Training in progress, step 90
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +8 -0
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 819328
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e952b6567d9802f328dd88c96a6a2b494472b31f2aeeab6df917b59a7cf697a5
|
| 3 |
size 819328
|
trainer_log.jsonl
CHANGED
|
@@ -12,3 +12,11 @@
|
|
| 12 |
{"current_steps": 55, "total_steps": 900, "loss": 0.1915, "lr": 3e-05, "epoch": 0.6111111111111112, "percentage": 6.11, "elapsed_time": "0:00:13", "remaining_time": "0:03:25", "throughput": 1285.75, "total_tokens": 17184}
|
| 13 |
{"current_steps": 60, "total_steps": 900, "loss": 0.1305, "lr": 3.277777777777778e-05, "epoch": 0.6666666666666666, "percentage": 6.67, "elapsed_time": "0:00:14", "remaining_time": "0:03:19", "throughput": 1313.76, "total_tokens": 18752}
|
| 14 |
{"current_steps": 65, "total_steps": 900, "loss": 0.2508, "lr": 3.555555555555556e-05, "epoch": 0.7222222222222222, "percentage": 7.22, "elapsed_time": "0:00:15", "remaining_time": "0:03:15", "throughput": 1340.25, "total_tokens": 20352}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
{"current_steps": 55, "total_steps": 900, "loss": 0.1915, "lr": 3e-05, "epoch": 0.6111111111111112, "percentage": 6.11, "elapsed_time": "0:00:13", "remaining_time": "0:03:25", "throughput": 1285.75, "total_tokens": 17184}
|
| 13 |
{"current_steps": 60, "total_steps": 900, "loss": 0.1305, "lr": 3.277777777777778e-05, "epoch": 0.6666666666666666, "percentage": 6.67, "elapsed_time": "0:00:14", "remaining_time": "0:03:19", "throughput": 1313.76, "total_tokens": 18752}
|
| 14 |
{"current_steps": 65, "total_steps": 900, "loss": 0.2508, "lr": 3.555555555555556e-05, "epoch": 0.7222222222222222, "percentage": 7.22, "elapsed_time": "0:00:15", "remaining_time": "0:03:15", "throughput": 1340.25, "total_tokens": 20352}
|
| 15 |
+
{"current_steps": 70, "total_steps": 900, "loss": 0.0133, "lr": 3.8333333333333334e-05, "epoch": 0.7777777777777778, "percentage": 7.78, "elapsed_time": "0:00:16", "remaining_time": "0:03:10", "throughput": 1363.69, "total_tokens": 21952}
|
| 16 |
+
{"current_steps": 75, "total_steps": 900, "loss": 0.0971, "lr": 4.111111111111111e-05, "epoch": 0.8333333333333334, "percentage": 8.33, "elapsed_time": "0:00:17", "remaining_time": "0:03:07", "throughput": 1379.65, "total_tokens": 23456}
|
| 17 |
+
{"current_steps": 80, "total_steps": 900, "loss": 0.335, "lr": 4.388888888888889e-05, "epoch": 0.8888888888888888, "percentage": 8.89, "elapsed_time": "0:00:17", "remaining_time": "0:03:03", "throughput": 1398.1, "total_tokens": 25056}
|
| 18 |
+
{"current_steps": 85, "total_steps": 900, "loss": 0.0556, "lr": 4.666666666666667e-05, "epoch": 0.9444444444444444, "percentage": 9.44, "elapsed_time": "0:00:18", "remaining_time": "0:03:00", "throughput": 1410.88, "total_tokens": 26560}
|
| 19 |
+
{"current_steps": 90, "total_steps": 900, "loss": 0.2002, "lr": 4.9444444444444446e-05, "epoch": 1.0, "percentage": 10.0, "elapsed_time": "0:00:19", "remaining_time": "0:02:58", "throughput": 1420.38, "total_tokens": 28096}
|
| 20 |
+
{"current_steps": 90, "total_steps": 900, "eval_loss": 0.17683683335781097, "epoch": 1.0, "percentage": 10.0, "elapsed_time": "0:00:20", "remaining_time": "0:03:07", "throughput": 1350.39, "total_tokens": 28096}
|
| 21 |
+
{"current_steps": 95, "total_steps": 900, "loss": 0.1392, "lr": 4.9996991493233693e-05, "epoch": 1.0555555555555556, "percentage": 10.56, "elapsed_time": "0:00:22", "remaining_time": "0:03:14", "throughput": 1292.42, "total_tokens": 29696}
|
| 22 |
+
{"current_steps": 100, "total_steps": 900, "loss": 0.1666, "lr": 4.99847706754774e-05, "epoch": 1.1111111111111112, "percentage": 11.11, "elapsed_time": "0:00:23", "remaining_time": "0:03:11", "throughput": 1307.41, "total_tokens": 31232}
|