Training in progress, step 1710
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +19 -0
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 58745928
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f5524c21ac56e84ccecb502446bff34953758b37c78418ab304558e0c9b9e9d
|
| 3 |
size 58745928
|
trainer_log.jsonl
CHANGED
|
@@ -351,3 +351,22 @@
|
|
| 351 |
{"current_steps": 1665, "total_steps": 1800, "loss": 0.0, "lr": 8.64447643366953e-07, "epoch": 18.5, "percentage": 92.5, "elapsed_time": "0:06:20", "remaining_time": "0:00:30", "throughput": 1370.03, "total_tokens": 521824}
|
| 352 |
{"current_steps": 1670, "total_steps": 1800, "loss": 0.0, "lr": 8.023897500469391e-07, "epoch": 18.555555555555557, "percentage": 92.78, "elapsed_time": "0:06:21", "remaining_time": "0:00:29", "throughput": 1370.64, "total_tokens": 523424}
|
| 353 |
{"current_steps": 1675, "total_steps": 1800, "loss": 0.0, "lr": 7.426068431000882e-07, "epoch": 18.61111111111111, "percentage": 93.06, "elapsed_time": "0:06:22", "remaining_time": "0:00:28", "throughput": 1371.11, "total_tokens": 524960}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 351 |
{"current_steps": 1665, "total_steps": 1800, "loss": 0.0, "lr": 8.64447643366953e-07, "epoch": 18.5, "percentage": 92.5, "elapsed_time": "0:06:20", "remaining_time": "0:00:30", "throughput": 1370.03, "total_tokens": 521824}
|
| 352 |
{"current_steps": 1670, "total_steps": 1800, "loss": 0.0, "lr": 8.023897500469391e-07, "epoch": 18.555555555555557, "percentage": 92.78, "elapsed_time": "0:06:21", "remaining_time": "0:00:29", "throughput": 1370.64, "total_tokens": 523424}
|
| 353 |
{"current_steps": 1675, "total_steps": 1800, "loss": 0.0, "lr": 7.426068431000882e-07, "epoch": 18.61111111111111, "percentage": 93.06, "elapsed_time": "0:06:22", "remaining_time": "0:00:28", "throughput": 1371.11, "total_tokens": 524960}
|
| 354 |
+
{"current_steps": 1680, "total_steps": 1800, "loss": 0.0, "lr": 6.851045431350927e-07, "epoch": 18.666666666666668, "percentage": 93.33, "elapsed_time": "0:06:23", "remaining_time": "0:00:27", "throughput": 1371.56, "total_tokens": 526496}
|
| 355 |
+
{"current_steps": 1685, "total_steps": 1800, "loss": 0.0, "lr": 6.298882563448599e-07, "epoch": 18.72222222222222, "percentage": 93.61, "elapsed_time": "0:06:24", "remaining_time": "0:00:26", "throughput": 1372.07, "total_tokens": 528064}
|
| 356 |
+
{"current_steps": 1690, "total_steps": 1800, "loss": 0.0, "lr": 5.769631739982267e-07, "epoch": 18.77777777777778, "percentage": 93.89, "elapsed_time": "0:06:25", "remaining_time": "0:00:25", "throughput": 1372.64, "total_tokens": 529632}
|
| 357 |
+
{"current_steps": 1695, "total_steps": 1800, "loss": 0.0, "lr": 5.263342719518921e-07, "epoch": 18.833333333333332, "percentage": 94.17, "elapsed_time": "0:06:26", "remaining_time": "0:00:23", "throughput": 1373.29, "total_tokens": 531232}
|
| 358 |
+
{"current_steps": 1700, "total_steps": 1800, "loss": 0.0, "lr": 4.780063101826132e-07, "epoch": 18.88888888888889, "percentage": 94.44, "elapsed_time": "0:06:27", "remaining_time": "0:00:22", "throughput": 1373.83, "total_tokens": 532800}
|
| 359 |
+
{"current_steps": 1705, "total_steps": 1800, "loss": 0.0, "lr": 4.319838323396691e-07, "epoch": 18.944444444444443, "percentage": 94.72, "elapsed_time": "0:06:28", "remaining_time": "0:00:21", "throughput": 1374.43, "total_tokens": 534400}
