Training in progress, step 1800
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +18 -0
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 798032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01d50c364d8d953c3c125fcab2a5525e2208ed24f91d4d4b0dbb31bfd9ef1e39
|
| 3 |
size 798032
|
trainer_log.jsonl
CHANGED
|
@@ -361,3 +361,21 @@
|
|
| 361 |
{"current_steps": 1710, "total_steps": 1800, "eval_loss": 0.06143023446202278, "epoch": 19.0, "percentage": 95.0, "elapsed_time": "0:04:24", "remaining_time": "0:00:13", "throughput": 2023.66, "total_tokens": 535584}
|
| 362 |
{"current_steps": 1715, "total_steps": 1800, "loss": 0.1495, "lr": 3.468724188498751e-07, "epoch": 19.055555555555557, "percentage": 95.28, "elapsed_time": "0:04:26", "remaining_time": "0:00:13", "throughput": 2017.27, "total_tokens": 537152}
|
| 363 |
{"current_steps": 1720, "total_steps": 1800, "loss": 0.0176, "lr": 3.077914851215585e-07, "epoch": 19.11111111111111, "percentage": 95.56, "elapsed_time": "0:04:26", "remaining_time": "0:00:12", "throughput": 2017.93, "total_tokens": 538720}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 361 |
{"current_steps": 1710, "total_steps": 1800, "eval_loss": 0.06143023446202278, "epoch": 19.0, "percentage": 95.0, "elapsed_time": "0:04:24", "remaining_time": "0:00:13", "throughput": 2023.66, "total_tokens": 535584}
|
| 362 |
{"current_steps": 1715, "total_steps": 1800, "loss": 0.1495, "lr": 3.468724188498751e-07, "epoch": 19.055555555555557, "percentage": 95.28, "elapsed_time": "0:04:26", "remaining_time": "0:00:13", "throughput": 2017.27, "total_tokens": 537152}
|
| 363 |
{"current_steps": 1720, "total_steps": 1800, "loss": 0.0176, "lr": 3.077914851215585e-07, "epoch": 19.11111111111111, "percentage": 95.56, "elapsed_time": "0:04:26", "remaining_time": "0:00:12", "throughput": 2017.93, "total_tokens": 538720}
|
| 364 |
+
{"current_steps": 1725, "total_steps": 1800, "loss": 0.0203, "lr": 2.71032038404323e-07, "epoch": 19.166666666666668, "percentage": 95.83, "elapsed_time": "0:04:27", "remaining_time": "0:00:11", "throughput": 2018.45, "total_tokens": 540256}
|
| 365 |
+
{"current_steps": 1730, "total_steps": 1800, "loss": 0.008, "lr": 2.365975347105448e-07, "epoch": 19.22222222222222, "percentage": 96.11, "elapsed_time": "0:04:28", "remaining_time": "0:00:10", "throughput": 2019.12, "total_tokens": 541824}
|
| 366 |
+
{"current_steps": 1735, "total_steps": 1800, "loss": 0.0081, "lr": 2.0449121146845774e-07, "epoch": 19.27777777777778, "percentage": 96.39, "elapsed_time": "0:04:29", "remaining_time": "0:00:10", "throughput": 2019.91, "total_tokens": 543424}
|
| 367 |
+
{"current_steps": 1740, "total_steps": 1800, "loss": 0.0494, "lr": 1.747160872177883e-07, "epoch": 19.333333333333332, "percentage": 96.67, "elapsed_time": "0:04:29", "remaining_time": "0:00:09", "throughput": 2020.7, "total_tokens": 545024}
|
| 368 |
+
{"current_steps": 1745, "total_steps": 1800, "loss": 0.0258, "lr": 1.472749613259661e-07, "epoch": 19.38888888888889, "percentage": 96.94, "elapsed_time": "0:04:30", "remaining_time": "0:00:08", "throughput": 2021.2, "total_tokens": 546560}
|
| 369 |
+
