Training in progress, step 3050

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b538a0a0e54384ad87de2092402be8f45bc821d6a1abbb2da29fb0c50b16944
+oid sha256:7c0919a08fffa1587acbe31835d5a8f8669c94a21edd38c6366ed4e1822b6b15
 size 29034840

trainer_log.jsonl

@@ -661,3 +661,14 @@
 {"current_steps": 2995, "total_steps": 3400, "loss": 0.3327, "lr": 3.829320579258466e-06, "epoch": 0.7713108421323719, "percentage": 88.09, "elapsed_time": "2:15:59", "remaining_time": "0:18:23", "throughput": 3854.49, "total_tokens": 31451704}
 {"current_steps": 3000, "total_steps": 3400, "loss": 0.3522, "lr": 3.7365415833504725e-06, "epoch": 0.7725985063095545, "percentage": 88.24, "elapsed_time": "2:17:26", "remaining_time": "0:18:19", "throughput": 3820.26, "total_tokens": 31503344}
 {"current_steps": 3000, "total_steps": 3400, "eval_loss": 0.4726044833660126, "epoch": 0.7725985063095545, "percentage": 88.24, "elapsed_time": "2:18:04", "remaining_time": "0:18:24", "throughput": 3802.82, "total_tokens": 31503344}
+{"current_steps": 3005, "total_steps": 3400, "loss": 0.3076, "lr": 3.644856725057405e-06, "epoch": 0.773886170486737, "percentage": 88.38, "elapsed_time": "2:19:34", "remaining_time": "0:18:20", "throughput": 3768.05, "total_tokens": 31555896}
+{"current_steps": 3010, "total_steps": 3400, "loss": 0.2934, "lr": 3.554268172739661e-06, "epoch": 0.7751738346639196, "percentage": 88.53, "elapsed_time": "2:21:00", "remaining_time": "0:18:16", "throughput": 3735.81, "total_tokens": 31608208}
+{"current_steps": 3015, "total_steps": 3400, "loss": 0.3333, "lr": 3.4647780688298826e-06, "epoch": 0.7764614988411023, "percentage": 88.68, "elapsed_time": "2:22:26", "remaining_time": "0:18:11", "throughput": 3704.6, "total_tokens": 31659576}
+{"current_steps": 3020, "total_steps": 3400, "loss": 0.2666, "lr": 3.376388529782215e-06, "epoch": 0.7777491630182848, "percentage": 88.82, "elapsed_time": "2:23:51", "remaining_time": "0:18:06", "throughput": 3673.99, "total_tokens": 31712176}
+{"current_steps": 3025, "total_steps": 3400, "loss": 0.2454, "lr": 3.2891016460222967e-06, "epoch": 0.7790368271954674, "percentage": 88.97, "elapsed_time": "2:25:17", "remaining_time": "0:18:00", "throughput": 3644.09, "total_tokens": 31765672}
+{"current_steps": 3030, "total_steps": 3400, "loss": 0.3242, "lr": 3.2029194818977983e-06, "epoch": 0.78032449137265, "percentage": 89.12, "elapsed_time": "2:26:42", "remaining_time": "0:17:54", "throughput": 3614.68, "total_tokens": 31818456}
+{"current_steps": 3035, "total_steps": 3400, "loss": 0.3378, "lr": 3.117844075629617e-06, "epoch": 0.7816121555498327, "percentage": 89.26, "elapsed_time": "2:28:08", "remaining_time": "0:17:48", "throughput": 3585.87, "total_tokens": 31871648}
+{"current_steps": 3040, "total_steps": 3400, "loss": 0.2981, "lr": 3.033877439263666e-06, "epoch": 0.7828998197270152, "percentage": 89.41, "elapsed_time": "2:29:33", "remaining_time": "0:17:42", "throughput": 3557.62, "total_tokens": 31924688}
+{"current_steps": 3045, "total_steps": 3400, "loss": 0.2909, "lr": 2.951021558623274e-06, "epoch": 0.7841874839041978, "percentage": 89.56, "elapsed_time": "2:30:59", "remaining_time": "0:17:36", "throughput": 3529.88, "total_tokens": 31977752}
+{"current_steps": 3050, "total_steps": 3400, "loss": 0.3137, "lr": 2.869278393262226e-06, "epoch": 0.7854751480813804, "percentage": 89.71, "elapsed_time": "2:32:23", "remaining_time": "0:17:29", "throughput": 3502.95, "total_tokens": 32030016}
+{"current_steps": 3050, "total_steps": 3400, "eval_loss": 0.4746885299682617, "epoch": 0.7854751480813804, "percentage": 89.71, "elapsed_time": "2:33:01", "remaining_time": "0:17:33", "throughput": 3488.43, "total_tokens": 32030016}