Training in progress, step 200
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +11 -0
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 29034840
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfb788f0d6ef0dec08ed5f5eb5575155c2531033fdd3222d6ffa1678d4305eab
|
3 |
size 29034840
|
trainer_log.jsonl
CHANGED
@@ -31,3 +31,14 @@
|
|
31 |
{"current_steps": 145, "total_steps": 3882, "loss": 0.9071, "lr": 7.435897435897436e-05, "epoch": 0.07468452227659027, "percentage": 3.74, "elapsed_time": "0:45:55", "remaining_time": "19:43:28", "throughput": 615.57, "total_tokens": 1696024}
|
32 |
{"current_steps": 150, "total_steps": 3882, "loss": 0.9045, "lr": 7.692307692307693e-05, "epoch": 0.07725985063095545, "percentage": 3.86, "elapsed_time": "0:47:24", "remaining_time": "19:39:19", "throughput": 616.91, "total_tokens": 1754512}
|
33 |
{"current_steps": 150, "total_steps": 3882, "eval_loss": 0.8934853076934814, "epoch": 0.07725985063095545, "percentage": 3.86, "elapsed_time": "0:47:43", "remaining_time": "19:47:33", "throughput": 612.63, "total_tokens": 1754512}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
31 |
{"current_steps": 145, "total_steps": 3882, "loss": 0.9071, "lr": 7.435897435897436e-05, "epoch": 0.07468452227659027, "percentage": 3.74, "elapsed_time": "0:45:55", "remaining_time": "19:43:28", "throughput": 615.57, "total_tokens": 1696024}
|
32 |
{"current_steps": 150, "total_steps": 3882, "loss": 0.9045, "lr": 7.692307692307693e-05, "epoch": 0.07725985063095545, "percentage": 3.86, "elapsed_time": "0:47:24", "remaining_time": "19:39:19", "throughput": 616.91, "total_tokens": 1754512}
|
33 |
{"current_steps": 150, "total_steps": 3882, "eval_loss": 0.8934853076934814, "epoch": 0.07725985063095545, "percentage": 3.86, "elapsed_time": "0:47:43", "remaining_time": "19:47:33", "throughput": 612.63, "total_tokens": 1754512}
|
34 |
+
{"current_steps": 155, "total_steps": 3882, "loss": 0.8992, "lr": 7.948717948717948e-05, "epoch": 0.07983517898532062, "percentage": 3.99, "elapsed_time": "0:49:20", "remaining_time": "19:46:21", "throughput": 612.43, "total_tokens": 1812976}
|
35 |
+
{"current_steps": 160, "total_steps": 3882, "loss": 0.8965, "lr": 8.205128205128205e-05, "epoch": 0.08241050733968582, "percentage": 4.12, "elapsed_time": "0:50:48", "remaining_time": "19:42:01", "throughput": 613.85, "total_tokens": 1871464}
|
36 |
+
{"current_steps": 165, "total_steps": 3882, "loss": 0.9094, "lr": 8.461538461538461e-05, "epoch": 0.08498583569405099, "percentage": 4.25, "elapsed_time": "0:52:18", "remaining_time": "19:38:32", "throughput": 614.83, "total_tokens": 1929928}
|
37 |
+
{"current_steps": 170, "total_steps": 3882, "loss": 0.903, "lr": 8.717948717948718e-05, "epoch": 0.08756116404841617, "percentage": 4.38, "elapsed_time": "0:53:47", "remaining_time": "19:34:27", "throughput": 616.14, "total_tokens": 1988432}
|
38 |
+
{"current_steps": 175, "total_steps": 3882, "loss": 0.902, "lr": 8.974358974358975e-05, "epoch": 0.09013649240278135, "percentage": 4.51, "elapsed_time": "0:55:16", "remaining_time": "19:30:56", "throughput": 617.16, "total_tokens": 2046920}
|
39 |
+
{"current_steps": 180, "total_steps": 3882, "loss": 0.9006, "lr": 9.230769230769232e-05, "epoch": 0.09271182075714654, "percentage": 4.64, "elapsed_time": "0:56:45", "remaining_time": "19:27:28", "throughput": 618.16, "total_tokens": 2105392}
|
40 |
+
{"current_steps": 185, "total_steps": 3882, "loss": 0.9042, "lr": 9.487179487179487e-05, "epoch": 0.09528714911151172, "percentage": 4.77, "elapsed_time": "0:58:15", "remaining_time": "19:24:13", "throughput": 619.04, "total_tokens": 2163872}
|
41 |
+
{"current_steps": 190, "total_steps": 3882, "loss": 0.9096, "lr": 9.743589743589744e-05, "epoch": 0.0978624774658769, "percentage": 4.89, "elapsed_time": "0:59:43", "remaining_time": "19:20:39", "throughput": 620.11, "total_tokens": 2222352}
|
42 |
+
{"current_steps": 195, "total_steps": 3882, "loss": 0.9037, "lr": 0.0001, "epoch": 0.10043780582024209, "percentage": 5.02, "elapsed_time": "1:01:11", "remaining_time": "19:17:04", "throughput": 621.18, "total_tokens": 2280800}
|
43 |
+
{"current_steps": 200, "total_steps": 3882, "loss": 0.904, "lr": 9.999954623308172e-05, "epoch": 0.10301313417460727, "percentage": 5.15, "elapsed_time": "1:02:41", "remaining_time": "19:14:00", "throughput": 621.98, "total_tokens": 2339304}
|
44 |
+
{"current_steps": 200, "total_steps": 3882, "eval_loss": 0.8980139493942261, "epoch": 0.10301313417460727, "percentage": 5.15, "elapsed_time": "1:03:00", "remaining_time": "19:19:56", "throughput": 618.8, "total_tokens": 2339304}
|