{"current_steps": 1750, "total_steps": 1800, "loss": 0.0316, "lr": 1.22170413724923e-07, "epoch": 19.444444444444443, "percentage": 97.22, "elapsed_time": "0:04:31", "remaining_time": "0:00:07", "throughput": 2021.74, "total_tokens": 548096}
|
| 370 |
+
{"current_steps": 1755, "total_steps": 1800, "loss": 0.0542, "lr": 9.940480466855417e-08, "epoch": 19.5, "percentage": 97.5, "elapsed_time": "0:04:31", "remaining_time": "0:00:06", "throughput": 2022.43, "total_tokens": 549664}
|
| 371 |
+
{"current_steps": 1760, "total_steps": 1800, "loss": 0.0125, "lr": 7.898027451078982e-08, "epoch": 19.555555555555557, "percentage": 97.78, "elapsed_time": "0:04:32", "remaining_time": "0:00:06", "throughput": 2023.23, "total_tokens": 551264}
|
| 372 |
+
{"current_steps": 1765, "total_steps": 1800, "loss": 0.0641, "lr": 6.089874350439506e-08, "epoch": 19.61111111111111, "percentage": 98.06, "elapsed_time": "0:04:33", "remaining_time": "0:00:05", "throughput": 2023.76, "total_tokens": 552800}
|
| 373 |
+
{"current_steps": 1770, "total_steps": 1800, "loss": 0.0581, "lr": 4.516191162040051e-08, "epoch": 19.666666666666668, "percentage": 98.33, "elapsed_time": "0:04:33", "remaining_time": "0:00:04", "throughput": 2024.29, "total_tokens": 554336}
|
| 374 |
+
{"current_steps": 1775, "total_steps": 1800, "loss": 0.0233, "lr": 3.177125838830786e-08, "epoch": 19.72222222222222, "percentage": 98.61, "elapsed_time": "0:04:34", "remaining_time": "0:00:03", "throughput": 2024.8, "total_tokens": 555872}
|
| 375 |
+
{"current_steps": 1780, "total_steps": 1800, "loss": 0.0767, "lr": 2.0728042756967824e-08, "epoch": 19.77777777777778, "percentage": 98.89, "elapsed_time": "0:04:35", "remaining_time": "0:00:03", "throughput": 2025.68, "total_tokens": 557504}
|
| 376 |
+
{"current_steps": 1785, "total_steps": 1800, "loss": 0.0158, "lr": 1.2033302976222071e-08, "epoch": 19.833333333333332, "percentage": 99.17, "elapsed_time": "0:04:35", "remaining_time": "0:00:02", "throughput": 2026.2, "total_tokens": 559040}
|
| 377 |
+
{"current_steps": 1790, "total_steps": 1800, "loss": 0.0513, "lr": 5.687856499297928e-09, "epoch": 19.88888888888889, "percentage": 99.44, "elapsed_time": "0:04:36", "remaining_time": "0:00:01", "throughput": 2026.97, "total_tokens": 560640}
|
| 378 |
+
{"current_steps": 1795, "total_steps": 1800, "loss": 0.0649, "lr": 1.692299905944883e-09, "epoch": 19.944444444444443, "percentage": 99.72, "elapsed_time": "0:04:37", "remaining_time": "0:00:00", "throughput": 2027.52, "total_tokens": 562176}
|
| 379 |
+
{"current_steps": 1800, "total_steps": 1800, "loss": 0.0292, "lr": 4.700884634611935e-11, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:04:37", "remaining_time": "0:00:00", "throughput": 2027.87, "total_tokens": 563744}
|
| 380 |
+
{"current_steps": 1800, "total_steps": 1800, "eval_loss": 0.060703717172145844, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:04:38", "remaining_time": "0:00:00", "throughput": 2024.07, "total_tokens": 563744}
|
| 381 |
+
{"current_steps": 1800, "total_steps": 1800, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:04:39", "remaining_time": "0:00:00", "throughput": 2018.63, "total_tokens": 563744}
|