Training in progress, step 250
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +6 -0
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 25200088
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfdf030d9f653cfe09bf2f374b2aa77ef8852890deb390006cde083903588695
|
3 |
size 25200088
|
trainer_log.jsonl
CHANGED
@@ -22,3 +22,9 @@
|
|
22 |
{"current_steps": 190, "total_steps": 1500, "loss": 0.884, "accuracy": 0.625, "learning_rate": 4.804657878971252e-06, "epoch": 0.1633003867640739, "percentage": 12.67, "elapsed_time": "0:25:12", "remaining_time": "2:53:45", "throughput": "0.00", "total_tokens": 0}
|
23 |
{"current_steps": 200, "total_steps": 1500, "loss": 0.8419, "accuracy": 0.612500011920929, "learning_rate": 4.783863644106502e-06, "epoch": 0.17189514396218306, "percentage": 13.33, "elapsed_time": "0:26:25", "remaining_time": "2:51:43", "throughput": "0.00", "total_tokens": 0}
|
24 |
{"current_steps": 200, "total_steps": 1500, "eval_loss": 0.8462886810302734, "epoch": 0.17189514396218306, "percentage": 13.33, "elapsed_time": "0:26:50", "remaining_time": "2:54:28", "throughput": "0.00", "total_tokens": 0}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
{"current_steps": 190, "total_steps": 1500, "loss": 0.884, "accuracy": 0.625, "learning_rate": 4.804657878971252e-06, "epoch": 0.1633003867640739, "percentage": 12.67, "elapsed_time": "0:25:12", "remaining_time": "2:53:45", "throughput": "0.00", "total_tokens": 0}
|
23 |
{"current_steps": 200, "total_steps": 1500, "loss": 0.8419, "accuracy": 0.612500011920929, "learning_rate": 4.783863644106502e-06, "epoch": 0.17189514396218306, "percentage": 13.33, "elapsed_time": "0:26:25", "remaining_time": "2:51:43", "throughput": "0.00", "total_tokens": 0}
|
24 |
{"current_steps": 200, "total_steps": 1500, "eval_loss": 0.8462886810302734, "epoch": 0.17189514396218306, "percentage": 13.33, "elapsed_time": "0:26:50", "remaining_time": "2:54:28", "throughput": "0.00", "total_tokens": 0}
|
25 |
+
{"current_steps": 210, "total_steps": 1500, "loss": 0.8187, "accuracy": 0.612500011920929, "learning_rate": 4.762067631165049e-06, "epoch": 0.18048990116029223, "percentage": 14.0, "elapsed_time": "0:28:11", "remaining_time": "2:53:09", "throughput": "0.00", "total_tokens": 0}
|
26 |
+
{"current_steps": 220, "total_steps": 1500, "loss": 0.8448, "accuracy": 0.675000011920929, "learning_rate": 4.7392794005985324e-06, "epoch": 0.18908465835840138, "percentage": 14.67, "elapsed_time": "0:29:24", "remaining_time": "2:51:07", "throughput": "0.00", "total_tokens": 0}
|
27 |
+
{"current_steps": 230, "total_steps": 1500, "loss": 0.8066, "accuracy": 0.6625000238418579, "learning_rate": 4.715508948078037e-06, "epoch": 0.19767941555651053, "percentage": 15.33, "elapsed_time": "0:30:39", "remaining_time": "2:49:16", "throughput": "0.00", "total_tokens": 0}
|
28 |
+
{"current_steps": 240, "total_steps": 1500, "loss": 0.7787, "accuracy": 0.6499999761581421, "learning_rate": 4.690766700109659e-06, "epoch": 0.20627417275461968, "percentage": 16.0, "elapsed_time": "0:31:52", "remaining_time": "2:47:23", "throughput": "0.00", "total_tokens": 0}
|
29 |
+
{"current_steps": 250, "total_steps": 1500, "loss": 0.7776, "accuracy": 0.625, "learning_rate": 4.665063509461098e-06, "epoch": 0.21486892995272883, "percentage": 16.67, "elapsed_time": "0:33:08", "remaining_time": "2:45:43", "throughput": "0.00", "total_tokens": 0}
|
30 |
+
{"current_steps": 250, "total_steps": 1500, "eval_loss": 0.7469337582588196, "epoch": 0.21486892995272883, "percentage": 16.67, "elapsed_time": "0:33:34", "remaining_time": "2:47:50", "throughput": "0.00", "total_tokens": 0}
|