Training in progress, step 195
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +7 -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 sha256:003f24b14a4371ebaafe2cf845ac82ec48f6741cb34e8fbac4e2cf36035c597a
|
| 3 |
size 335717200
|
trainer_log.jsonl
CHANGED
|
@@ -51,3 +51,10 @@
|
|
| 51 |
{"current_steps": 185, "total_steps": 249, "loss": 0.3852, "lr": 9.688407967401248e-06, "epoch": 0.7429718875502008, "percentage": 74.3, "elapsed_time": "0:00:55", "remaining_time": "0:00:19", "throughput": 583.93, "total_tokens": 32608}
|
| 52 |
{"current_steps": 190, "total_steps": 249, "loss": 0.4115, "lr": 8.341335551199902e-06, "epoch": 0.7630522088353414, "percentage": 76.31, "elapsed_time": "0:00:56", "remaining_time": "0:00:17", "throughput": 593.85, "total_tokens": 33360}
|
| 53 |
{"current_steps": 195, "total_steps": 249, "loss": 0.3673, "lr": 7.076148430479321e-06, "epoch": 0.7831325301204819, "percentage": 78.31, "elapsed_time": "0:00:56", "remaining_time": "0:00:15", "throughput": 604.8, "total_tokens": 34176}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
{"current_steps": 185, "total_steps": 249, "loss": 0.3852, "lr": 9.688407967401248e-06, "epoch": 0.7429718875502008, "percentage": 74.3, "elapsed_time": "0:00:55", "remaining_time": "0:00:19", "throughput": 583.93, "total_tokens": 32608}
|
| 52 |
{"current_steps": 190, "total_steps": 249, "loss": 0.4115, "lr": 8.341335551199902e-06, "epoch": 0.7630522088353414, "percentage": 76.31, "elapsed_time": "0:00:56", "remaining_time": "0:00:17", "throughput": 593.85, "total_tokens": 33360}
|
| 53 |
{"current_steps": 195, "total_steps": 249, "loss": 0.3673, "lr": 7.076148430479321e-06, "epoch": 0.7831325301204819, "percentage": 78.31, "elapsed_time": "0:00:56", "remaining_time": "0:00:15", "throughput": 604.8, "total_tokens": 34176}
|
| 54 |
+
{"current_steps": 195, "total_steps": 249, "eval_loss": 0.3541497588157654, "epoch": 0.7831325301204819, "percentage": 78.31, "elapsed_time": "0:00:57", "remaining_time": "0:00:15", "throughput": 598.64, "total_tokens": 34176}
|
| 55 |
+
{"current_steps": 200, "total_steps": 249, "loss": 0.3583, "lr": 5.899065604459814e-06, "epoch": 0.8032128514056225, "percentage": 80.32, "elapsed_time": "0:01:00", "remaining_time": "0:00:14", "throughput": 581.33, "total_tokens": 34992}
|
| 56 |
+
{"current_steps": 205, "total_steps": 249, "loss": 0.3675, "lr": 4.81587299765594e-06, "epoch": 0.8232931726907631, "percentage": 82.33, "elapsed_time": "0:01:00", "remaining_time": "0:00:12", "throughput": 592.88, "total_tokens": 35888}
|
| 57 |
+
{"current_steps": 208, "total_steps": 249, "eval_loss": 0.3513210713863373, "epoch": 0.8353413654618473, "percentage": 83.53, "elapsed_time": "0:01:01", "remaining_time": "0:00:12", "throughput": 595.29, "total_tokens": 36512}
|
| 58 |
+
{"current_steps": 210, "total_steps": 249, "loss": 0.3717, "lr": 3.831895019292897e-06, "epoch": 0.8433734939759037, "percentage": 84.34, "elapsed_time": "0:01:02", "remaining_time": "0:00:11", "throughput": 586.88, "total_tokens": 36848}
|
| 59 |
+
{"current_steps": 215, "total_steps": 249, "loss": 0.3723, "lr": 2.9519683912911266e-06, "epoch": 0.8634538152610441, "percentage": 86.35, "elapsed_time": "0:01:03", "remaining_time": "0:00:09", "throughput": 600.27, "total_tokens": 37888}
|
| 60 |
+
{"current_steps": 220, "total_steps": 249, "loss": 0.3634, "lr": 2.1804183734670277e-06, "epoch": 0.8835341365461847, "percentage": 88.35, "elapsed_time": "0:01:03", "remaining_time": "0:00:08", "throughput": 610.98, "total_tokens": 38768}
|