Training in progress, step 1950

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b12fb1f62f0a49e6f331ab88ac0fdb4d07b7b5f34d217fb17ed283ee54aef732
+oid sha256:ad3594bcb3ff35f3f2e878e13876be354135b355ddc08a0bafcc51fa9e238692
 size 29034840

trainer_log.jsonl

@@ -420,3 +420,14 @@
 {"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}
+{"current_steps": 1905, "total_steps": 3400, "loss": 0.3542, "lr": 4.41774648053257e-05, "epoch": 0.4906000515065671, "percentage": 56.03, "elapsed_time": "6:45:56", "remaining_time": "5:18:34", "throughput": 821.27, "total_tokens": 20002968}
+{"current_steps": 1910, "total_steps": 3400, "loss": 0.4095, "lr": 4.3936031610520124e-05, "epoch": 0.49188771568374967, "percentage": 56.18, "elapsed_time": "6:47:22", "remaining_time": "5:17:47", "throughput": 820.53, "total_tokens": 20055560}
+{"current_steps": 1915, "total_steps": 3400, "loss": 0.3887, "lr": 4.3694741829461336e-05, "epoch": 0.4931753798609323, "percentage": 56.32, "elapsed_time": "6:48:49", "remaining_time": "5:17:01", "throughput": 819.74, "total_tokens": 20108016}
+{"current_steps": 1920, "total_steps": 3400, "loss": 0.3485, "lr": 4.345360116868823e-05, "epoch": 0.49446304403811486, "percentage": 56.47, "elapsed_time": "6:50:16", "remaining_time": "5:16:15", "throughput": 818.97, "total_tokens": 20160480}
+{"current_steps": 1925, "total_steps": 3400, "loss": 0.4348, "lr": 4.321261533121303e-05, "epoch": 0.49575070821529743, "percentage": 56.62, "elapsed_time": "6:51:43", "remaining_time": "5:15:28", "throughput": 818.22, "total_tokens": 20213312}
+{"current_steps": 1930, "total_steps": 3400, "loss": 0.4073, "lr": 4.2971790016386286e-05, "epoch": 0.49703837239248005, "percentage": 56.76, "elapsed_time": "6:53:11", "remaining_time": "5:14:42", "throughput": 817.48, "total_tokens": 20266288}
+{"current_steps": 1935, "total_steps": 3400, "loss": 0.3297, "lr": 4.273113091976225e-05, "epoch": 0.4983260365696626, "percentage": 56.91, "elapsed_time": "6:54:38", "remaining_time": "5:13:55", "throughput": 816.72, "total_tokens": 20318576}
+{"current_steps": 1940, "total_steps": 3400, "loss": 0.3352, "lr": 4.249064373296403e-05, "epoch": 0.49961370074684525, "percentage": 57.06, "elapsed_time": "6:56:05", "remaining_time": "5:13:08", "throughput": 815.96, "total_tokens": 20370696}
+{"current_steps": 1945, "total_steps": 3400, "loss": 0.3195, "lr": 4.225033414354908e-05, "epoch": 0.5009013649240278, "percentage": 57.21, "elapsed_time": "6:57:32", "remaining_time": "5:12:20", "throughput": 815.23, "total_tokens": 20423480}
+{"current_steps": 1950, "total_steps": 3400, "loss": 0.365, "lr": 4.201020783487464e-05, "epoch": 0.5021890291012104, "percentage": 57.35, "elapsed_time": "6:58:59", "remaining_time": "5:11:33", "throughput": 814.49, "total_tokens": 20476176}
+{"current_steps": 1950, "total_steps": 3400, "eval_loss": 0.4763557016849518, "epoch": 0.5021890291012104, "percentage": 57.35, "elapsed_time": "6:59:37", "remaining_time": "5:12:02", "throughput": 813.26, "total_tokens": 20476176}