Training in progress, step 500

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e3aaf9e6c8d830995b2a237a6a326491ecc141ce2f9713c7cafa4ab230f17cb
+oid sha256:32d6d14f8c29da8cdb8be1658c159a9d27e00215388ecaf0c21dc7d9ce80b66e
 size 29034840

trainer_log.jsonl

@@ -98,3 +98,14 @@
 {"current_steps": 445, "total_steps": 6770, "loss": 0.6526, "lr": 9.993298108049582e-05, "epoch": 0.13146233382570163, "percentage": 6.57, "elapsed_time": "2:13:50", "remaining_time": "1 day, 7:42:20", "throughput": 574.21, "total_tokens": 4611184}
 {"current_steps": 450, "total_steps": 6770, "loss": 0.5661, "lr": 9.992651101018445e-05, "epoch": 0.1329394387001477, "percentage": 6.65, "elapsed_time": "2:15:17", "remaining_time": "1 day, 7:40:00", "throughput": 574.5, "total_tokens": 4663320}
 {"current_steps": 450, "total_steps": 6770, "eval_loss": 0.7132604718208313, "epoch": 0.1329394387001477, "percentage": 6.65, "elapsed_time": "2:15:36", "remaining_time": "1 day, 7:44:27", "throughput": 573.16, "total_tokens": 4663320}
+{"current_steps": 455, "total_steps": 6770, "loss": 0.5954, "lr": 9.991974307880907e-05, "epoch": 0.1344165435745938, "percentage": 6.72, "elapsed_time": "2:17:08", "remaining_time": "1 day, 7:43:19", "throughput": 572.96, "total_tokens": 4714448}
+{"current_steps": 460, "total_steps": 6770, "loss": 0.721, "lr": 9.991267732674711e-05, "epoch": 0.1358936484490399, "percentage": 6.79, "elapsed_time": "2:18:34", "remaining_time": "1 day, 7:40:59", "throughput": 573.32, "total_tokens": 4767136}
+{"current_steps": 465, "total_steps": 6770, "loss": 0.6578, "lr": 9.99053137961528e-05, "epoch": 0.13737075332348597, "percentage": 6.87, "elapsed_time": "2:20:00", "remaining_time": "1 day, 7:38:26", "throughput": 573.69, "total_tokens": 4819408}
+{"current_steps": 470, "total_steps": 6770, "loss": 0.6642, "lr": 9.989765253095686e-05, "epoch": 0.13884785819793205, "percentage": 6.94, "elapsed_time": "2:21:27", "remaining_time": "1 day, 7:36:03", "throughput": 574.06, "total_tokens": 4872120}
+{"current_steps": 475, "total_steps": 6770, "loss": 0.6462, "lr": 9.988969357686636e-05, "epoch": 0.14032496307237813, "percentage": 7.02, "elapsed_time": "2:22:53", "remaining_time": "1 day, 7:33:40", "throughput": 574.38, "total_tokens": 4924400}
+{"current_steps": 480, "total_steps": 6770, "loss": 0.6055, "lr": 9.988143698136429e-05, "epoch": 0.14180206794682423, "percentage": 7.09, "elapsed_time": "2:24:19", "remaining_time": "1 day, 7:31:09", "throughput": 574.72, "total_tokens": 4976504}
+{"current_steps": 485, "total_steps": 6770, "loss": 0.5928, "lr": 9.987288279370945e-05, "epoch": 0.1432791728212703, "percentage": 7.16, "elapsed_time": "2:25:46", "remaining_time": "1 day, 7:28:59", "throughput": 574.96, "total_tokens": 5028648}
+{"current_steps": 490, "total_steps": 6770, "loss": 0.5835, "lr": 9.986403106493604e-05, "epoch": 0.1447562776957164, "percentage": 7.24, "elapsed_time": "2:27:11", "remaining_time": "1 day, 7:26:26", "throughput": 575.27, "total_tokens": 5080488}
+{"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}