Training in progress, step 700

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdc08534aac7838c266708395ae95ee206c6d0313a225f23be71ea0622c11781
+oid sha256:1d425bc219a9d654d836fee0b4aa2ca86744dd40b8005ba8f3882e419b82dad4
 size 25200088

trainer_log.jsonl

@@ -76,3 +76,9 @@
 {"current_steps": 640, "total_steps": 1500, "loss": 0.2598, "accuracy": 0.925000011920929, "learning_rate": 3.0708771752766397e-06, "epoch": 0.5683836589698046, "percentage": 42.67, "elapsed_time": "1:26:45", "remaining_time": "1:56:35", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 650, "total_steps": 1500, "loss": 0.2453, "accuracy": 0.9375, "learning_rate": 3.019779227044398e-06, "epoch": 0.5772646536412078, "percentage": 43.33, "elapsed_time": "1:28:00", "remaining_time": "1:55:05", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 650, "total_steps": 1500, "eval_loss": 0.27302286028862, "epoch": 0.5772646536412078, "percentage": 43.33, "elapsed_time": "1:28:25", "remaining_time": "1:55:38", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 660, "total_steps": 1500, "loss": 0.2726, "accuracy": 0.8374999761581421, "learning_rate": 2.9684532864643123e-06, "epoch": 0.5861456483126111, "percentage": 44.0, "elapsed_time": "1:29:47", "remaining_time": "1:54:16", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 670, "total_steps": 1500, "loss": 0.2484, "accuracy": 0.887499988079071, "learning_rate": 2.9169218667902562e-06, "epoch": 0.5950266429840142, "percentage": 44.67, "elapsed_time": "1:31:02", "remaining_time": "1:52:47", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 680, "total_steps": 1500, "loss": 0.2144, "accuracy": 0.987500011920929, "learning_rate": 2.8652075714060296e-06, "epoch": 0.6039076376554174, "percentage": 45.33, "elapsed_time": "1:32:22", "remaining_time": "1:51:23", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 690, "total_steps": 1500, "loss": 0.2861, "accuracy": 0.925000011920929, "learning_rate": 2.813333083910761e-06, "epoch": 0.6127886323268206, "percentage": 46.0, "elapsed_time": "1:33:41", "remaining_time": "1:49:58", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 700, "total_steps": 1500, "loss": 0.2885, "accuracy": 0.887499988079071, "learning_rate": 2.761321158169134e-06, "epoch": 0.6216696269982238, "percentage": 46.67, "elapsed_time": "1:34:56", "remaining_time": "1:48:30", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 700, "total_steps": 1500, "eval_loss": 0.26512712240219116, "epoch": 0.6216696269982238, "percentage": 46.67, "elapsed_time": "1:35:22", "remaining_time": "1:48:59", "throughput": "0.00", "total_tokens": 0}