Training in progress, step 221
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 335717200
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f39a4d0181d83b75bea8d35343fe99264d206f013217af96252cad24c34eccdb
|
| 3 |
size 335717200
|
trainer_log.jsonl
CHANGED
|
@@ -55,3 +55,11 @@
|
|
| 55 |
{"current_steps": 200, "total_steps": 249, "loss": 0.355, "lr": 5.899065604459814e-06, "epoch": 0.8032128514056225, "percentage": 80.32, "elapsed_time": "0:00:50", "remaining_time": "0:00:12", "throughput": 699.61, "total_tokens": 34992}
|
| 56 |
{"current_steps": 205, "total_steps": 249, "loss": 0.3585, "lr": 4.81587299765594e-06, "epoch": 0.8232931726907631, "percentage": 82.33, "elapsed_time": "0:00:50", "remaining_time": "0:00:10", "throughput": 711.93, "total_tokens": 35888}
|
| 57 |
{"current_steps": 208, "total_steps": 249, "eval_loss": 0.3534963130950928, "epoch": 0.8353413654618473, "percentage": 83.53, "elapsed_time": "0:00:51", "remaining_time": "0:00:10", "throughput": 708.79, "total_tokens": 36512}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
{"current_steps": 200, "total_steps": 249, "loss": 0.355, "lr": 5.899065604459814e-06, "epoch": 0.8032128514056225, "percentage": 80.32, "elapsed_time": "0:00:50", "remaining_time": "0:00:12", "throughput": 699.61, "total_tokens": 34992}
|
| 56 |
{"current_steps": 205, "total_steps": 249, "loss": 0.3585, "lr": 4.81587299765594e-06, "epoch": 0.8232931726907631, "percentage": 82.33, "elapsed_time": "0:00:50", "remaining_time": "0:00:10", "throughput": 711.93, "total_tokens": 35888}
|
| 57 |
{"current_steps": 208, "total_steps": 249, "eval_loss": 0.3534963130950928, "epoch": 0.8353413654618473, "percentage": 83.53, "elapsed_time": "0:00:51", "remaining_time": "0:00:10", "throughput": 708.79, "total_tokens": 36512}
|
| 58 |
+
{"current_steps": 210, "total_steps": 249, "loss": 0.3715, "lr": 3.831895019292897e-06, "epoch": 0.8433734939759037, "percentage": 84.34, "elapsed_time": "0:00:52", "remaining_time": "0:00:09", "throughput": 697.89, "total_tokens": 36848}
|
| 59 |
+
{"current_steps": 215, "total_steps": 249, "loss": 0.3719, "lr": 2.9519683912911266e-06, "epoch": 0.8634538152610441, "percentage": 86.35, "elapsed_time": "0:00:53", "remaining_time": "0:00:08", "throughput": 712.27, "total_tokens": 37888}
|
| 60 |
+
{"current_steps": 220, "total_steps": 249, "loss": 0.3626, "lr": 2.1804183734670277e-06, "epoch": 0.8835341365461847, "percentage": 88.35, "elapsed_time": "0:00:53", "remaining_time": "0:00:07", "throughput": 723.79, "total_tokens": 38768}
|
| 61 |
+
{"current_steps": 221, "total_steps": 249, "eval_loss": 0.35169586539268494, "epoch": 0.8875502008032129, "percentage": 88.76, "elapsed_time": "0:00:54", "remaining_time": "0:00:06", "throughput": 714.69, "total_tokens": 38912}
|
| 62 |
+
{"current_steps": 225, "total_steps": 249, "loss": 0.3549, "lr": 1.5210375028143097e-06, "epoch": 0.9036144578313253, "percentage": 90.36, "elapsed_time": "0:00:56", "remaining_time": "0:00:06", "throughput": 700.34, "total_tokens": 39488}
|
| 63 |
+
{"current_steps": 230, "total_steps": 249, "loss": 0.3419, "lr": 9.770669513725128e-07, "epoch": 0.9236947791164659, "percentage": 92.37, "elapsed_time": "0:00:56", "remaining_time": "0:00:04", "throughput": 710.8, "total_tokens": 40336}
|
| 64 |
+
{"current_steps": 234, "total_steps": 249, "eval_loss": 0.3496658504009247, "epoch": 0.9397590361445783, "percentage": 93.98, "elapsed_time": "0:00:57", "remaining_time": "0:00:03", "throughput": 710.15, "total_tokens": 41120}
|
| 65 |
+
{"current_steps": 235, "total_steps": 249, "loss": 0.3635, "lr": 5.5118059431781e-07, "epoch": 0.9437751004016064, "percentage": 94.38, "elapsed_time": "0:00:59", "remaining_time": "0:00:03", "throughput": 697.74, "total_tokens": 41328}
|