Training in progress, step 900

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98b4d557f50be34280bd9d894919bfa69b4c61751b23a62ce97e416718516be8
+oid sha256:f249beea73a99517aa1b04e241c58d5ad0dbb1e964b6dafbb97a9a57d9494130
 size 25200088

trainer_log.jsonl

@@ -100,3 +100,9 @@
 {"current_steps": 840, "total_steps": 1500, "loss": 0.2584, "accuracy": 0.9125000238418579, "learning_rate": 2.031546713535688e-06, "epoch": 1.3170492446537179, "percentage": 56.0, "elapsed_time": "1:52:17", "remaining_time": "1:28:13", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 850, "total_steps": 1500, "loss": 0.2242, "accuracy": 0.9125000238418579, "learning_rate": 1.9802207729556023e-06, "epoch": 1.332744751814793, "percentage": 56.67, "elapsed_time": "1:53:35", "remaining_time": "1:26:51", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 850, "total_steps": 1500, "eval_loss": 0.2621641755104065, "epoch": 1.332744751814793, "percentage": 56.67, "elapsed_time": "1:53:49", "remaining_time": "1:27:02", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 860, "total_steps": 1500, "loss": 0.2711, "accuracy": 0.9125000238418579, "learning_rate": 1.9291228247233607e-06, "epoch": 1.3484402589758682, "percentage": 57.33, "elapsed_time": "1:55:13", "remaining_time": "1:25:45", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 870, "total_steps": 1500, "loss": 0.2569, "accuracy": 0.9624999761581421, "learning_rate": 1.8782752820878636e-06, "epoch": 1.3641357661369433, "percentage": 58.0, "elapsed_time": "1:56:28", "remaining_time": "1:24:20", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 880, "total_steps": 1500, "loss": 0.2876, "accuracy": 0.925000011920929, "learning_rate": 1.827700448461836e-06, "epoch": 1.3798312732980185, "percentage": 58.67, "elapsed_time": "1:57:46", "remaining_time": "1:22:58", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 890, "total_steps": 1500, "loss": 0.2502, "accuracy": 0.925000011920929, "learning_rate": 1.7774205076388207e-06, "epoch": 1.3955267804590936, "percentage": 59.33, "elapsed_time": "1:59:02", "remaining_time": "1:21:35", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 900, "total_steps": 1500, "loss": 0.2162, "accuracy": 0.9624999761581421, "learning_rate": 1.7274575140626318e-06, "epoch": 1.4112222876201688, "percentage": 60.0, "elapsed_time": "2:00:20", "remaining_time": "1:20:13", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 900, "total_steps": 1500, "eval_loss": 0.2529076933860779, "epoch": 1.4112222876201688, "percentage": 60.0, "elapsed_time": "2:00:34", "remaining_time": "1:20:23", "throughput": "0.00", "total_tokens": 0}