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:dae5494464d2058407b119400d4d4250d78f0f5f9633a08ad5593a0553770405
|
| 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": "0:41:03", "remaining_time": "0:45:55"}
|
| 65 |
{"current_steps": 60, "total_steps": 125, "loss": 0.0168, "lr": 6.248882390836135e-05, "epoch": 2.3703703703703702, "percentage": 48.0, "elapsed_time": "0:41:33", "remaining_time": "0:45:01"}
|
| 66 |
{"current_steps": 60, "total_steps": 125, "eval_loss": 0.019772132858633995, "epoch": 2.3703703703703702, "percentage": 48.0, "elapsed_time": "0:41:59", "remaining_time": "0:45:29"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 64 |
{"current_steps": 59, "total_steps": 125, "loss": 0.0194, "lr": 6.384177557124247e-05, "epoch": 2.330864197530864, "percentage": 47.2, "elapsed_time": "0:41:03", "remaining_time": "0:45:55"}
|
| 65 |
{"current_steps": 60, "total_steps": 125, "loss": 0.0168, "lr": 6.248882390836135e-05, "epoch": 2.3703703703703702, "percentage": 48.0, "elapsed_time": "0:41:33", "remaining_time": "0:45:01"}
|
| 66 |
{"current_steps": 60, "total_steps": 125, "eval_loss": 0.019772132858633995, "epoch": 2.3703703703703702, "percentage": 48.0, "elapsed_time": "0:41:59", "remaining_time": "0:45:29"}
|
| 67 |
+
{"current_steps": 61, "total_steps": 125, "loss": 0.0175, "lr": 6.112604669781572e-05, "epoch": 2.4098765432098768, "percentage": 48.8, "elapsed_time": "0:42:39", "remaining_time": "0:44:45"}
|
| 68 |
+
{"current_steps": 62, "total_steps": 125, "loss": 0.0178, "lr": 5.9754516100806423e-05, "epoch": 2.449382716049383, "percentage": 49.6, "elapsed_time": "0:43:12", "remaining_time": "0:43:54"}
|
| 69 |
+
{"current_steps": 63, "total_steps": 125, "loss": 0.0222, "lr": 5.837531116523682e-05, "epoch": 2.488888888888889, "percentage": 50.4, "elapsed_time": "0:43:49", "remaining_time": "0:43:07"}
|
| 70 |
+
{"current_steps": 64, "total_steps": 125, "loss": 0.0146, "lr": 5.698951697677498e-05, "epoch": 2.528395061728395, "percentage": 51.2, "elapsed_time": "0:44:21", "remaining_time": "0:42:16"}
|
| 71 |
+
{"current_steps": 65, "total_steps": 125, "loss": 0.0143, "lr": 5.559822380516539e-05, "epoch": 2.567901234567901, "percentage": 52.0, "elapsed_time": "0:45:04", "remaining_time": "0:41:36"}
|
| 72 |
+
{"current_steps": 66, "total_steps": 125, "loss": 0.0184, "lr": 5.420252624646238e-05, "epoch": 2.6074074074074076, "percentage": 52.8, "elapsed_time": "0:45:48", "remaining_time": "0:40:56"}
|
| 73 |
+
{"current_steps": 67, "total_steps": 125, "loss": 0.0157, "lr": 5.2803522361859594e-05, "epoch": 2.6469135802469137, "percentage": 53.6, "elapsed_time": "0:46:25", "remaining_time": "0:40:10"}
|
| 74 |
+
{"current_steps": 68, "total_steps": 125, "loss": 0.0169, "lr": 5.140231281379345e-05, "epoch": 2.68641975308642, "percentage": 54.4, "elapsed_time": "0:47:00", "remaining_time": "0:39:24"}
|
| 75 |
+
{"current_steps": 69, "total_steps": 125, "loss": 0.0194, "lr": 5e-05, "epoch": 2.725925925925926, "percentage": 55.2, "elapsed_time": "0:47:34", "remaining_time": "0:38:37"}
|
| 76 |
+
{"current_steps": 70, "total_steps": 125, "loss": 0.0201, "lr": 4.859768718620656e-05, "epoch": 2.765432098765432, "percentage": 56.0, "elapsed_time": "0:48:10", "remaining_time": "0:37:50"}
|
| 77 |
+
{"current_steps": 70, "total_steps": 125, "eval_loss": 0.018415603786706924, "epoch": 2.765432098765432, "percentage": 56.0, "elapsed_time": "0:48:36", "remaining_time": "0:38:11"}
|