Training in progress, step 70
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +5 -0
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 409728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd8a190d4994ff2fe1c343f864f2918e51f0d7dbc39e6de35d8971dd54739baf
|
| 3 |
size 409728
|
trainer_log.jsonl
CHANGED
|
@@ -19,3 +19,8 @@
|
|
| 19 |
{"current_steps": 56, "total_steps": 125, "eval_loss": 0.8889466524124146, "epoch": 0.448, "percentage": 44.8, "elapsed_time": "0:00:17", "remaining_time": "0:00:21", "throughput": 1289.81, "total_tokens": 22432}
|
| 20 |
{"current_steps": 60, "total_steps": 125, "loss": 0.8296, "lr": 0.01915253267137274, "epoch": 0.48, "percentage": 48.0, "elapsed_time": "0:00:18", "remaining_time": "0:00:19", "throughput": 1309.09, "total_tokens": 24160}
|
| 21 |
{"current_steps": 63, "total_steps": 125, "eval_loss": 0.7238854169845581, "epoch": 0.504, "percentage": 50.4, "elapsed_time": "0:00:19", "remaining_time": "0:00:19", "throughput": 1314.93, "total_tokens": 25504}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
{"current_steps": 56, "total_steps": 125, "eval_loss": 0.8889466524124146, "epoch": 0.448, "percentage": 44.8, "elapsed_time": "0:00:17", "remaining_time": "0:00:21", "throughput": 1289.81, "total_tokens": 22432}
|
| 20 |
{"current_steps": 60, "total_steps": 125, "loss": 0.8296, "lr": 0.01915253267137274, "epoch": 0.48, "percentage": 48.0, "elapsed_time": "0:00:18", "remaining_time": "0:00:19", "throughput": 1309.09, "total_tokens": 24160}
|
| 21 |
{"current_steps": 63, "total_steps": 125, "eval_loss": 0.7238854169845581, "epoch": 0.504, "percentage": 50.4, "elapsed_time": "0:00:19", "remaining_time": "0:00:19", "throughput": 1314.93, "total_tokens": 25504}
|
| 22 |
+
{"current_steps": 65, "total_steps": 125, "loss": 0.6751, "lr": 0.017096855093032493, "epoch": 0.52, "percentage": 52.0, "elapsed_time": "0:00:20", "remaining_time": "0:00:18", "throughput": 1282.75, "total_tokens": 26112}
|
| 23 |
+
{"current_steps": 70, "total_steps": 125, "loss": 0.516, "lr": 0.015, "epoch": 0.56, "percentage": 56.0, "elapsed_time": "0:00:20", "remaining_time": "0:00:16", "throughput": 1347.62, "total_tokens": 28064}
|
| 24 |
+
{"current_steps": 70, "total_steps": 125, "eval_loss": 0.5987562537193298, "epoch": 0.56, "percentage": 56.0, "elapsed_time": "0:00:21", "remaining_time": "0:00:16", "throughput": 1305.71, "total_tokens": 28064}
|
| 25 |
+
{"current_steps": 75, "total_steps": 125, "loss": 0.5519, "lr": 0.012903144906967513, "epoch": 0.6, "percentage": 60.0, "elapsed_time": "0:00:23", "remaining_time": "0:00:15", "throughput": 1293.03, "total_tokens": 29824}
|
| 26 |
+
{"current_steps": 77, "total_steps": 125, "eval_loss": 0.447248637676239, "epoch": 0.616, "percentage": 61.6, "elapsed_time": "0:00:23", "remaining_time": "0:00:14", "throughput": 1282.51, "total_tokens": 30720}
|