Training in progress, step 189

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3261adc84bf772e4cdba87326b1399fef109675f999775d8614d358520f54601
+oid sha256:c80c1d5d5723c6fddfcdad02a7a7e2569350a8791858bc8b6c2a27bb60c52fb4
 size 819328

trainer_log.jsonl

@@ -28,3 +28,16 @@
 {"current_steps": 130, "total_steps": 1250, "loss": 0.5602, "lr": 0.029999064225016296, "epoch": 1.04, "percentage": 10.4, "elapsed_time": "0:00:19", "remaining_time": "0:02:51", "throughput": 2577.45, "total_tokens": 51200}
 {"current_steps": 135, "total_steps": 1250, "loss": 0.6027, "lr": 0.029995262839249498, "epoch": 1.08, "percentage": 10.8, "elapsed_time": "0:00:20", "remaining_time": "0:02:48", "throughput": 2602.96, "total_tokens": 53216}
 {"current_steps": 140, "total_steps": 1250, "loss": 0.7287, "lr": 0.0299885380972807, "epoch": 1.12, "percentage": 11.2, "elapsed_time": "0:00:21", "remaining_time": "0:02:46", "throughput": 2624.77, "total_tokens": 55168}
+{"current_steps": 145, "total_steps": 1250, "loss": 0.6063, "lr": 0.02997889131011168, "epoch": 1.16, "percentage": 11.6, "elapsed_time": "0:00:21", "remaining_time": "0:02:44", "throughput": 2640.56, "total_tokens": 56960}
+{"current_steps": 150, "total_steps": 1250, "loss": 0.6846, "lr": 0.0299663243584027, "epoch": 1.2, "percentage": 12.0, "elapsed_time": "0:00:22", "remaining_time": "0:02:42", "throughput": 2660.71, "total_tokens": 58880}
+{"current_steps": 155, "total_steps": 1250, "loss": 0.7672, "lr": 0.029950839692105897, "epoch": 1.24, "percentage": 12.4, "elapsed_time": "0:00:22", "remaining_time": "0:02:40", "throughput": 2675.34, "total_tokens": 60672}
+{"current_steps": 160, "total_steps": 1250, "loss": 1.9008, "lr": 0.029932440329987653, "epoch": 1.28, "percentage": 12.8, "elapsed_time": "0:00:23", "remaining_time": "0:02:38", "throughput": 2701.85, "total_tokens": 62848}
+{"current_steps": 165, "total_steps": 1250, "loss": 1.5402, "lr": 0.02991112985904007, "epoch": 1.32, "percentage": 13.2, "elapsed_time": "0:00:23", "remaining_time": "0:02:36", "throughput": 2707.61, "total_tokens": 64448}
+{"current_steps": 170, "total_steps": 1250, "loss": 1.0271, "lr": 0.029886912433781675, "epoch": 1.3599999999999999, "percentage": 13.6, "elapsed_time": "0:00:24", "remaining_time": "0:02:34", "throughput": 2724.78, "total_tokens": 66368}
+{"current_steps": 175, "total_steps": 1250, "loss": 0.6777, "lr": 0.02985979277544751, "epoch": 1.4, "percentage": 14.0, "elapsed_time": "0:00:24", "remaining_time": "0:02:32", "throughput": 2735.66, "total_tokens": 68128}
+{"current_steps": 180, "total_steps": 1250, "loss": 0.7326, "lr": 0.029829776171068707, "epoch": 1.44, "percentage": 14.4, "elapsed_time": "0:00:25", "remaining_time": "0:02:31", "throughput": 2753.16, "total_tokens": 70112}
+{"current_steps": 185, "total_steps": 1250, "loss": 1.1616, "lr": 0.029796868472441763, "epoch": 1.48, "percentage": 14.8, "elapsed_time": "0:00:26", "remaining_time": "0:02:30", "throughput": 2775.22, "total_tokens": 72384}
+{"current_steps": 189, "total_steps": 1250, "eval_loss": 0.532053530216217, "epoch": 1.512, "percentage": 15.12, "elapsed_time": "0:00:27", "remaining_time": "0:02:34", "throughput": 2684.23, "total_tokens": 74112}
+{"current_steps": 190, "total_steps": 1250, "loss": 0.5949, "lr": 0.029761076094987723, "epoch": 1.52, "percentage": 15.2, "elapsed_time": "0:00:28", "remaining_time": "0:02:41", "throughput": 2588.01, "total_tokens": 74752}
+{"current_steps": 195, "total_steps": 1250, "loss": 0.5306, "lr": 0.02972240601650149, "epoch": 1.56, "percentage": 15.6, "elapsed_time": "0:00:29", "remaining_time": "0:02:39", "throughput": 2602.78, "total_tokens": 76640}
+{"current_steps": 200, "total_steps": 1250, "loss": 0.5088, "lr": 0.029680865775791494, "epoch": 1.6, "percentage": 16.0, "elapsed_time": "0:00:30", "remaining_time": "0:02:37", "throughput": 2623.88, "total_tokens": 78784}