Training in progress, step 2400

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8464937776286fdba4fee3aa59e0e0cefe29cc3b83812b6842ff0a56228048f2
+oid sha256:2874dfb474adef2e86193b1ab18660860287a5e9abf08e0b2d06a88e2eefcb7a
 size 29034840

trainer_log.jsonl

@@ -519,3 +519,14 @@
 {"current_steps": 2345, "total_steps": 3400, "loss": 0.3243, "lr": 2.4093103400192625e-05, "epoch": 0.603914499098635, "percentage": 68.97, "elapsed_time": "8:59:49", "remaining_time": "4:02:51", "throughput": 760.3, "total_tokens": 24625824}
 {"current_steps": 2350, "total_steps": 3400, "loss": 0.3651, "lr": 2.388543882155067e-05, "epoch": 0.6052021632758177, "percentage": 69.12, "elapsed_time": "9:01:18", "remaining_time": "4:01:51", "throughput": 759.85, "total_tokens": 24678768}
 {"current_steps": 2350, "total_steps": 3400, "eval_loss": 0.4145541489124298, "epoch": 0.6052021632758177, "percentage": 69.12, "elapsed_time": "9:01:56", "remaining_time": "4:02:08", "throughput": 758.96, "total_tokens": 24678768}
+{"current_steps": 2355, "total_steps": 3400, "loss": 0.3229, "lr": 2.3678391856132204e-05, "epoch": 0.6064898274530003, "percentage": 69.26, "elapsed_time": "9:03:29", "remaining_time": "4:01:09", "throughput": 758.39, "total_tokens": 24730528}
+{"current_steps": 2360, "total_steps": 3400, "loss": 0.3308, "lr": 2.3471967400628513e-05, "epoch": 0.6077774916301828, "percentage": 69.41, "elapsed_time": "9:04:57", "remaining_time": "4:00:09", "throughput": 757.98, "total_tokens": 24784472}
+{"current_steps": 2365, "total_steps": 3400, "loss": 0.356, "lr": 2.3266170337008398e-05, "epoch": 0.6090651558073654, "percentage": 69.56, "elapsed_time": "9:06:24", "remaining_time": "3:59:07", "throughput": 757.61, "total_tokens": 24838168}
+{"current_steps": 2370, "total_steps": 3400, "loss": 0.2784, "lr": 2.306100553240274e-05, "epoch": 0.610352819984548, "percentage": 69.71, "elapsed_time": "9:07:53", "remaining_time": "3:58:06", "throughput": 757.16, "total_tokens": 24890552}
+{"current_steps": 2375, "total_steps": 3400, "loss": 0.2859, "lr": 2.2856477838989456e-05, "epoch": 0.6116404841617307, "percentage": 69.85, "elapsed_time": "9:09:20", "remaining_time": "3:57:05", "throughput": 756.74, "total_tokens": 24942904}
+{"current_steps": 2380, "total_steps": 3400, "loss": 0.3107, "lr": 2.2652592093878666e-05, "epoch": 0.6129281483389132, "percentage": 70.0, "elapsed_time": "9:10:48", "remaining_time": "3:56:03", "throughput": 756.33, "total_tokens": 24995776}
+{"current_steps": 2385, "total_steps": 3400, "loss": 0.3131, "lr": 2.244935311899829e-05, "epoch": 0.6142158125160958, "percentage": 70.15, "elapsed_time": "9:12:16", "remaining_time": "3:55:02", "throughput": 755.89, "total_tokens": 25047848}
+{"current_steps": 2390, "total_steps": 3400, "loss": 0.3175, "lr": 2.224676572098007e-05, "epoch": 0.6155034766932784, "percentage": 70.29, "elapsed_time": "9:13:44", "remaining_time": "3:54:00", "throughput": 755.49, "total_tokens": 25100896}
+{"current_steps": 2395, "total_steps": 3400, "loss": 0.3482, "lr": 2.2044834691045873e-05, "epoch": 0.6167911408704609, "percentage": 70.44, "elapsed_time": "9:15:12", "remaining_time": "3:52:58", "throughput": 755.08, "total_tokens": 25153912}
+{"current_steps": 2400, "total_steps": 3400, "loss": 0.3445, "lr": 2.184356480489432e-05, "epoch": 0.6180788050476436, "percentage": 70.59, "elapsed_time": "9:16:40", "remaining_time": "3:51:56", "throughput": 754.67, "total_tokens": 25206168}
+{"current_steps": 2400, "total_steps": 3400, "eval_loss": 0.42807063460350037, "epoch": 0.6180788050476436, "percentage": 70.59, "elapsed_time": "9:17:18", "remaining_time": "3:52:12", "throughput": 753.81, "total_tokens": 25206168}