Training in progress, step 550

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32d6d14f8c29da8cdb8be1658c159a9d27e00215388ecaf0c21dc7d9ce80b66e
+oid sha256:8ea0b12291caef0384f7fd3bc0b1e4fc7815f7b867e0e565a267ef13238fd6a9
 size 29034840

trainer_log.jsonl

@@ -109,3 +109,14 @@
 {"current_steps": 495, "total_steps": 6770, "loss": 0.6641, "lr": 9.985488184785336e-05, "epoch": 0.14623338257016247, "percentage": 7.31, "elapsed_time": "2:28:38", "remaining_time": "1 day, 7:24:18", "throughput": 575.4, "total_tokens": 5131744}
 {"current_steps": 500, "total_steps": 6770, "loss": 0.6283, "lr": 9.984543519704557e-05, "epoch": 0.14771048744460857, "percentage": 7.39, "elapsed_time": "2:30:03", "remaining_time": "1 day, 7:21:48", "throughput": 575.71, "total_tokens": 5183664}
 {"current_steps": 500, "total_steps": 6770, "eval_loss": 0.6505001187324524, "epoch": 0.14771048744460857, "percentage": 7.39, "elapsed_time": "2:30:22", "remaining_time": "1 day, 7:25:46", "throughput": 574.51, "total_tokens": 5183664}
+{"current_steps": 505, "total_steps": 6770, "loss": 0.573, "lr": 9.983569116887128e-05, "epoch": 0.14918759231905465, "percentage": 7.46, "elapsed_time": "2:31:55", "remaining_time": "1 day, 7:24:45", "throughput": 574.29, "total_tokens": 5234920}
+{"current_steps": 510, "total_steps": 6770, "loss": 0.6261, "lr": 9.982564982146327e-05, "epoch": 0.15066469719350073, "percentage": 7.53, "elapsed_time": "2:33:20", "remaining_time": "1 day, 7:22:15", "throughput": 574.66, "total_tokens": 5287312}
+{"current_steps": 515, "total_steps": 6770, "loss": 0.6072, "lr": 9.981531121472811e-05, "epoch": 0.15214180206794684, "percentage": 7.61, "elapsed_time": "2:34:47", "remaining_time": "1 day, 7:20:02", "throughput": 574.99, "total_tokens": 5340240}
+{"current_steps": 520, "total_steps": 6770, "loss": 0.565, "lr": 9.980467541034584e-05, "epoch": 0.1536189069423929, "percentage": 7.68, "elapsed_time": "2:36:13", "remaining_time": "1 day, 7:17:38", "throughput": 575.32, "total_tokens": 5392600}
+{"current_steps": 525, "total_steps": 6770, "loss": 0.6188, "lr": 9.979374247176956e-05, "epoch": 0.155096011816839, "percentage": 7.75, "elapsed_time": "2:37:39", "remaining_time": "1 day, 7:15:27", "throughput": 575.61, "total_tokens": 5445168}
+{"current_steps": 530, "total_steps": 6770, "loss": 0.6069, "lr": 9.978251246422505e-05, "epoch": 0.15657311669128507, "percentage": 7.83, "elapsed_time": "2:39:05", "remaining_time": "1 day, 7:13:06", "throughput": 575.8, "total_tokens": 5496384}
+{"current_steps": 535, "total_steps": 6770, "loss": 0.5805, "lr": 9.977098545471046e-05, "epoch": 0.15805022156573117, "percentage": 7.9, "elapsed_time": "2:40:32", "remaining_time": "1 day, 7:10:58", "throughput": 576.0, "total_tokens": 5548264}
+{"current_steps": 540, "total_steps": 6770, "loss": 0.6383, "lr": 9.975916151199579e-05, "epoch": 0.15952732644017725, "percentage": 7.98, "elapsed_time": "2:41:58", "remaining_time": "1 day, 7:08:47", "throughput": 576.12, "total_tokens": 5599216}
+{"current_steps": 545, "total_steps": 6770, "loss": 0.5845, "lr": 9.974704070662254e-05, "epoch": 0.16100443131462333, "percentage": 8.05, "elapsed_time": "2:43:27", "remaining_time": "1 day, 7:06:58", "throughput": 576.19, "total_tokens": 5650816}
+{"current_steps": 550, "total_steps": 6770, "loss": 0.5957, "lr": 9.973462311090336e-05, "epoch": 0.16248153618906944, "percentage": 8.12, "elapsed_time": "2:44:53", "remaining_time": "1 day, 7:04:48", "throughput": 576.43, "total_tokens": 5703016}
+{"current_steps": 550, "total_steps": 6770, "eval_loss": 0.6883422136306763, "epoch": 0.16248153618906944, "percentage": 8.12, "elapsed_time": "2:45:12", "remaining_time": "1 day, 7:08:25", "throughput": 575.31, "total_tokens": 5703016}