Training in progress, step 200

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:858615ba8711149ca3bffaabea9993faf32ee41829ca40d166ca47a485008823
+oid sha256:249fffe476058092aeef5b427f5dc1ef1059380afd82cd41f1bba83ca17fafa3
 size 25200088

trainer_log.jsonl

@@ -16,3 +16,9 @@
 {"current_steps": 140, "total_steps": 1500, "loss": 0.9138, "accuracy": 0.5625, "learning_rate": 4.893298743830168e-06, "epoch": 0.12032660077352815, "percentage": 9.33, "elapsed_time": "0:18:12", "remaining_time": "2:56:55", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 150, "total_steps": 1500, "loss": 0.9157, "accuracy": 0.574999988079071, "learning_rate": 4.8776412907378845e-06, "epoch": 0.1289213579716373, "percentage": 10.0, "elapsed_time": "0:19:26", "remaining_time": "2:54:58", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 150, "total_steps": 1500, "eval_loss": 0.909102737903595, "epoch": 0.1289213579716373, "percentage": 10.0, "elapsed_time": "0:19:52", "remaining_time": "2:58:50", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 160, "total_steps": 1500, "loss": 0.9, "accuracy": 0.512499988079071, "learning_rate": 4.860940925593703e-06, "epoch": 0.13751611516974646, "percentage": 10.67, "elapsed_time": "0:21:11", "remaining_time": "2:57:27", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 170, "total_steps": 1500, "loss": 0.896, "accuracy": 0.637499988079071, "learning_rate": 4.84320497372973e-06, "epoch": 0.1461108723678556, "percentage": 11.33, "elapsed_time": "0:22:25", "remaining_time": "2:55:28", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 180, "total_steps": 1500, "loss": 0.8911, "accuracy": 0.5625, "learning_rate": 4.824441214720629e-06, "epoch": 0.15470562956596476, "percentage": 12.0, "elapsed_time": "0:23:38", "remaining_time": "2:53:25", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 190, "total_steps": 1500, "loss": 0.9002, "accuracy": 0.6000000238418579, "learning_rate": 4.804657878971252e-06, "epoch": 0.1633003867640739, "percentage": 12.67, "elapsed_time": "0:24:53", "remaining_time": "2:51:40", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 200, "total_steps": 1500, "loss": 0.8773, "accuracy": 0.574999988079071, "learning_rate": 4.783863644106502e-06, "epoch": 0.17189514396218306, "percentage": 13.33, "elapsed_time": "0:26:03", "remaining_time": "2:49:20", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 200, "total_steps": 1500, "eval_loss": 0.8721462488174438, "epoch": 0.17189514396218306, "percentage": 13.33, "elapsed_time": "0:26:28", "remaining_time": "2:52:08", "throughput": "0.00", "total_tokens": 0}