Training in progress, step 1200

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad37ecfc8f56cfb958ea72a1146b5dd079374376e542f0312701bdbcbb5deae5
+oid sha256:0c1933263a4147535e3edcd506e0269c5b74a0e48619e4b7de41e058b06d730b
 size 29034840

trainer_log.jsonl

@@ -255,3 +255,14 @@
 {"current_steps": 1145, "total_steps": 3400, "loss": 0.508, "lr": 7.915270142049566e-05, "epoch": 0.2948750965748133, "percentage": 33.68, "elapsed_time": "2:51:47", "remaining_time": "5:38:20", "throughput": 1166.0, "total_tokens": 12018928}
 {"current_steps": 1150, "total_steps": 3400, "loss": 0.4553, "lr": 7.89548083375394e-05, "epoch": 0.2961627607519959, "percentage": 33.82, "elapsed_time": "2:53:14", "remaining_time": "5:38:57", "throughput": 1161.26, "total_tokens": 12071088}
 {"current_steps": 1150, "total_steps": 3400, "eval_loss": 0.45381438732147217, "epoch": 0.2961627607519959, "percentage": 33.82, "elapsed_time": "2:53:53", "remaining_time": "5:40:12", "throughput": 1156.99, "total_tokens": 12071088}
+{"current_steps": 1155, "total_steps": 3400, "loss": 0.4192, "lr": 7.875623046909544e-05, "epoch": 0.29745042492917845, "percentage": 33.97, "elapsed_time": "2:55:26", "remaining_time": "5:41:00", "throughput": 1151.57, "total_tokens": 12122128}
+{"current_steps": 1160, "total_steps": 3400, "loss": 0.433, "lr": 7.855697251155967e-05, "epoch": 0.29873808910636107, "percentage": 34.12, "elapsed_time": "2:56:53", "remaining_time": "5:41:34", "throughput": 1147.09, "total_tokens": 12174288}
+{"current_steps": 1165, "total_steps": 3400, "loss": 0.4817, "lr": 7.835703917741212e-05, "epoch": 0.30002575328354364, "percentage": 34.26, "elapsed_time": "2:58:21", "remaining_time": "5:42:09", "throughput": 1142.59, "total_tokens": 12227008}
+{"current_steps": 1170, "total_steps": 3400, "loss": 0.485, "lr": 7.81564351951057e-05, "epoch": 0.30131341746072626, "percentage": 34.41, "elapsed_time": "2:59:48", "remaining_time": "5:42:41", "throughput": 1138.31, "total_tokens": 12280168}
+{"current_steps": 1175, "total_steps": 3400, "loss": 0.4532, "lr": 7.795516530895414e-05, "epoch": 0.30260108163790883, "percentage": 34.56, "elapsed_time": "3:01:15", "remaining_time": "5:43:13", "throughput": 1134.03, "total_tokens": 12333072}
+{"current_steps": 1180, "total_steps": 3400, "loss": 0.4643, "lr": 7.775323427901993e-05, "epoch": 0.3038887458150914, "percentage": 34.71, "elapsed_time": "3:02:43", "remaining_time": "5:43:46", "throughput": 1129.73, "total_tokens": 12386208}
+{"current_steps": 1185, "total_steps": 3400, "loss": 0.4577, "lr": 7.755064688100171e-05, "epoch": 0.305176409992274, "percentage": 34.85, "elapsed_time": "3:04:11", "remaining_time": "5:44:16", "throughput": 1125.62, "total_tokens": 12439304}
+{"current_steps": 1190, "total_steps": 3400, "loss": 0.4666, "lr": 7.734740790612136e-05, "epoch": 0.3064640741694566, "percentage": 35.0, "elapsed_time": "3:05:39", "remaining_time": "5:44:48", "throughput": 1121.31, "total_tokens": 12491360}
+{"current_steps": 1195, "total_steps": 3400, "loss": 0.407, "lr": 7.714352216101055e-05, "epoch": 0.3077517383466392, "percentage": 35.15, "elapsed_time": "3:07:07", "remaining_time": "5:45:17", "throughput": 1117.27, "total_tokens": 12544264}
+{"current_steps": 1200, "total_steps": 3400, "loss": 0.454, "lr": 7.693899446759727e-05, "epoch": 0.3090394025238218, "percentage": 35.29, "elapsed_time": "3:08:36", "remaining_time": "5:45:47", "throughput": 1113.05, "total_tokens": 12596208}
+{"current_steps": 1200, "total_steps": 3400, "eval_loss": 0.49250805377960205, "epoch": 0.3090394025238218, "percentage": 35.29, "elapsed_time": "3:09:15", "remaining_time": "5:46:58", "throughput": 1109.25, "total_tokens": 12596208}