Training in progress, step 3200

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d53665e5e9c8528df47b7ef76a4152d56ed4d96010a44cb39a4f16dca91d64bb
+oid sha256:3fb7a1dd58ebc0c93ef82d01cefb2df34681f15debd4b2701f60fafd33e16761
 size 29034840

trainer_log.jsonl

@@ -694,3 +694,14 @@
 {"current_steps": 3145, "total_steps": 3400, "loss": 0.2521, "lr": 1.5299867030334814e-06, "epoch": 0.8099407674478496, "percentage": 92.5, "elapsed_time": "3:00:53", "remaining_time": "0:14:39", "throughput": 3043.05, "total_tokens": 33026320}
 {"current_steps": 3150, "total_steps": 3400, "loss": 0.2669, "lr": 1.4708685051444515e-06, "epoch": 0.8112284316250322, "percentage": 92.65, "elapsed_time": "3:02:18", "remaining_time": "0:14:28", "throughput": 3023.98, "total_tokens": 33078960}
 {"current_steps": 3150, "total_steps": 3400, "eval_loss": 0.4687062203884125, "epoch": 0.8112284316250322, "percentage": 92.65, "elapsed_time": "3:02:56", "remaining_time": "0:14:31", "throughput": 3013.66, "total_tokens": 33078960}
+{"current_steps": 3155, "total_steps": 3400, "loss": 0.2622, "lr": 1.4128980283727943e-06, "epoch": 0.8125160958022147, "percentage": 92.79, "elapsed_time": "3:04:27", "remaining_time": "0:14:19", "throughput": 2993.58, "total_tokens": 33131352}
+{"current_steps": 3160, "total_steps": 3400, "loss": 0.2776, "lr": 1.356076643728843e-06, "epoch": 0.8138037599793974, "percentage": 92.94, "elapsed_time": "3:05:54", "remaining_time": "0:14:07", "throughput": 2974.74, "total_tokens": 33183032}
+{"current_steps": 3165, "total_steps": 3400, "loss": 0.247, "lr": 1.3004056950467135e-06, "epoch": 0.81509142415658, "percentage": 93.09, "elapsed_time": "3:07:21", "remaining_time": "0:13:54", "throughput": 2956.6, "total_tokens": 33235992}
+{"current_steps": 3170, "total_steps": 3400, "loss": 0.2917, "lr": 1.2458864989525698e-06, "epoch": 0.8163790883337626, "percentage": 93.24, "elapsed_time": "3:08:48", "remaining_time": "0:13:41", "throughput": 2938.55, "total_tokens": 33288696}
+{"current_steps": 3175, "total_steps": 3400, "loss": 0.257, "lr": 1.19252034483342e-06, "epoch": 0.8176667525109451, "percentage": 93.38, "elapsed_time": "3:10:13", "remaining_time": "0:13:28", "throughput": 2921.35, "total_tokens": 33341472}
+{"current_steps": 3180, "total_steps": 3400, "loss": 0.2836, "lr": 1.1403084948067021e-06, "epoch": 0.8189544166881277, "percentage": 93.53, "elapsed_time": "3:11:39", "remaining_time": "0:13:15", "throughput": 2904.15, "total_tokens": 33394856}
+{"current_steps": 3185, "total_steps": 3400, "loss": 0.3201, "lr": 1.089252183690348e-06, "epoch": 0.8202420808653104, "percentage": 93.68, "elapsed_time": "3:13:04", "remaining_time": "0:13:01", "throughput": 2887.33, "total_tokens": 33447208}
+{"current_steps": 3190, "total_steps": 3400, "loss": 0.2751, "lr": 1.0393526189736602e-06, "epoch": 0.8215297450424929, "percentage": 93.82, "elapsed_time": "3:14:30", "remaining_time": "0:12:48", "throughput": 2870.61, "total_tokens": 33500288}
+{"current_steps": 3195, "total_steps": 3400, "loss": 0.3231, "lr": 9.906109807887032e-07, "epoch": 0.8228174092196755, "percentage": 93.97, "elapsed_time": "3:15:55", "remaining_time": "0:12:34", "throughput": 2854.25, "total_tokens": 33552400}
+{"current_steps": 3200, "total_steps": 3400, "loss": 0.3322, "lr": 9.430284218824026e-07, "epoch": 0.8241050733968581, "percentage": 94.12, "elapsed_time": "3:17:21", "remaining_time": "0:12:20", "throughput": 2837.93, "total_tokens": 33604328}
+{"current_steps": 3200, "total_steps": 3400, "eval_loss": 0.47025421261787415, "epoch": 0.8241050733968581, "percentage": 94.12, "elapsed_time": "3:17:58", "remaining_time": "0:12:22", "throughput": 2828.96, "total_tokens": 33604328}