Training in progress, step 200

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7949774ded016d1a26cec57754466bac6d68a480485badc373577cbddb42d8f
+oid sha256:f459a64f85c3e786cc271d3b2898b3fbb51247160c3c9e890a41405e9c35e88c
 size 25200088

trainer_log.jsonl

@@ -16,3 +16,9 @@
 {"current_steps": 140, "total_steps": 1500, "loss": 0.9373, "accuracy": 0.42500001192092896, "learning_rate": 4.893298743830168e-06, "epoch": 0.14925373134328357, "percentage": 9.33, "elapsed_time": "0:18:47", "remaining_time": "3:02:35", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 150, "total_steps": 1500, "loss": 0.9388, "accuracy": 0.5375000238418579, "learning_rate": 4.8776412907378845e-06, "epoch": 0.15991471215351813, "percentage": 10.0, "elapsed_time": "0:20:03", "remaining_time": "3:00:35", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 150, "total_steps": 1500, "eval_loss": 0.9302574396133423, "epoch": 0.15991471215351813, "percentage": 10.0, "elapsed_time": "0:20:25", "remaining_time": "3:03:48", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 160, "total_steps": 1500, "loss": 0.9396, "accuracy": 0.512499988079071, "learning_rate": 4.860940925593703e-06, "epoch": 0.17057569296375266, "percentage": 10.67, "elapsed_time": "0:21:47", "remaining_time": "3:02:31", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 170, "total_steps": 1500, "loss": 0.9222, "accuracy": 0.5375000238418579, "learning_rate": 4.84320497372973e-06, "epoch": 0.1812366737739872, "percentage": 11.33, "elapsed_time": "0:23:01", "remaining_time": "3:00:05", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 180, "total_steps": 1500, "loss": 0.9052, "accuracy": 0.675000011920929, "learning_rate": 4.824441214720629e-06, "epoch": 0.19189765458422176, "percentage": 12.0, "elapsed_time": "0:24:16", "remaining_time": "2:57:59", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 190, "total_steps": 1500, "loss": 0.8996, "accuracy": 0.6875, "learning_rate": 4.804657878971252e-06, "epoch": 0.2025586353944563, "percentage": 12.67, "elapsed_time": "0:25:34", "remaining_time": "2:56:19", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 200, "total_steps": 1500, "loss": 0.9015, "accuracy": 0.5375000238418579, "learning_rate": 4.783863644106502e-06, "epoch": 0.21321961620469082, "percentage": 13.33, "elapsed_time": "0:26:50", "remaining_time": "2:54:28", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 200, "total_steps": 1500, "eval_loss": 0.8796805143356323, "epoch": 0.21321961620469082, "percentage": 13.33, "elapsed_time": "0:27:12", "remaining_time": "2:56:48", "throughput": "0.00", "total_tokens": 0}