Training in progress, step 1500

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e588a14bf8c6084e2c48f8095f996da7105c630f6b3c4db9466a4c3d0ede278
+oid sha256:cd8be0169f34a82b94751e4c00a153b79325d2105c366548e39c4888d2d89543
 size 25200088

trainer_log.jsonl

@@ -172,3 +172,10 @@
 {"current_steps": 1440, "total_steps": 1500, "loss": 0.2167, "accuracy": 0.925000011920929, "learning_rate": 1.9713246713805588e-08, "epoch": 1.198147569986471, "percentage": 96.0, "elapsed_time": "3:21:29", "remaining_time": "0:08:23", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 1450, "total_steps": 1500, "loss": 0.1655, "accuracy": 0.9125000238418579, "learning_rate": 1.3695261579316776e-08, "epoch": 1.2064730981371632, "percentage": 96.67, "elapsed_time": "3:22:45", "remaining_time": "0:06:59", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 1450, "total_steps": 1500, "eval_loss": 0.21536922454833984, "epoch": 1.2064730981371632, "percentage": 96.67, "elapsed_time": "3:23:14", "remaining_time": "0:07:00", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1460, "total_steps": 1500, "loss": 0.1886, "accuracy": 0.925000011920929, "learning_rate": 8.767851876239075e-09, "epoch": 1.2147986262878552, "percentage": 97.33, "elapsed_time": "3:24:35", "remaining_time": "0:05:36", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1470, "total_steps": 1500, "loss": 0.1917, "accuracy": 0.949999988079071, "learning_rate": 4.933178929321103e-09, "epoch": 1.2231241544385472, "percentage": 98.0, "elapsed_time": "3:25:54", "remaining_time": "0:04:12", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1480, "total_steps": 1500, "loss": 0.1683, "accuracy": 0.8999999761581421, "learning_rate": 2.192924752854042e-09, "epoch": 1.2314496825892394, "percentage": 98.67, "elapsed_time": "3:27:15", "remaining_time": "0:02:48", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1490, "total_steps": 1500, "loss": 0.1915, "accuracy": 0.949999988079071, "learning_rate": 5.48291312886251e-10, "epoch": 1.2397752107399314, "percentage": 99.33, "elapsed_time": "3:28:29", "remaining_time": "0:01:23", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1500, "total_steps": 1500, "loss": 0.2109, "accuracy": 0.9624999761581421, "learning_rate": 0.0, "epoch": 1.2481007388906233, "percentage": 100.0, "elapsed_time": "3:29:47", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1500, "total_steps": 1500, "eval_loss": 0.21422816812992096, "epoch": 1.2481007388906233, "percentage": 100.0, "elapsed_time": "3:30:16", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1500, "total_steps": 1500, "epoch": 1.2481007388906233, "percentage": 100.0, "elapsed_time": "3:30:22", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}