Training in progress, step 80
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:e079e31e339b4873e19e491cd5d661d4a12e530241c39498351ec5df4beac880
|
| 3 |
size 80792096
|
trainer_log.jsonl
CHANGED
|
@@ -75,3 +75,14 @@
|
|
| 75 |
{"current_steps": 69, "total_steps": 125, "loss": 0.02, "lr": 5e-05, "epoch": 2.725925925925926, "percentage": 55.2, "elapsed_time": "0:48:43", "remaining_time": "0:39:32"}
|
| 76 |
{"current_steps": 70, "total_steps": 125, "loss": 0.014, "lr": 4.859768718620656e-05, "epoch": 2.765432098765432, "percentage": 56.0, "elapsed_time": "0:49:19", "remaining_time": "0:38:45"}
|
| 77 |
{"current_steps": 70, "total_steps": 125, "eval_loss": 0.018982170149683952, "epoch": 2.765432098765432, "percentage": 56.0, "elapsed_time": "0:49:47", "remaining_time": "0:39:07"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 75 |
{"current_steps": 69, "total_steps": 125, "loss": 0.02, "lr": 5e-05, "epoch": 2.725925925925926, "percentage": 55.2, "elapsed_time": "0:48:43", "remaining_time": "0:39:32"}
|
| 76 |
{"current_steps": 70, "total_steps": 125, "loss": 0.014, "lr": 4.859768718620656e-05, "epoch": 2.765432098765432, "percentage": 56.0, "elapsed_time": "0:49:19", "remaining_time": "0:38:45"}
|
| 77 |
{"current_steps": 70, "total_steps": 125, "eval_loss": 0.018982170149683952, "epoch": 2.765432098765432, "percentage": 56.0, "elapsed_time": "0:49:47", "remaining_time": "0:39:07"}
|
| 78 |
+
{"current_steps": 71, "total_steps": 125, "loss": 0.0158, "lr": 4.7196477638140404e-05, "epoch": 2.8049382716049385, "percentage": 56.8, "elapsed_time": "0:50:34", "remaining_time": "0:38:27"}
|
| 79 |
+
{"current_steps": 72, "total_steps": 125, "loss": 0.0154, "lr": 4.579747375353763e-05, "epoch": 2.8444444444444446, "percentage": 57.6, "elapsed_time": "0:51:20", "remaining_time": "0:37:47"}
|
| 80 |
+
{"current_steps": 73, "total_steps": 125, "loss": 0.0112, "lr": 4.4401776194834613e-05, "epoch": 2.8839506172839506, "percentage": 58.4, "elapsed_time": "0:51:49", "remaining_time": "0:36:54"}
|
| 81 |
+
{"current_steps": 74, "total_steps": 125, "loss": 0.0206, "lr": 4.3010483023225045e-05, "epoch": 2.9234567901234567, "percentage": 59.2, "elapsed_time": "0:52:39", "remaining_time": "0:36:17"}
|
| 82 |
+
{"current_steps": 75, "total_steps": 125, "loss": 0.0177, "lr": 4.162468883476319e-05, "epoch": 2.962962962962963, "percentage": 60.0, "elapsed_time": "0:53:12", "remaining_time": "0:35:28"}
|
| 83 |
+
{"current_steps": 76, "total_steps": 125, "loss": 0.0256, "lr": 4.0245483899193595e-05, "epoch": 3.0024691358024693, "percentage": 60.8, "elapsed_time": "0:54:01", "remaining_time": "0:34:49"}
|
| 84 |
+
{"current_steps": 77, "total_steps": 125, "loss": 0.0142, "lr": 3.887395330218429e-05, "epoch": 3.0419753086419754, "percentage": 61.6, "elapsed_time": "0:54:46", "remaining_time": "0:34:08"}
|
| 85 |
+
{"current_steps": 78, "total_steps": 125, "loss": 0.0148, "lr": 3.7511176091638653e-05, "epoch": 3.0814814814814815, "percentage": 62.4, "elapsed_time": "0:55:43", "remaining_time": "0:33:34"}
|
| 86 |
+
{"current_steps": 79, "total_steps": 125, "loss": 0.0127, "lr": 3.6158224428757535e-05, "epoch": 3.1209876543209876, "percentage": 63.2, "elapsed_time": "0:56:24", "remaining_time": "0:32:50"}
|
| 87 |
+
{"current_steps": 80, "total_steps": 125, "loss": 0.0181, "lr": 3.4816162744519263e-05, "epoch": 3.1604938271604937, "percentage": 64.0, "elapsed_time": "0:57:02", "remaining_time": "0:32:05"}
|
| 88 |
+
{"current_steps": 80, "total_steps": 125, "eval_loss": 0.018312804400920868, "epoch": 3.1604938271604937, "percentage": 64.0, "elapsed_time": "0:57:30", "remaining_time": "0:32:20"}
|