Training in progress, step 120
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 sha256:6cacfdee2b006fa7e76d4a0588fb0e8fd4a1c737d1e6b0a4a58b7b948616279b
|
| 3 |
size 80792096
|
trainer_log.jsonl
CHANGED
|
@@ -119,3 +119,14 @@
|
|
| 119 |
{"current_steps": 109, "total_steps": 125, "loss": 0.1117, "lr": 4.951556604879048e-06, "epoch": 4.306172839506173, "percentage": 87.2, "elapsed_time": "0:49:51", "remaining_time": "0:07:19"}
|
| 120 |
{"current_steps": 110, "total_steps": 125, "loss": 0.0595, "lr": 4.360836746934055e-06, "epoch": 4.345679012345679, "percentage": 88.0, "elapsed_time": "0:50:16", "remaining_time": "0:06:51"}
|
| 121 |
{"current_steps": 110, "total_steps": 125, "eval_loss": 0.10285650938749313, "epoch": 4.345679012345679, "percentage": 88.0, "elapsed_time": "0:50:38", "remaining_time": "0:06:54"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 119 |
{"current_steps": 109, "total_steps": 125, "loss": 0.1117, "lr": 4.951556604879048e-06, "epoch": 4.306172839506173, "percentage": 87.2, "elapsed_time": "0:49:51", "remaining_time": "0:07:19"}
|
| 120 |
{"current_steps": 110, "total_steps": 125, "loss": 0.0595, "lr": 4.360836746934055e-06, "epoch": 4.345679012345679, "percentage": 88.0, "elapsed_time": "0:50:16", "remaining_time": "0:06:51"}
|
| 121 |
{"current_steps": 110, "total_steps": 125, "eval_loss": 0.10285650938749313, "epoch": 4.345679012345679, "percentage": 88.0, "elapsed_time": "0:50:38", "remaining_time": "0:06:54"}
|
| 122 |
+
{"current_steps": 111, "total_steps": 125, "loss": 0.0385, "lr": 3.8060233744356633e-06, "epoch": 4.385185185185185, "percentage": 88.8, "elapsed_time": "0:51:07", "remaining_time": "0:06:26"}
|
| 123 |
+
{"current_steps": 112, "total_steps": 125, "loss": 0.0541, "lr": 3.2875529852700147e-06, "epoch": 4.424691358024692, "percentage": 89.6, "elapsed_time": "0:51:33", "remaining_time": "0:05:59"}
|
| 124 |
+
{"current_steps": 113, "total_steps": 125, "loss": 0.0539, "lr": 2.8058334845816213e-06, "epoch": 4.4641975308641975, "percentage": 90.4, "elapsed_time": "0:51:58", "remaining_time": "0:05:31"}
|
| 125 |
+
{"current_steps": 114, "total_steps": 125, "loss": 0.0753, "lr": 2.361243863855184e-06, "epoch": 4.503703703703704, "percentage": 91.2, "elapsed_time": "0:52:23", "remaining_time": "0:05:03"}
|
| 126 |
+
{"current_steps": 115, "total_steps": 125, "loss": 0.0601, "lr": 1.9541339027450256e-06, "epoch": 4.54320987654321, "percentage": 92.0, "elapsed_time": "0:52:50", "remaining_time": "0:04:35"}
|
| 127 |
+
{"current_steps": 116, "total_steps": 125, "loss": 0.0924, "lr": 1.584823893886933e-06, "epoch": 4.582716049382716, "percentage": 92.8, "elapsed_time": "0:53:14", "remaining_time": "0:04:07"}
|
| 128 |
+
{"current_steps": 117, "total_steps": 125, "loss": 0.1117, "lr": 1.2536043909088191e-06, "epoch": 4.622222222222222, "percentage": 93.6, "elapsed_time": "0:53:36", "remaining_time": "0:03:39"}
|
| 129 |
+
{"current_steps": 118, "total_steps": 125, "loss": 0.0454, "lr": 9.607359798384785e-07, "epoch": 4.661728395061728, "percentage": 94.4, "elapsed_time": "0:54:01", "remaining_time": "0:03:12"}
|
| 130 |
+
{"current_steps": 119, "total_steps": 125, "loss": 0.0771, "lr": 7.064490740882057e-07, "epoch": 4.701234567901235, "percentage": 95.2, "elapsed_time": "0:54:24", "remaining_time": "0:02:44"}
|
| 131 |
+
{"current_steps": 120, "total_steps": 125, "loss": 0.1126, "lr": 4.909437331777179e-07, "epoch": 4.7407407407407405, "percentage": 96.0, "elapsed_time": "0:54:50", "remaining_time": "0:02:17"}
|
| 132 |
+
{"current_steps": 120, "total_steps": 125, "eval_loss": 0.1026734858751297, "epoch": 4.7407407407407405, "percentage": 96.0, "elapsed_time": "0:55:11", "remaining_time": "0:02:17"}
|