Training in progress, step 2950

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f649bc97ca842140ab28c612e0e561ebbde8139ce799f23e401fad5ec0bf673a
+oid sha256:3b7a40fbb5d3ef8c199f94ef197e14510d714bce74ec2a360d2feaf74aeb1aee
 size 29034840

trainer_log.jsonl

@@ -648,3 +648,14 @@
 {"current_steps": 2895, "total_steps": 6770, "loss": 0.2312, "lr": 6.5831320462607e-05, "epoch": 0.8552437223042836, "percentage": 42.76, "elapsed_time": "6:12:49", "remaining_time": "8:19:01", "throughput": 1344.06, "total_tokens": 30066016}
 {"current_steps": 2900, "total_steps": 6770, "loss": 0.2029, "lr": 6.571542983224223e-05, "epoch": 0.8567208271787297, "percentage": 42.84, "elapsed_time": "6:14:15", "remaining_time": "8:19:26", "throughput": 1341.23, "total_tokens": 30118072}
 {"current_steps": 2900, "total_steps": 6770, "eval_loss": 0.39434579014778137, "epoch": 0.8567208271787297, "percentage": 42.84, "elapsed_time": "6:14:34", "remaining_time": "8:19:52", "throughput": 1340.09, "total_tokens": 30118072}
+{"current_steps": 2905, "total_steps": 6770, "loss": 0.2241, "lr": 6.559944544378072e-05, "epoch": 0.8581979320531757, "percentage": 42.91, "elapsed_time": "6:16:07", "remaining_time": "8:20:24", "throughput": 1336.91, "total_tokens": 30170248}
+{"current_steps": 2910, "total_steps": 6770, "loss": 0.2298, "lr": 6.548336798918411e-05, "epoch": 0.8596750369276218, "percentage": 42.98, "elapsed_time": "6:17:33", "remaining_time": "8:20:49", "throughput": 1334.08, "total_tokens": 30222016}
+{"current_steps": 2915, "total_steps": 6770, "loss": 0.2396, "lr": 6.536719816096935e-05, "epoch": 0.8611521418020679, "percentage": 43.06, "elapsed_time": "6:19:01", "remaining_time": "8:21:15", "throughput": 1331.18, "total_tokens": 30273312}
+{"current_steps": 2920, "total_steps": 6770, "loss": 0.2324, "lr": 6.52509366522045e-05, "epoch": 0.8626292466765141, "percentage": 43.13, "elapsed_time": "6:20:29", "remaining_time": "8:21:39", "throughput": 1328.32, "total_tokens": 30324328}
+{"current_steps": 2925, "total_steps": 6770, "loss": 0.2263, "lr": 6.513458415650452e-05, "epoch": 0.8641063515509602, "percentage": 43.21, "elapsed_time": "6:21:57", "remaining_time": "8:22:05", "throughput": 1325.47, "total_tokens": 30376488}
+{"current_steps": 2930, "total_steps": 6770, "loss": 0.1734, "lr": 6.501814136802725e-05, "epoch": 0.8655834564254062, "percentage": 43.28, "elapsed_time": "6:23:24", "remaining_time": "8:22:28", "throughput": 1322.77, "total_tokens": 30429504}
+{"current_steps": 2935, "total_steps": 6770, "loss": 0.2235, "lr": 6.490160898146918e-05, "epoch": 0.8670605612998523, "percentage": 43.35, "elapsed_time": "6:24:52", "remaining_time": "8:22:53", "throughput": 1319.93, "total_tokens": 30480400}
+{"current_steps": 2940, "total_steps": 6770, "loss": 0.2297, "lr": 6.47849876920614e-05, "epoch": 0.8685376661742984, "percentage": 43.43, "elapsed_time": "6:26:19", "remaining_time": "8:23:15", "throughput": 1317.22, "total_tokens": 30531912}
+{"current_steps": 2945, "total_steps": 6770, "loss": 0.1764, "lr": 6.46682781955653e-05, "epoch": 0.8700147710487445, "percentage": 43.5, "elapsed_time": "6:27:46", "remaining_time": "8:23:39", "throughput": 1314.52, "total_tokens": 30584688}
+{"current_steps": 2950, "total_steps": 6770, "loss": 0.1692, "lr": 6.455148118826859e-05, "epoch": 0.8714918759231906, "percentage": 43.57, "elapsed_time": "6:29:12", "remaining_time": "8:23:59", "throughput": 1311.97, "total_tokens": 30637448}
+{"current_steps": 2950, "total_steps": 6770, "eval_loss": 0.20344533026218414, "epoch": 0.8714918759231906, "percentage": 43.57, "elapsed_time": "6:29:31", "remaining_time": "8:24:23", "throughput": 1310.91, "total_tokens": 30637448}