Training in progress, step 750

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88ae170a3982b503eb5beb995f6497de80bd35014cb3c23e14aea414cec3f39d
+oid sha256:44891068fa51f1b4640132ae32ba98fa9ebe29969042e52331d1881d58a81d4d
 size 25200088

trainer_log.jsonl

@@ -82,3 +82,9 @@
 {"current_steps": 690, "total_steps": 1500, "loss": 0.3451, "accuracy": 0.925000011920929, "learning_rate": 2.813333083910761e-06, "epoch": 0.8761904761904762, "percentage": 46.0, "elapsed_time": "1:34:43", "remaining_time": "1:51:12", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 700, "total_steps": 1500, "loss": 0.4094, "accuracy": 0.8500000238418579, "learning_rate": 2.761321158169134e-06, "epoch": 0.8888888888888888, "percentage": 46.67, "elapsed_time": "1:35:57", "remaining_time": "1:49:40", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 700, "total_steps": 1500, "eval_loss": 0.33448922634124756, "epoch": 0.8888888888888888, "percentage": 46.67, "elapsed_time": "1:36:15", "remaining_time": "1:50:01", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 710, "total_steps": 1500, "loss": 0.3604, "accuracy": 0.925000011920929, "learning_rate": 2.70919460833079e-06, "epoch": 0.9015873015873016, "percentage": 47.33, "elapsed_time": "1:37:45", "remaining_time": "1:48:46", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 720, "total_steps": 1500, "loss": 0.3682, "accuracy": 0.9375, "learning_rate": 2.6569762988232838e-06, "epoch": 0.9142857142857143, "percentage": 48.0, "elapsed_time": "1:38:59", "remaining_time": "1:47:14", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 730, "total_steps": 1500, "loss": 0.3886, "accuracy": 0.8500000238418579, "learning_rate": 2.604689134322999e-06, "epoch": 0.926984126984127, "percentage": 48.67, "elapsed_time": "1:40:12", "remaining_time": "1:45:42", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 740, "total_steps": 1500, "loss": 0.3548, "accuracy": 0.9125000238418579, "learning_rate": 2.5523560497083927e-06, "epoch": 0.9396825396825397, "percentage": 49.33, "elapsed_time": "1:41:30", "remaining_time": "1:44:15", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 750, "total_steps": 1500, "loss": 0.3706, "accuracy": 0.925000011920929, "learning_rate": 2.5e-06, "epoch": 0.9523809523809523, "percentage": 50.0, "elapsed_time": "1:42:48", "remaining_time": "1:42:48", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 750, "total_steps": 1500, "eval_loss": 0.31834185123443604, "epoch": 0.9523809523809523, "percentage": 50.0, "elapsed_time": "1:43:06", "remaining_time": "1:43:06", "throughput": "0.00", "total_tokens": 0}