remaining_time": "0:49:05"}
|
| 62 |
+
{"current_steps": 57, "total_steps": 125, "loss": 0.0203, "lr": 6.651395309775837e-05, "epoch": 2.251851851851852, "percentage": 45.6, "elapsed_time": "0:40:41", "remaining_time": "0:48:32"}
|
| 63 |
+
{"current_steps": 58, "total_steps": 125, "loss": 0.0183, "lr": 6.518383725548074e-05, "epoch": 2.291358024691358, "percentage": 46.4, "elapsed_time": "0:41:14", "remaining_time": "0:47:38"}
|
| 64 |
+
{"current_steps": 59, "total_steps": 125, "loss": 0.0218, "lr": 6.384177557124247e-05, "epoch": 2.330864197530864, "percentage": 47.2, "elapsed_time": "0:41:52", "remaining_time": "0:46:50"}
|
| 65 |
+
{"current_steps": 60, "total_steps": 125, "loss": 0.0165, "lr": 6.248882390836135e-05, "epoch": 2.3703703703703702, "percentage": 48.0, "elapsed_time": "0:42:25", "remaining_time": "0:45:57"}
|
| 66 |
+
{"current_steps": 60, "total_steps": 125, "eval_loss": 0.020269988104701042, "epoch": 2.3703703703703702, "percentage": 48.0, "elapsed_time": "0:42:53", "remaining_time": "0:46:28"}
|