Training in progress, step 117
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 sha256:2c94e5f35bfe3e146d0823b10bb721b0dd0bdc5aeddc5b4f6d9309fd21c7d91d
|
| 3 |
size 335717200
|
trainer_log.jsonl
CHANGED
|
@@ -29,3 +29,10 @@
|
|
| 29 |
{"current_steps": 105, "total_steps": 249, "loss": 0.3169, "lr": 3.616191779978907e-05, "epoch": 0.42168674698795183, "percentage": 42.17, "elapsed_time": "0:00:33", "remaining_time": "0:00:45", "throughput": 549.13, "total_tokens": 18400}
|
| 30 |
{"current_steps": 110, "total_steps": 249, "loss": 0.3631, "lr": 3.456708580912725e-05, "epoch": 0.44176706827309237, "percentage": 44.18, "elapsed_time": "0:00:33", "remaining_time": "0:00:42", "throughput": 574.97, "total_tokens": 19456}
|
| 31 |
{"current_steps": 115, "total_steps": 249, "loss": 0.4246, "lr": 3.292522702044221e-05, "epoch": 0.46184738955823296, "percentage": 46.18, "elapsed_time": "0:00:34", "remaining_time": "0:00:39", "throughput": 593.75, "total_tokens": 20288}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
{"current_steps": 105, "total_steps": 249, "loss": 0.3169, "lr": 3.616191779978907e-05, "epoch": 0.42168674698795183, "percentage": 42.17, "elapsed_time": "0:00:33", "remaining_time": "0:00:45", "throughput": 549.13, "total_tokens": 18400}
|
| 30 |
{"current_steps": 110, "total_steps": 249, "loss": 0.3631, "lr": 3.456708580912725e-05, "epoch": 0.44176706827309237, "percentage": 44.18, "elapsed_time": "0:00:33", "remaining_time": "0:00:42", "throughput": 574.97, "total_tokens": 19456}
|
| 31 |
{"current_steps": 115, "total_steps": 249, "loss": 0.4246, "lr": 3.292522702044221e-05, "epoch": 0.46184738955823296, "percentage": 46.18, "elapsed_time": "0:00:34", "remaining_time": "0:00:39", "throughput": 593.75, "total_tokens": 20288}
|
| 32 |
+
{"current_steps": 117, "total_steps": 249, "eval_loss": 0.36986905336380005, "epoch": 0.46987951807228917, "percentage": 46.99, "elapsed_time": "0:00:34", "remaining_time": "0:00:39", "throughput": 592.06, "total_tokens": 20656}
|
| 33 |
+
{"current_steps": 120, "total_steps": 249, "loss": 0.3885, "lr": 3.1244411954180676e-05, "epoch": 0.4819277108433735, "percentage": 48.19, "elapsed_time": "0:00:38", "remaining_time": "0:00:41", "throughput": 552.47, "total_tokens": 21328}
|
| 34 |
+
{"current_steps": 125, "total_steps": 249, "loss": 0.3539, "lr": 2.9532902619507462e-05, "epoch": 0.5020080321285141, "percentage": 50.2, "elapsed_time": "0:00:38", "remaining_time": "0:00:38", "throughput": 572.73, "total_tokens": 22304}
|
| 35 |
+
{"current_steps": 130, "total_steps": 249, "loss": 0.3657, "lr": 2.7799111902582696e-05, "epoch": 0.5220883534136547, "percentage": 52.21, "elapsed_time": "0:00:39", "remaining_time": "0:00:35", "throughput": 586.92, "total_tokens": 23056}
|
| 36 |
+
{"current_steps": 130, "total_steps": 249, "eval_loss": 0.35231098532676697, "epoch": 0.5220883534136547, "percentage": 52.21, "elapsed_time": "0:00:39", "remaining_time": "0:00:36", "throughput": 578.36, "total_tokens": 23056}
|
| 37 |
+
{"current_steps": 135, "total_steps": 249, "loss": 0.3499, "lr": 2.6051562213206632e-05, "epoch": 0.5421686746987951, "percentage": 54.22, "elapsed_time": "0:00:41", "remaining_time": "0:00:35", "throughput": 571.58, "total_tokens": 23840}
|
| 38 |
+
{"current_steps": 140, "total_steps": 249, "loss": 0.3637, "lr": 2.429884359310328e-05, "epoch": 0.5622489959839357, "percentage": 56.22, "elapsed_time": "0:00:42", "remaining_time": "0:00:32", "throughput": 590.67, "total_tokens": 24832}
|