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 83945296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:454df03f4cb34c78e3e8a57972b12f5242035148578e02e8b7a51006c10c399f
|
| 3 |
size 83945296
|
trainer_log.jsonl
CHANGED
|
@@ -119,3 +119,14 @@
|
|
| 119 |
{"current_steps": 109, "total_steps": 125, "loss": 0.0643, "lr": 4.951556604879048e-06, "epoch": 4.306172839506173, "percentage": 87.2, "elapsed_time": "0:53:58", "remaining_time": "0:07:55"}
|
| 120 |
{"current_steps": 110, "total_steps": 125, "loss": 0.0352, "lr": 4.360836746934055e-06, "epoch": 4.345679012345679, "percentage": 88.0, "elapsed_time": "0:54:25", "remaining_time": "0:07:25"}
|
| 121 |
{"current_steps": 110, "total_steps": 125, "eval_loss": 0.0669243261218071, "epoch": 4.345679012345679, "percentage": 88.0, "elapsed_time": "0:54:46", "remaining_time": "0:07:28"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 119 |
{"current_steps": 109, "total_steps": 125, "loss": 0.0643, "lr": 4.951556604879048e-06, "epoch": 4.306172839506173, "percentage": 87.2, "elapsed_time": "0:53:58", "remaining_time": "0:07:55"}
|
| 120 |
{"current_steps": 110, "total_steps": 125, "loss": 0.0352, "lr": 4.360836746934055e-06, "epoch": 4.345679012345679, "percentage": 88.0, "elapsed_time": "0:54:25", "remaining_time": "0:07:25"}
|
| 121 |
{"current_steps": 110, "total_steps": 125, "eval_loss": 0.0669243261218071, "epoch": 4.345679012345679, "percentage": 88.0, "elapsed_time": "0:54:46", "remaining_time": "0:07:28"}
|
| 122 |
+
{"current_steps": 111, "total_steps": 125, "loss": 0.045, "lr": 3.8060233744356633e-06, "epoch": 4.385185185185185, "percentage": 88.8, "elapsed_time": "0:55:15", "remaining_time": "0:06:58"}
|
| 123 |
+
{"current_steps": 112, "total_steps": 125, "loss": 0.0592, "lr": 3.2875529852700147e-06, "epoch": 4.424691358024692, "percentage": 89.6, "elapsed_time": "0:55:43", "remaining_time": "0:06:28"}
|
| 124 |
+
{"current_steps": 113, "total_steps": 125, "loss": 0.0307, "lr": 2.8058334845816213e-06, "epoch": 4.4641975308641975, "percentage": 90.4, "elapsed_time": "0:56:05", "remaining_time": "0:05:57"}
|
| 125 |
+
{"current_steps": 114, "total_steps": 125, "loss": 0.0423, "lr": 2.361243863855184e-06, "epoch": 4.503703703703704, "percentage": 91.2, "elapsed_time": "0:56:30", "remaining_time": "0:05:27"}
|
| 126 |
+
{"current_steps": 115, "total_steps": 125, "loss": 0.03, "lr": 1.9541339027450256e-06, "epoch": 4.54320987654321, "percentage": 92.0, "elapsed_time": "0:56:56", "remaining_time": "0:04:57"}
|
| 127 |
+
{"current_steps": 116, "total_steps": 125, "loss": 0.0361, "lr": 1.584823893886933e-06, "epoch": 4.582716049382716, "percentage": 92.8, "elapsed_time": "0:57:23", "remaining_time": "0:04:27"}
|
| 128 |
+
{"current_steps": 117, "total_steps": 125, "loss": 0.0458, "lr": 1.2536043909088191e-06, "epoch": 4.622222222222222, "percentage": 93.6, "elapsed_time": "0:57:50", "remaining_time": "0:03:57"}
|
| 129 |
+
{"current_steps": 118, "total_steps": 125, "loss": 0.0538, "lr": 9.607359798384785e-07, "epoch": 4.661728395061728, "percentage": 94.4, "elapsed_time": "0:58:14", "remaining_time": "0:03:27"}
|
| 130 |
+
{"current_steps": 119, "total_steps": 125, "loss": 0.0635, "lr": 7.064490740882057e-07, "epoch": 4.701234567901235, "percentage": 95.2, "elapsed_time": "0:58:40", "remaining_time": "0:02:57"}
|
| 131 |
+
{"current_steps": 120, "total_steps": 125, "loss": 0.0603, "lr": 4.909437331777179e-07, "epoch": 4.7407407407407405, "percentage": 96.0, "elapsed_time": "0:59:10", "remaining_time": "0:02:27"}
|
| 132 |
+
{"current_steps": 120, "total_steps": 125, "eval_loss": 0.06684371829032898, "epoch": 4.7407407407407405, "percentage": 96.0, "elapsed_time": "0:59:31", "remaining_time": "0:02:28"}
|