Training in progress, step 350

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4106b45ceccceae95e8b528b101fd891982dc12a562b267303c0a5c15c56e31
+oid sha256:7517520116a90df96714c96a11fa862e42a0dd35dffeff98e7454aeee1e7c1a9
 size 29034840

trainer_log.jsonl

@@ -64,3 +64,14 @@
 {"current_steps": 295, "total_steps": 3400, "loss": 0.7346, "lr": 9.96309206782565e-05, "epoch": 0.07597218645377285, "percentage": 8.68, "elapsed_time": "1:32:13", "remaining_time": "16:10:42", "throughput": 559.66, "total_tokens": 3096920}
 {"current_steps": 300, "total_steps": 3400, "loss": 0.6815, "lr": 9.960084393841355e-05, "epoch": 0.07725985063095545, "percentage": 8.82, "elapsed_time": "1:33:40", "remaining_time": "16:07:58", "throughput": 560.28, "total_tokens": 3149032}
 {"current_steps": 300, "total_steps": 3400, "eval_loss": 0.7073924541473389, "epoch": 0.07725985063095545, "percentage": 8.82, "elapsed_time": "1:34:18", "remaining_time": "16:14:32", "throughput": 556.5, "total_tokens": 3149032}
+{"current_steps": 305, "total_steps": 3400, "loss": 0.7208, "lr": 9.956959413129585e-05, "epoch": 0.07854751480813804, "percentage": 8.97, "elapsed_time": "1:35:53", "remaining_time": "16:13:04", "throughput": 556.45, "total_tokens": 3201560}
+{"current_steps": 310, "total_steps": 3400, "loss": 0.7144, "lr": 9.953717199596598e-05, "epoch": 0.07983517898532062, "percentage": 9.12, "elapsed_time": "1:37:21", "remaining_time": "16:10:27", "throughput": 557.14, "total_tokens": 3254632}
+{"current_steps": 315, "total_steps": 3400, "loss": 0.6861, "lr": 9.95035782992122e-05, "epoch": 0.08112284316250322, "percentage": 9.26, "elapsed_time": "1:38:52", "remaining_time": "16:08:22", "throughput": 557.33, "total_tokens": 3306432}
+{"current_steps": 320, "total_steps": 3400, "loss": 0.6836, "lr": 9.94688138355304e-05, "epoch": 0.08241050733968582, "percentage": 9.41, "elapsed_time": "1:40:21", "remaining_time": "16:05:55", "throughput": 557.75, "total_tokens": 3358392}
+{"current_steps": 325, "total_steps": 3400, "loss": 0.7353, "lr": 9.943287942710527e-05, "epoch": 0.0836981715168684, "percentage": 9.56, "elapsed_time": "1:41:50", "remaining_time": "16:03:39", "throughput": 558.24, "total_tokens": 3411424}
+{"current_steps": 330, "total_steps": 3400, "loss": 0.6774, "lr": 9.939577592379088e-05, "epoch": 0.08498583569405099, "percentage": 9.71, "elapsed_time": "1:43:18", "remaining_time": "16:01:07", "throughput": 558.66, "total_tokens": 3462992}
+{"current_steps": 335, "total_steps": 3400, "loss": 0.7331, "lr": 9.935750420309055e-05, "epoch": 0.08627349987123359, "percentage": 9.85, "elapsed_time": "1:44:49", "remaining_time": "15:59:00", "throughput": 559.08, "total_tokens": 3516136}
+{"current_steps": 340, "total_steps": 3400, "loss": 0.6939, "lr": 9.931806517013612e-05, "epoch": 0.08756116404841617, "percentage": 10.0, "elapsed_time": "1:46:17", "remaining_time": "15:56:39", "throughput": 559.51, "total_tokens": 3568360}
+{"current_steps": 345, "total_steps": 3400, "loss": 0.7158, "lr": 9.927745975766654e-05, "epoch": 0.08884882822559877, "percentage": 10.15, "elapsed_time": "1:47:46", "remaining_time": "15:54:25", "throughput": 559.88, "total_tokens": 3620696}
+{"current_steps": 350, "total_steps": 3400, "loss": 0.6932, "lr": 9.923568892600578e-05, "epoch": 0.09013649240278135, "percentage": 10.29, "elapsed_time": "1:49:14", "remaining_time": "15:51:57", "throughput": 560.41, "total_tokens": 3673152}
+{"current_steps": 350, "total_steps": 3400, "eval_loss": 0.7044599056243896, "epoch": 0.09013649240278135, "percentage": 10.29, "elapsed_time": "1:49:52", "remaining_time": "15:57:30", "throughput": 557.15, "total_tokens": 3673152}