Training in progress, step 234
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +5 -0
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 312947112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54ebedeaac3dbb5971e58ba8a72cdc0251e6e6beb6250c3d66fecd9ed6dc5d91
|
| 3 |
size 312947112
|
trainer_log.jsonl
CHANGED
|
@@ -61,3 +61,8 @@
|
|
| 61 |
{"current_steps": 221, "total_steps": 249, "eval_loss": 0.4947091042995453, "epoch": 0.8875502008032129, "percentage": 88.76, "elapsed_time": "0:00:59", "remaining_time": "0:00:07", "throughput": 654.97, "total_tokens": 38912}
|
| 62 |
{"current_steps": 225, "total_steps": 249, "loss": 0.6159, "lr": 1.5210375028143097e-06, "epoch": 0.9036144578313253, "percentage": 90.36, "elapsed_time": "0:01:01", "remaining_time": "0:00:06", "throughput": 645.49, "total_tokens": 39488}
|
| 63 |
{"current_steps": 230, "total_steps": 249, "loss": 0.5318, "lr": 9.770669513725128e-07, "epoch": 0.9236947791164659, "percentage": 92.37, "elapsed_time": "0:01:01", "remaining_time": "0:00:05", "throughput": 654.32, "total_tokens": 40336}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 61 |
{"current_steps": 221, "total_steps": 249, "eval_loss": 0.4947091042995453, "epoch": 0.8875502008032129, "percentage": 88.76, "elapsed_time": "0:00:59", "remaining_time": "0:00:07", "throughput": 654.97, "total_tokens": 38912}
|
| 62 |
{"current_steps": 225, "total_steps": 249, "loss": 0.6159, "lr": 1.5210375028143097e-06, "epoch": 0.9036144578313253, "percentage": 90.36, "elapsed_time": "0:01:01", "remaining_time": "0:00:06", "throughput": 645.49, "total_tokens": 39488}
|
| 63 |
{"current_steps": 230, "total_steps": 249, "loss": 0.5318, "lr": 9.770669513725128e-07, "epoch": 0.9236947791164659, "percentage": 92.37, "elapsed_time": "0:01:01", "remaining_time": "0:00:05", "throughput": 654.32, "total_tokens": 40336}
|
| 64 |
+
{"current_steps": 234, "total_steps": 249, "eval_loss": 0.49773862957954407, "epoch": 0.9397590361445783, "percentage": 93.98, "elapsed_time": "0:01:03", "remaining_time": "0:00:04", "throughput": 652.62, "total_tokens": 41120}
|
| 65 |
+
{"current_steps": 235, "total_steps": 249, "loss": 0.6135, "lr": 5.5118059431781e-07, "epoch": 0.9437751004016064, "percentage": 94.38, "elapsed_time": "0:01:04", "remaining_time": "0:00:03", "throughput": 639.48, "total_tokens": 41328}
|
| 66 |
+
{"current_steps": 240, "total_steps": 249, "loss": 0.6099, "lr": 2.454718665888589e-07, "epoch": 0.963855421686747, "percentage": 96.39, "elapsed_time": "0:01:05", "remaining_time": "0:00:02", "throughput": 647.98, "total_tokens": 42176}
|
| 67 |
+
{"current_steps": 245, "total_steps": 249, "loss": 0.445, "lr": 6.14434726538493e-08, "epoch": 0.9839357429718876, "percentage": 98.39, "elapsed_time": "0:01:05", "remaining_time": "0:00:01", "throughput": 660.47, "total_tokens": 43312}
|
| 68 |
+
{"current_steps": 247, "total_steps": 249, "eval_loss": 0.5010460019111633, "epoch": 0.9919678714859438, "percentage": 99.2, "elapsed_time": "0:01:06", "remaining_time": "0:00:00", "throughput": 652.35, "total_tokens": 43600}
|