Training in progress, step 1400

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3ce6daf3c20e1ee39c6a4135462748b3119e8e74d43e226b9b4b7810797d2c9
+oid sha256:a1c7ec080c49b4ded7d9add721716bdf06187fb00c39ff223f5982466d466c72
 size 29034840

trainer_log.jsonl

@@ -299,3 +299,14 @@
 {"current_steps": 1345, "total_steps": 3400, "loss": 0.4608, "lr": 7.07506410132501e-05, "epoch": 0.3463816636621169, "percentage": 39.56, "elapsed_time": "3:53:14", "remaining_time": "5:56:22", "throughput": 1009.05, "total_tokens": 14121272}
 {"current_steps": 1350, "total_steps": 3400, "loss": 0.3994, "lr": 7.052916818778918e-05, "epoch": 0.3476693278392995, "percentage": 39.71, "elapsed_time": "3:54:42", "remaining_time": "5:56:24", "throughput": 1006.46, "total_tokens": 14173240}
 {"current_steps": 1350, "total_steps": 3400, "eval_loss": 0.460835725069046, "epoch": 0.3476693278392995, "percentage": 39.71, "elapsed_time": "3:55:20", "remaining_time": "5:57:22", "throughput": 1003.72, "total_tokens": 14173240}
+{"current_steps": 1355, "total_steps": 3400, "loss": 0.41, "lr": 7.030720984447279e-05, "epoch": 0.3489569920164821, "percentage": 39.85, "elapsed_time": "3:56:54", "remaining_time": "5:57:33", "throughput": 1000.79, "total_tokens": 14226032}
+{"current_steps": 1360, "total_steps": 3400, "loss": 0.3751, "lr": 7.008477123264848e-05, "epoch": 0.3502446561936647, "percentage": 40.0, "elapsed_time": "3:58:22", "remaining_time": "5:57:33", "throughput": 998.33, "total_tokens": 14278128}
+{"current_steps": 1365, "total_steps": 3400, "loss": 0.4814, "lr": 6.986185761302224e-05, "epoch": 0.3515323203708473, "percentage": 40.15, "elapsed_time": "3:59:49", "remaining_time": "5:57:32", "throughput": 995.92, "total_tokens": 14330624}
+{"current_steps": 1370, "total_steps": 3400, "loss": 0.5007, "lr": 6.963847425753403e-05, "epoch": 0.3528199845480299, "percentage": 40.29, "elapsed_time": "4:01:16", "remaining_time": "5:57:31", "throughput": 993.47, "total_tokens": 14382416}
+{"current_steps": 1375, "total_steps": 3400, "loss": 0.4335, "lr": 6.941462644923318e-05, "epoch": 0.35410764872521244, "percentage": 40.44, "elapsed_time": "4:02:44", "remaining_time": "5:57:29", "throughput": 991.11, "total_tokens": 14434896}
+{"current_steps": 1380, "total_steps": 3400, "loss": 0.4427, "lr": 6.919031948215335e-05, "epoch": 0.35539531290239507, "percentage": 40.59, "elapsed_time": "4:04:12", "remaining_time": "5:57:28", "throughput": 988.7, "total_tokens": 14487152}
+{"current_steps": 1385, "total_steps": 3400, "loss": 0.42, "lr": 6.896555866118741e-05, "epoch": 0.35668297707957763, "percentage": 40.74, "elapsed_time": "4:05:39", "remaining_time": "5:57:24", "throughput": 986.43, "total_tokens": 14539608}
+{"current_steps": 1390, "total_steps": 3400, "loss": 0.4573, "lr": 6.87403493019619e-05, "epoch": 0.35797064125676026, "percentage": 40.88, "elapsed_time": "4:07:08", "remaining_time": "5:57:22", "throughput": 984.08, "total_tokens": 14592168}
+{"current_steps": 1395, "total_steps": 3400, "loss": 0.4341, "lr": 6.851469673071143e-05, "epoch": 0.3592583054339428, "percentage": 41.03, "elapsed_time": "4:08:35", "remaining_time": "5:57:17", "throughput": 981.81, "total_tokens": 14643920}
+{"current_steps": 1400, "total_steps": 3400, "loss": 0.437, "lr": 6.828860628415253e-05, "epoch": 0.3605459696111254, "percentage": 41.18, "elapsed_time": "4:10:03", "remaining_time": "5:57:13", "throughput": 979.58, "total_tokens": 14697136}
+{"current_steps": 1400, "total_steps": 3400, "eval_loss": 0.46620962023735046, "epoch": 0.3605459696111254, "percentage": 41.18, "elapsed_time": "4:10:41", "remaining_time": "5:58:08", "throughput": 977.08, "total_tokens": 14697136}