Training in progress, step 300

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:810af82eabdcc28df7d1bf5eb9ac2a1f9cf690e08d76987aa6aef5043270f66e
+oid sha256:a4106b45ceccceae95e8b528b101fd891982dc12a562b267303c0a5c15c56e31
 size 29034840

trainer_log.jsonl

@@ -53,3 +53,14 @@
 {"current_steps": 245, "total_steps": 3400, "loss": 0.7704, "lr": 9.986702663973722e-05, "epoch": 0.06309554468194695, "percentage": 7.21, "elapsed_time": "1:16:48", "remaining_time": "16:29:01", "throughput": 558.22, "total_tokens": 2572384}
 {"current_steps": 250, "total_steps": 3400, "loss": 0.7346, "lr": 9.98487151097676e-05, "epoch": 0.06438320885912954, "percentage": 7.35, "elapsed_time": "1:18:17", "remaining_time": "16:26:29", "throughput": 558.88, "total_tokens": 2625352}
 {"current_steps": 250, "total_steps": 3400, "eval_loss": 0.7181503176689148, "epoch": 0.06438320885912954, "percentage": 7.35, "elapsed_time": "1:18:55", "remaining_time": "16:34:29", "throughput": 554.38, "total_tokens": 2625352}
+{"current_steps": 255, "total_steps": 3400, "loss": 0.7408, "lr": 9.98292246503335e-05, "epoch": 0.06567087303631212, "percentage": 7.5, "elapsed_time": "1:20:28", "remaining_time": "16:32:30", "throughput": 554.67, "total_tokens": 2678216}
+{"current_steps": 260, "total_steps": 3400, "loss": 0.7044, "lr": 9.980855572238714e-05, "epoch": 0.06695853721349472, "percentage": 7.65, "elapsed_time": "1:21:57", "remaining_time": "16:29:49", "throughput": 555.29, "total_tokens": 2730664}
+{"current_steps": 265, "total_steps": 3400, "loss": 0.7334, "lr": 9.978670881475172e-05, "epoch": 0.06824620139067732, "percentage": 7.79, "elapsed_time": "1:23:25", "remaining_time": "16:26:51", "throughput": 556.14, "total_tokens": 2783584}
+{"current_steps": 270, "total_steps": 3400, "loss": 0.7075, "lr": 9.976368444410985e-05, "epoch": 0.0695338655678599, "percentage": 7.94, "elapsed_time": "1:24:53", "remaining_time": "16:24:09", "throughput": 556.79, "total_tokens": 2836152}
+{"current_steps": 275, "total_steps": 3400, "loss": 0.7039, "lr": 9.973948315499126e-05, "epoch": 0.0708215297450425, "percentage": 8.09, "elapsed_time": "1:26:21", "remaining_time": "16:21:18", "throughput": 557.35, "total_tokens": 2887808}
+{"current_steps": 280, "total_steps": 3400, "loss": 0.6953, "lr": 9.971410551976002e-05, "epoch": 0.07210919392222509, "percentage": 8.24, "elapsed_time": "1:27:50", "remaining_time": "16:18:43", "throughput": 557.81, "total_tokens": 2939656}
+{"current_steps": 285, "total_steps": 3400, "loss": 0.7022, "lr": 9.968755213860094e-05, "epoch": 0.07339685809940767, "percentage": 8.38, "elapsed_time": "1:29:17", "remaining_time": "16:15:56", "throughput": 558.4, "total_tokens": 2991632}
+{"current_steps": 290, "total_steps": 3400, "loss": 0.6796, "lr": 9.96598236395054e-05, "epoch": 0.07468452227659027, "percentage": 8.53, "elapsed_time": "1:30:45", "remaining_time": "16:13:18", "throughput": 558.92, "total_tokens": 3043616}
+{"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}