Training in progress, step 1100

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4499fca7257a53d1a8959e9e138764d24facbc55103cd1d2e30b092c058fc6d9
+oid sha256:f16f6078244d0994120e51d527f92194dad6fa70876b55e40b787da46626e91a
 size 29034840

trainer_log.jsonl

@@ -229,3 +229,14 @@
 {"current_steps": 1045, "total_steps": 3400, "loss": 0.018, "lr": 8.29596727716949e-05, "epoch": 0.5382436260623229, "percentage": 30.74, "elapsed_time": "5:09:50", "remaining_time": "11:38:14", "throughput": 561.23, "total_tokens": 10433280}
 {"current_steps": 1050, "total_steps": 3400, "loss": 0.0007, "lr": 8.277643590156894e-05, "epoch": 0.5408189544166881, "percentage": 30.88, "elapsed_time": "5:11:16", "remaining_time": "11:36:40", "throughput": 561.3, "total_tokens": 10483200}
 {"current_steps": 1050, "total_steps": 3400, "eval_loss": 0.05677948147058487, "epoch": 0.5408189544166881, "percentage": 30.88, "elapsed_time": "5:11:35", "remaining_time": "11:37:22", "throughput": 560.73, "total_tokens": 10483200}
+{"current_steps": 1055, "total_steps": 3400, "loss": 0.0436, "lr": 8.259242386389973e-05, "epoch": 0.5433942827710533, "percentage": 31.03, "elapsed_time": "5:13:08", "remaining_time": "11:36:01", "throughput": 560.63, "total_tokens": 10533120}
+{"current_steps": 1060, "total_steps": 3400, "loss": 0.0124, "lr": 8.240764101059912e-05, "epoch": 0.5459696111254185, "percentage": 31.18, "elapsed_time": "5:14:34", "remaining_time": "11:34:26", "throughput": 560.71, "total_tokens": 10583040}
+{"current_steps": 1065, "total_steps": 3400, "loss": 0.0155, "lr": 8.222209171180883e-05, "epoch": 0.5485449394797837, "percentage": 31.32, "elapsed_time": "5:16:00", "remaining_time": "11:32:50", "throughput": 560.79, "total_tokens": 10632960}
+{"current_steps": 1070, "total_steps": 3400, "loss": 0.0206, "lr": 8.203578035579715e-05, "epoch": 0.5511202678341488, "percentage": 31.47, "elapsed_time": "5:17:26", "remaining_time": "11:31:15", "throughput": 560.88, "total_tokens": 10682880}
+{"current_steps": 1075, "total_steps": 3400, "loss": 0.0237, "lr": 8.184871134885513e-05, "epoch": 0.553695596188514, "percentage": 31.62, "elapsed_time": "5:18:53", "remaining_time": "11:29:41", "throughput": 560.95, "total_tokens": 10732800}
+{"current_steps": 1080, "total_steps": 3400, "loss": 0.0018, "lr": 8.166088911519235e-05, "epoch": 0.5562709245428792, "percentage": 31.76, "elapsed_time": "5:20:19", "remaining_time": "11:28:06", "throughput": 561.03, "total_tokens": 10782720}
+{"current_steps": 1085, "total_steps": 3400, "loss": 0.0296, "lr": 8.147231809683236e-05, "epoch": 0.5588462528972444, "percentage": 31.91, "elapsed_time": "5:21:46", "remaining_time": "11:26:32", "throughput": 561.1, "total_tokens": 10832640}
+{"current_steps": 1090, "total_steps": 3400, "loss": 0.0006, "lr": 8.128300275350756e-05, "epoch": 0.5614215812516096, "percentage": 32.06, "elapsed_time": "5:23:12", "remaining_time": "11:24:56", "throughput": 561.19, "total_tokens": 10882560}
+{"current_steps": 1095, "total_steps": 3400, "loss": 0.0004, "lr": 8.109294756255375e-05, "epoch": 0.5639969096059748, "percentage": 32.21, "elapsed_time": "5:24:38", "remaining_time": "11:23:23", "throughput": 561.25, "total_tokens": 10932480}
+{"current_steps": 1100, "total_steps": 3400, "loss": 0.0056, "lr": 8.090215701880419e-05, "epoch": 0.56657223796034, "percentage": 32.35, "elapsed_time": "5:26:04", "remaining_time": "11:21:47", "throughput": 561.34, "total_tokens": 10982400}
+{"current_steps": 1100, "total_steps": 3400, "eval_loss": 0.0003656313638202846, "epoch": 0.56657223796034, "percentage": 32.35, "elapsed_time": "5:26:23", "remaining_time": "11:22:28", "throughput": 560.79, "total_tokens": 10982400}