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:e44c4cc80d2bce69e5bb5bb6579ac5587896d8260bf74776f08396df834f7ea8
|
| 3 |
size 80792096
|
trainer_log.jsonl
CHANGED
|
@@ -64,3 +64,14 @@
|
|
| 64 |
{"current_steps": 59, "total_steps": 125, "loss": 0.05, "lr": 6.384177557124247e-05, "epoch": 2.330864197530864, "percentage": 47.2, "elapsed_time": "0:26:03", "remaining_time": "0:29:09"}
|
| 65 |
{"current_steps": 60, "total_steps": 125, "loss": 0.0737, "lr": 6.248882390836135e-05, "epoch": 2.3703703703703702, "percentage": 48.0, "elapsed_time": "0:26:27", "remaining_time": "0:28:39"}
|
| 66 |
{"current_steps": 60, "total_steps": 125, "eval_loss": 0.06489859521389008, "epoch": 2.3703703703703702, "percentage": 48.0, "elapsed_time": "0:26:49", "remaining_time": "0:29:03"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 64 |
{"current_steps": 59, "total_steps": 125, "loss": 0.05, "lr": 6.384177557124247e-05, "epoch": 2.330864197530864, "percentage": 47.2, "elapsed_time": "0:26:03", "remaining_time": "0:29:09"}
|
| 65 |
{"current_steps": 60, "total_steps": 125, "loss": 0.0737, "lr": 6.248882390836135e-05, "epoch": 2.3703703703703702, "percentage": 48.0, "elapsed_time": "0:26:27", "remaining_time": "0:28:39"}
|
| 66 |
{"current_steps": 60, "total_steps": 125, "eval_loss": 0.06489859521389008, "epoch": 2.3703703703703702, "percentage": 48.0, "elapsed_time": "0:26:49", "remaining_time": "0:29:03"}
|
| 67 |
+
{"current_steps": 61, "total_steps": 125, "loss": 0.0675, "lr": 6.112604669781572e-05, "epoch": 2.4098765432098768, "percentage": 48.8, "elapsed_time": "0:27:16", "remaining_time": "0:28:37"}
|
| 68 |
+
{"current_steps": 62, "total_steps": 125, "loss": 0.0524, "lr": 5.9754516100806423e-05, "epoch": 2.449382716049383, "percentage": 49.6, "elapsed_time": "0:27:42", "remaining_time": "0:28:09"}
|
| 69 |
+
{"current_steps": 63, "total_steps": 125, "loss": 0.0386, "lr": 5.837531116523682e-05, "epoch": 2.488888888888889, "percentage": 50.4, "elapsed_time": "0:28:06", "remaining_time": "0:27:39"}
|
| 70 |
+
{"current_steps": 64, "total_steps": 125, "loss": 0.067, "lr": 5.698951697677498e-05, "epoch": 2.528395061728395, "percentage": 51.2, "elapsed_time": "0:28:31", "remaining_time": "0:27:11"}
|
| 71 |
+
{"current_steps": 65, "total_steps": 125, "loss": 0.1527, "lr": 5.559822380516539e-05, "epoch": 2.567901234567901, "percentage": 52.0, "elapsed_time": "0:28:55", "remaining_time": "0:26:42"}
|
| 72 |
+
{"current_steps": 66, "total_steps": 125, "loss": 0.0437, "lr": 5.420252624646238e-05, "epoch": 2.6074074074074076, "percentage": 52.8, "elapsed_time": "0:29:18", "remaining_time": "0:26:12"}
|
| 73 |
+
{"current_steps": 67, "total_steps": 125, "loss": 0.1072, "lr": 5.2803522361859594e-05, "epoch": 2.6469135802469137, "percentage": 53.6, "elapsed_time": "0:29:41", "remaining_time": "0:25:42"}
|
| 74 |
+
{"current_steps": 68, "total_steps": 125, "loss": 0.0894, "lr": 5.140231281379345e-05, "epoch": 2.68641975308642, "percentage": 54.4, "elapsed_time": "0:30:06", "remaining_time": "0:25:14"}
|
| 75 |
+
{"current_steps": 69, "total_steps": 125, "loss": 0.1327, "lr": 5e-05, "epoch": 2.725925925925926, "percentage": 55.2, "elapsed_time": "0:30:30", "remaining_time": "0:24:45"}
|
| 76 |
+
{"current_steps": 70, "total_steps": 125, "loss": 0.1055, "lr": 4.859768718620656e-05, "epoch": 2.765432098765432, "percentage": 56.0, "elapsed_time": "0:30:55", "remaining_time": "0:24:17"}
|
| 77 |
+
{"current_steps": 70, "total_steps": 125, "eval_loss": 0.06331419944763184, "epoch": 2.765432098765432, "percentage": 56.0, "elapsed_time": "0:31:17", "remaining_time": "0:24:34"}
|