Training in progress, step 1900

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83d482b0521ba55cbd644a8b0adfd6f4e4037fa30dd12a4a9ba58c4d63a8e631
+oid sha256:b12fb1f62f0a49e6f331ab88ac0fdb4d07b7b5f34d217fb17ed283ee54aef732
 size 29034840

trainer_log.jsonl

@@ -409,3 +409,14 @@
 {"current_steps": 1845, "total_steps": 3400, "loss": 0.3699, "lr": 4.708376801122321e-05, "epoch": 0.475148081380376, "percentage": 54.26, "elapsed_time": "6:27:02", "remaining_time": "5:26:12", "throughput": 834.27, "total_tokens": 19373584}
 {"current_steps": 1850, "total_steps": 3400, "loss": 0.3941, "lr": 4.6841060060770154e-05, "epoch": 0.4764357455575586, "percentage": 54.41, "elapsed_time": "6:28:29", "remaining_time": "5:25:29", "throughput": 833.35, "total_tokens": 19424688}
 {"current_steps": 1850, "total_steps": 3400, "eval_loss": 0.45103010535240173, "epoch": 0.4764357455575586, "percentage": 54.41, "elapsed_time": "6:29:07", "remaining_time": "5:26:01", "throughput": 831.99, "total_tokens": 19424688}
+{"current_steps": 1855, "total_steps": 3400, "loss": 0.4362, "lr": 4.659842681971258e-05, "epoch": 0.4777234097347412, "percentage": 54.56, "elapsed_time": "6:30:40", "remaining_time": "5:25:23", "throughput": 830.93, "total_tokens": 19477320}
+{"current_steps": 1860, "total_steps": 3400, "loss": 0.4027, "lr": 4.635587402636241e-05, "epoch": 0.47901107391192377, "percentage": 54.71, "elapsed_time": "6:32:06", "remaining_time": "5:24:39", "throughput": 830.08, "total_tokens": 19529000}
+{"current_steps": 1865, "total_steps": 3400, "loss": 0.3981, "lr": 4.611340741712901e-05, "epoch": 0.48029873808910634, "percentage": 54.85, "elapsed_time": "6:33:34", "remaining_time": "5:23:56", "throughput": 829.22, "total_tokens": 19581736}
+{"current_steps": 1870, "total_steps": 3400, "loss": 0.3545, "lr": 4.5871032726383386e-05, "epoch": 0.48158640226628896, "percentage": 55.0, "elapsed_time": "6:35:00", "remaining_time": "5:23:11", "throughput": 828.45, "total_tokens": 19634744}
+{"current_steps": 1875, "total_steps": 3400, "loss": 0.34, "lr": 4.562875568632278e-05, "epoch": 0.48287406644347153, "percentage": 55.15, "elapsed_time": "6:36:28", "remaining_time": "5:22:28", "throughput": 827.57, "total_tokens": 19686792}
+{"current_steps": 1880, "total_steps": 3400, "loss": 0.3041, "lr": 4.5386582026834906e-05, "epoch": 0.48416173062065415, "percentage": 55.29, "elapsed_time": "6:37:54", "remaining_time": "5:21:42", "throughput": 826.81, "total_tokens": 19739784}
+{"current_steps": 1885, "total_steps": 3400, "loss": 0.445, "lr": 4.5144517475362514e-05, "epoch": 0.4854493947978367, "percentage": 55.44, "elapsed_time": "6:39:23", "remaining_time": "5:20:59", "throughput": 825.92, "total_tokens": 19792024}
+{"current_steps": 1890, "total_steps": 3400, "loss": 0.3532, "lr": 4.490256775676797e-05, "epoch": 0.4867370589750193, "percentage": 55.59, "elapsed_time": "6:40:50", "remaining_time": "5:20:14", "throughput": 825.12, "total_tokens": 19844568}
+{"current_steps": 1895, "total_steps": 3400, "loss": 0.4356, "lr": 4.466073859319781e-05, "epoch": 0.4880247231522019, "percentage": 55.74, "elapsed_time": "6:42:18", "remaining_time": "5:19:30", "throughput": 824.3, "total_tokens": 19897464}
+{"current_steps": 1900, "total_steps": 3400, "loss": 0.2877, "lr": 4.441903570394739e-05, "epoch": 0.4893123873293845, "percentage": 55.88, "elapsed_time": "6:43:44", "remaining_time": "5:18:44", "throughput": 823.55, "total_tokens": 19950480}
+{"current_steps": 1900, "total_steps": 3400, "eval_loss": 0.4511750042438507, "epoch": 0.4893123873293845, "percentage": 55.88, "elapsed_time": "6:44:22", "remaining_time": "5:19:14", "throughput": 822.26, "total_tokens": 19950480}