|
| 360 |
+
{"current_steps": 1710, "total_steps": 1800, "loss": 0.0, "lr": 3.88271165317694e-07, "epoch": 19.0, "percentage": 95.0, "elapsed_time": "0:06:29", "remaining_time": "0:00:20", "throughput": 1374.4, "total_tokens": 535968}
|
| 361 |
+
{"current_steps": 1710, "total_steps": 1800, "eval_loss": 0.101484015583992, "epoch": 19.0, "percentage": 95.0, "elapsed_time": "0:06:30", "remaining_time": "0:00:20", "throughput": 1372.27, "total_tokens": 535968}
|
| 362 |
+
{"current_steps": 1715, "total_steps": 1800, "loss": 0.0, "lr": 3.468724188498751e-07, "epoch": 19.055555555555557, "percentage": 95.28, "elapsed_time": "0:06:34", "remaining_time": "0:00:19", "throughput": 1362.28, "total_tokens": 537536}
|
| 363 |
+
{"current_steps": 1720, "total_steps": 1800, "loss": 0.0, "lr": 3.077914851215585e-07, "epoch": 19.11111111111111, "percentage": 95.56, "elapsed_time": "0:06:35", "remaining_time": "0:00:18", "throughput": 1362.73, "total_tokens": 539072}
|
| 364 |
+
{"current_steps": 1725, "total_steps": 1800, "loss": 0.0, "lr": 2.71032038404323e-07, "epoch": 19.166666666666668, "percentage": 95.83, "elapsed_time": "0:06:36", "remaining_time": "0:00:17", "throughput": 1363.17, "total_tokens": 540608}
|
| 365 |
+
{"current_steps": 1730, "total_steps": 1800, "loss": 0.0, "lr": 2.365975347105448e-07, "epoch": 19.22222222222222, "percentage": 96.11, "elapsed_time": "0:06:37", "remaining_time": "0:00:16", "throughput": 1362.85, "total_tokens": 542208}
|
| 366 |
+
{"current_steps": 1735, "total_steps": 1800, "loss": 0.0, "lr": 2.0449121146845774e-07, "epoch": 19.27777777777778, "percentage": 96.39, "elapsed_time": "0:06:38", "remaining_time": "0:00:14", "throughput": 1363.01, "total_tokens": 543776}
|
| 367 |
+
{"current_steps": 1740, "total_steps": 1800, "loss": 0.0, "lr": 1.747160872177883e-07, "epoch": 19.333333333333332, "percentage": 96.67, "elapsed_time": "0:06:39", "remaining_time": "0:00:13", "throughput": 1363.39, "total_tokens": 545280}
|
| 368 |
+
{"current_steps": 1745, "total_steps": 1800, "loss": 0.0, "lr": 1.472749613259661e-07, "epoch": 19.38888888888889, "percentage": 96.94, "elapsed_time": "0:06:40", "remaining_time": "0:00:12", "throughput": 1363.92, "total_tokens": 546848}
|
| 369 |
+
{"current_steps": 1750, "total_steps": 1800, "loss": 0.0, "lr": 1.22170413724923e-07, "epoch": 19.444444444444443, "percentage": 97.22, "elapsed_time": "0:06:41", "remaining_time": "0:00:11", "throughput": 1364.46, "total_tokens": 548416}
|
| 370 |
+
{"current_steps": 1755, "total_steps": 1800, "loss": 0.0, "lr": 9.940480466855417e-08, "epoch": 19.5, "percentage": 97.5, "elapsed_time": "0:06:42", "remaining_time": "0:00:10", "throughput": 1365.05, "total_tokens": 550016}
|
| 371 |
+
{"current_steps": 1760, "total_steps": 1800, "loss": 0.0, "lr": 7.898027451078982e-08, "epoch": 19.555555555555557, "percentage": 97.78, "elapsed_time": "0:06:43", "remaining_time": "0:00:09", "throughput": 1365.6, "total_tokens": 551584}
|
| 372 |
+
{"current_steps": 1765, "total_steps": 1800, "loss": 0.0, "lr": 6.089874350439506e-08, "epoch": 19.61111111111111, "percentage": 98.06, "elapsed_time": "0:06:44", "remaining_time": "0:00:08", "throughput": 1366.12, "total_tokens": 553152}
|