Training in progress, step 110
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:b5c0f492aa8a780a1d8f440624f0f2ae9a28d152be38363749c60d81548a1120
|
| 3 |
size 83945296
|
trainer_log.jsonl
CHANGED
|
@@ -108,3 +108,14 @@
|
|
| 108 |
{"current_steps": 99, "total_steps": 125, "loss": 0.0466, "lr": 1.2717891755841722e-05, "epoch": 3.911111111111111, "percentage": 79.2, "elapsed_time": "0:51:49", "remaining_time": "0:13:36"}
|
| 109 |
{"current_steps": 100, "total_steps": 125, "loss": 0.0473, "lr": 1.1798131208919627e-05, "epoch": 3.950617283950617, "percentage": 80.0, "elapsed_time": "0:52:15", "remaining_time": "0:13:03"}
|
| 110 |
{"current_steps": 100, "total_steps": 125, "eval_loss": 0.0731634795665741, "epoch": 3.950617283950617, "percentage": 80.0, "elapsed_time": "0:52:38", "remaining_time": "0:13:09"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 108 |
{"current_steps": 99, "total_steps": 125, "loss": 0.0466, "lr": 1.2717891755841722e-05, "epoch": 3.911111111111111, "percentage": 79.2, "elapsed_time": "0:51:49", "remaining_time": "0:13:36"}
|
| 109 |
{"current_steps": 100, "total_steps": 125, "loss": 0.0473, "lr": 1.1798131208919627e-05, "epoch": 3.950617283950617, "percentage": 80.0, "elapsed_time": "0:52:15", "remaining_time": "0:13:03"}
|
| 110 |
{"current_steps": 100, "total_steps": 125, "eval_loss": 0.0731634795665741, "epoch": 3.950617283950617, "percentage": 80.0, "elapsed_time": "0:52:38", "remaining_time": "0:13:09"}
|
| 111 |
+
{"current_steps": 101, "total_steps": 125, "loss": 0.0788, "lr": 1.090842587659851e-05, "epoch": 3.9901234567901236, "percentage": 80.8, "elapsed_time": "0:53:13", "remaining_time": "0:12:38"}
|
| 112 |
+
{"current_steps": 102, "total_steps": 125, "loss": 0.0921, "lr": 1.004947573208756e-05, "epoch": 4.029629629629629, "percentage": 81.6, "elapsed_time": "0:53:49", "remaining_time": "0:12:08"}
|
| 113 |
+
{"current_steps": 103, "total_steps": 125, "loss": 0.0374, "lr": 9.221956552036992e-06, "epoch": 4.069135802469136, "percentage": 82.4, "elapsed_time": "0:54:17", "remaining_time": "0:11:35"}
|
| 114 |
+
{"current_steps": 104, "total_steps": 125, "loss": 0.0405, "lr": 8.426519384872733e-06, "epoch": 4.108641975308642, "percentage": 83.2, "elapsed_time": "0:54:48", "remaining_time": "0:11:04"}
|
| 115 |
+
{"current_steps": 105, "total_steps": 125, "loss": 0.0315, "lr": 7.663790038585793e-06, "epoch": 4.148148148148148, "percentage": 84.0, "elapsed_time": "0:55:19", "remaining_time": "0:10:32"}
|
| 116 |
+
{"current_steps": 106, "total_steps": 125, "loss": 0.0287, "lr": 6.934368588379553e-06, "epoch": 4.187654320987654, "percentage": 84.8, "elapsed_time": "0:55:47", "remaining_time": "0:09:59"}
|
| 117 |
+
{"current_steps": 107, "total_steps": 125, "loss": 0.024, "lr": 6.238828904562316e-06, "epoch": 4.22716049382716, "percentage": 85.6, "elapsed_time": "0:56:15", "remaining_time": "0:09:27"}
|
| 118 |
+
{"current_steps": 108, "total_steps": 125, "loss": 0.042, "lr": 5.577718201056392e-06, "epoch": 4.266666666666667, "percentage": 86.4, "elapsed_time": "0:56:41", "remaining_time": "0:08:55"}
|
| 119 |
+
{"current_steps": 109, "total_steps": 125, "loss": 0.0508, "lr": 4.951556604879048e-06, "epoch": 4.306172839506173, "percentage": 87.2, "elapsed_time": "0:57:19", "remaining_time": "0:08:24"}
|
| 120 |
+
{"current_steps": 110, "total_steps": 125, "loss": 0.0282, "lr": 4.360836746934055e-06, "epoch": 4.345679012345679, "percentage": 88.0, "elapsed_time": "0:57:48", "remaining_time": "0:07:52"}
|
| 121 |
+
{"current_steps": 110, "total_steps": 125, "eval_loss": 0.07286052405834198, "epoch": 4.345679012345679, "percentage": 88.0, "elapsed_time": "0:58:10", "remaining_time": "0:07:55"}
|