Training in progress, step 300

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea0e59edded26f764540e30e37224e6309622e9f0d8713fac942b2956b39deb3
+oid sha256:8c6b6b2163a165d1469f79ac83287cf58b9febbee9aa4bb628b13cd978a905d2
 size 29034840

trainer_log.jsonl

@@ -53,3 +53,14 @@
 {"current_steps": 245, "total_steps": 3400, "loss": 0.0565, "lr": 9.986702663973722e-05, "epoch": 0.1261910893638939, "percentage": 7.21, "elapsed_time": "1:14:02", "remaining_time": "15:53:33", "throughput": 550.56, "total_tokens": 2446080}
 {"current_steps": 250, "total_steps": 3400, "loss": 0.0805, "lr": 9.98487151097676e-05, "epoch": 0.12876641771825909, "percentage": 7.35, "elapsed_time": "1:15:30", "remaining_time": "15:51:18", "throughput": 550.98, "total_tokens": 2496000}
 {"current_steps": 250, "total_steps": 3400, "eval_loss": 0.055875860154628754, "epoch": 0.12876641771825909, "percentage": 7.35, "elapsed_time": "1:15:49", "remaining_time": "15:55:24", "throughput": 548.62, "total_tokens": 2496000}
+{"current_steps": 255, "total_steps": 3400, "loss": 0.0235, "lr": 9.98292246503335e-05, "epoch": 0.13134174607262425, "percentage": 7.5, "elapsed_time": "1:17:21", "remaining_time": "15:54:02", "throughput": 548.54, "total_tokens": 2545920}
+{"current_steps": 260, "total_steps": 3400, "loss": 0.0137, "lr": 9.980855572238714e-05, "epoch": 0.13391707442698944, "percentage": 7.65, "elapsed_time": "1:18:48", "remaining_time": "15:51:46", "throughput": 548.97, "total_tokens": 2595840}
+{"current_steps": 265, "total_steps": 3400, "loss": 0.0605, "lr": 9.978670881475172e-05, "epoch": 0.13649240278135463, "percentage": 7.79, "elapsed_time": "1:20:15", "remaining_time": "15:49:23", "throughput": 549.47, "total_tokens": 2645760}
+{"current_steps": 270, "total_steps": 3400, "loss": 0.0585, "lr": 9.976368444410985e-05, "epoch": 0.1390677311357198, "percentage": 7.94, "elapsed_time": "1:21:42", "remaining_time": "15:47:09", "throughput": 549.89, "total_tokens": 2695680}
+{"current_steps": 275, "total_steps": 3400, "loss": 0.0096, "lr": 9.973948315499126e-05, "epoch": 0.141643059490085, "percentage": 8.09, "elapsed_time": "1:23:08", "remaining_time": "15:44:48", "throughput": 550.37, "total_tokens": 2745600}
+{"current_steps": 280, "total_steps": 3400, "loss": 0.1383, "lr": 9.971410551976002e-05, "epoch": 0.14421838784445018, "percentage": 8.24, "elapsed_time": "1:24:35", "remaining_time": "15:42:37", "throughput": 550.77, "total_tokens": 2795520}
+{"current_steps": 285, "total_steps": 3400, "loss": 0.049, "lr": 9.968755213860094e-05, "epoch": 0.14679371619881534, "percentage": 8.38, "elapsed_time": "1:26:02", "remaining_time": "15:40:23", "throughput": 551.19, "total_tokens": 2845440}
+{"current_steps": 290, "total_steps": 3400, "loss": 0.0336, "lr": 9.96598236395054e-05, "epoch": 0.14936904455318054, "percentage": 8.53, "elapsed_time": "1:27:29", "remaining_time": "15:38:15", "throughput": 551.56, "total_tokens": 2895360}
+{"current_steps": 295, "total_steps": 3400, "loss": 0.019, "lr": 9.96309206782565e-05, "epoch": 0.1519443729075457, "percentage": 8.68, "elapsed_time": "1:28:55", "remaining_time": "15:36:01", "throughput": 551.98, "total_tokens": 2945280}
+{"current_steps": 300, "total_steps": 3400, "loss": 0.0381, "lr": 9.960084393841355e-05, "epoch": 0.1545197012619109, "percentage": 8.82, "elapsed_time": "1:30:22", "remaining_time": "15:33:51", "throughput": 552.37, "total_tokens": 2995200}
+{"current_steps": 300, "total_steps": 3400, "eval_loss": 0.030908752232789993, "epoch": 0.1545197012619109, "percentage": 8.82, "elapsed_time": "1:30:42", "remaining_time": "15:37:17", "throughput": 550.35, "total_tokens": 2995200}