Training in progress, step 169

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f98dc81a9e9c2d70daf5d1eafd79eeca326649060dc43a2022f74c14077cfe2
+oid sha256:7bcc6a76bf23dfba6cf601356c3f71909bef09a3af7da0d5008818996b8e4e2a
 size 312947112

trainer_log.jsonl

@@ -41,3 +41,10 @@
 {"current_steps": 150, "total_steps": 249, "loss": 0.5382, "lr": 2.0812344417381595e-05, "epoch": 0.6024096385542169, "percentage": 60.24, "elapsed_time": "0:00:39", "remaining_time": "0:00:25", "throughput": 677.04, "total_tokens": 26496}
 {"current_steps": 155, "total_steps": 249, "loss": 0.5239, "lr": 1.909570167110415e-05, "epoch": 0.6224899598393574, "percentage": 62.25, "elapsed_time": "0:00:39", "remaining_time": "0:00:24", "throughput": 692.05, "total_tokens": 27392}
 {"current_steps": 156, "total_steps": 249, "eval_loss": 0.5172758102416992, "epoch": 0.6265060240963856, "percentage": 62.65, "elapsed_time": "0:00:41", "remaining_time": "0:00:24", "throughput": 667.09, "total_tokens": 27552}
+{"current_steps": 160, "total_steps": 249, "loss": 0.52, "lr": 1.7408081372259632e-05, "epoch": 0.642570281124498, "percentage": 64.26, "elapsed_time": "0:00:42", "remaining_time": "0:00:23", "throughput": 662.43, "total_tokens": 28272}
+{"current_steps": 165, "total_steps": 249, "loss": 0.4772, "lr": 1.5757778980982626e-05, "epoch": 0.6626506024096386, "percentage": 66.27, "elapsed_time": "0:00:43", "remaining_time": "0:00:21", "throughput": 675.53, "total_tokens": 29184}
+{"current_steps": 169, "total_steps": 249, "eval_loss": 0.5134099721908569, "epoch": 0.678714859437751, "percentage": 67.87, "elapsed_time": "0:00:44", "remaining_time": "0:00:21", "throughput": 672.59, "total_tokens": 29984}
+{"current_steps": 170, "total_steps": 249, "loss": 0.4832, "lr": 1.4152906522061048e-05, "epoch": 0.6827309236947792, "percentage": 68.27, "elapsed_time": "0:00:46", "remaining_time": "0:00:21", "throughput": 654.4, "total_tokens": 30128}
+{"current_steps": 175, "total_steps": 249, "loss": 0.494, "lr": 1.2601352710458313e-05, "epoch": 0.7028112449799196, "percentage": 70.28, "elapsed_time": "0:00:46", "remaining_time": "0:00:19", "throughput": 665.81, "total_tokens": 30976}
+{"current_steps": 180, "total_steps": 249, "loss": 0.4958, "lr": 1.1110744174509952e-05, "epoch": 0.7228915662650602, "percentage": 72.29, "elapsed_time": "0:00:46", "remaining_time": "0:00:18", "throughput": 676.56, "total_tokens": 31776}
+{"current_steps": 182, "total_steps": 249, "eval_loss": 0.5050697922706604, "epoch": 0.7309236947791165, "percentage": 73.09, "elapsed_time": "0:00:48", "remaining_time": "0:00:17", "throughput": 665.65, "total_tokens": 32080}