Training in progress, step 1350

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa15e07fd4419200f8e9989890744a7dc7ba3f56b0226237de1bc9d182afbe27
+oid sha256:4f522cf654498d859df32a42e97e21b3c82838dfdb72db544a95b5146f2f1c95
 size 40036488

trainer_log.jsonl

@@ -154,3 +154,9 @@
 {"current_steps": 1290, "total_steps": 1500, "loss": 0.7141, "accuracy": 0.9750000238418579, "learning_rate": 2.3793236883495164e-07, "epoch": 1.0582683627410752, "percentage": 86.0, "elapsed_time": "2:51:06", "remaining_time": "0:27:51", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 1300, "total_steps": 1500, "loss": 0.6253, "accuracy": 0.9624999761581421, "learning_rate": 2.1613635589349756e-07, "epoch": 1.0664751743947476, "percentage": 86.67, "elapsed_time": "2:52:23", "remaining_time": "0:26:31", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 1300, "total_steps": 1500, "eval_loss": 0.0825350433588028, "epoch": 1.0664751743947476, "percentage": 86.67, "elapsed_time": "2:52:49", "remaining_time": "0:26:35", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1310, "total_steps": 1500, "loss": 0.7902, "accuracy": 0.987500011920929, "learning_rate": 1.95342121028749e-07, "epoch": 1.0746819860484202, "percentage": 87.33, "elapsed_time": "2:54:15", "remaining_time": "0:25:16", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1320, "total_steps": 1500, "loss": 0.6974, "accuracy": 0.987500011920929, "learning_rate": 1.7555878527937164e-07, "epoch": 1.0828887977020927, "percentage": 88.0, "elapsed_time": "2:55:24", "remaining_time": "0:23:55", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1330, "total_steps": 1500, "loss": 0.6232, "accuracy": 0.987500011920929, "learning_rate": 1.567950262702714e-07, "epoch": 1.0910956093557653, "percentage": 88.67, "elapsed_time": "2:56:36", "remaining_time": "0:22:34", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1340, "total_steps": 1500, "loss": 0.5703, "accuracy": 0.9624999761581421, "learning_rate": 1.3905907440629752e-07, "epoch": 1.0993024210094378, "percentage": 89.33, "elapsed_time": "2:57:48", "remaining_time": "0:21:13", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1350, "total_steps": 1500, "loss": 0.6289, "accuracy": 1.0, "learning_rate": 1.223587092621162e-07, "epoch": 1.1075092326631104, "percentage": 90.0, "elapsed_time": "2:59:02", "remaining_time": "0:19:53", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1350, "total_steps": 1500, "eval_loss": 0.07863202691078186, "epoch": 1.1075092326631104, "percentage": 90.0, "elapsed_time": "2:59:28", "remaining_time": "0:19:56", "throughput": "0.00", "total_tokens": 0}