Training in progress, step 70
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 sha256:3dad60f6a0a145646d41a938f3b8f8ab3a870112053b1306d4440a81fa346e05
|
| 3 |
size 80792096
|
trainer_log.jsonl
CHANGED
|
@@ -64,3 +64,14 @@
|
|
| 64 |
{"current_steps": 59, "total_steps": 125, "loss": 0.0194, "lr": 6.384177557124247e-05, "epoch": 2.330864197530864, "percentage": 47.2, "elapsed_time": "0:38:52", "remaining_time": "0:43:28"}
|
| 65 |
{"current_steps": 60, "total_steps": 125, "loss": 0.0193, "lr": 6.248882390836135e-05, "epoch": 2.3703703703703702, "percentage": 48.0, "elapsed_time": "0:39:25", "remaining_time": "0:42:42"}
|
| 66 |
{"current_steps": 60, "total_steps": 125, "eval_loss": 0.02047140523791313, "epoch": 2.3703703703703702, "percentage": 48.0, "elapsed_time": "0:39:52", "remaining_time": "0:43:11"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 64 |
{"current_steps": 59, "total_steps": 125, "loss": 0.0194, "lr": 6.384177557124247e-05, "epoch": 2.330864197530864, "percentage": 47.2, "elapsed_time": "0:38:52", "remaining_time": "0:43:28"}
|
| 65 |
{"current_steps": 60, "total_steps": 125, "loss": 0.0193, "lr": 6.248882390836135e-05, "epoch": 2.3703703703703702, "percentage": 48.0, "elapsed_time": "0:39:25", "remaining_time": "0:42:42"}
|
| 66 |
{"current_steps": 60, "total_steps": 125, "eval_loss": 0.02047140523791313, "epoch": 2.3703703703703702, "percentage": 48.0, "elapsed_time": "0:39:52", "remaining_time": "0:43:11"}
|
| 67 |
+
{"current_steps": 61, "total_steps": 125, "loss": 0.0147, "lr": 6.112604669781572e-05, "epoch": 2.4098765432098768, "percentage": 48.8, "elapsed_time": "0:40:28", "remaining_time": "0:42:28"}
|
| 68 |
+
{"current_steps": 62, "total_steps": 125, "loss": 0.0166, "lr": 5.9754516100806423e-05, "epoch": 2.449382716049383, "percentage": 49.6, "elapsed_time": "0:41:01", "remaining_time": "0:41:41"}
|
| 69 |
+
{"current_steps": 63, "total_steps": 125, "loss": 0.0135, "lr": 5.837531116523682e-05, "epoch": 2.488888888888889, "percentage": 50.4, "elapsed_time": "0:41:35", "remaining_time": "0:40:56"}
|
| 70 |
+
{"current_steps": 64, "total_steps": 125, "loss": 0.02, "lr": 5.698951697677498e-05, "epoch": 2.528395061728395, "percentage": 51.2, "elapsed_time": "0:42:07", "remaining_time": "0:40:08"}
|
| 71 |
+
{"current_steps": 65, "total_steps": 125, "loss": 0.0175, "lr": 5.559822380516539e-05, "epoch": 2.567901234567901, "percentage": 52.0, "elapsed_time": "0:42:47", "remaining_time": "0:39:30"}
|
| 72 |
+
{"current_steps": 66, "total_steps": 125, "loss": 0.0159, "lr": 5.420252624646238e-05, "epoch": 2.6074074074074076, "percentage": 52.8, "elapsed_time": "0:43:27", "remaining_time": "0:38:50"}
|
| 73 |
+
{"current_steps": 67, "total_steps": 125, "loss": 0.0177, "lr": 5.2803522361859594e-05, "epoch": 2.6469135802469137, "percentage": 53.6, "elapsed_time": "0:44:15", "remaining_time": "0:38:18"}
|
| 74 |
+
{"current_steps": 68, "total_steps": 125, "loss": 0.0169, "lr": 5.140231281379345e-05, "epoch": 2.68641975308642, "percentage": 54.4, "elapsed_time": "0:45:08", "remaining_time": "0:37:50"}
|
| 75 |
+
{"current_steps": 69, "total_steps": 125, "loss": 0.0136, "lr": 5e-05, "epoch": 2.725925925925926, "percentage": 55.2, "elapsed_time": "0:45:42", "remaining_time": "0:37:05"}
|
| 76 |
+
{"current_steps": 70, "total_steps": 125, "loss": 0.0151, "lr": 4.859768718620656e-05, "epoch": 2.765432098765432, "percentage": 56.0, "elapsed_time": "0:46:17", "remaining_time": "0:36:22"}
|
| 77 |
+
{"current_steps": 70, "total_steps": 125, "eval_loss": 0.01994810812175274, "epoch": 2.765432098765432, "percentage": 56.0, "elapsed_time": "0:46:45", "remaining_time": "0:36:44"}
|