Training in progress, step 800

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb873b27a0ddbd459a54abf7c399a01453a2e748ed4875561bd6cfe3333f2007
+oid sha256:59e3913cdb218f4940e97110368dad2d1faea4555e2d3be9b765ca062f909214
 size 25200088

trainer_log.jsonl

@@ -88,3 +88,9 @@
 {"current_steps": 740, "total_steps": 1500, "loss": 0.2103, "accuracy": 0.949999988079071, "learning_rate": 2.5523560497083927e-06, "epoch": 0.6360120326600773, "percentage": 49.33, "elapsed_time": "1:37:00", "remaining_time": "1:39:37", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 750, "total_steps": 1500, "loss": 0.2545, "accuracy": 0.949999988079071, "learning_rate": 2.5e-06, "epoch": 0.6446067898581865, "percentage": 50.0, "elapsed_time": "1:38:13", "remaining_time": "1:38:13", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 750, "total_steps": 1500, "eval_loss": 0.2537091076374054, "epoch": 0.6446067898581865, "percentage": 50.0, "elapsed_time": "1:38:39", "remaining_time": "1:38:39", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 760, "total_steps": 1500, "loss": 0.2261, "accuracy": 0.9375, "learning_rate": 2.447643950291608e-06, "epoch": 0.6532015470562956, "percentage": 50.67, "elapsed_time": "1:40:01", "remaining_time": "1:37:23", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 770, "total_steps": 1500, "loss": 0.2703, "accuracy": 0.862500011920929, "learning_rate": 2.3953108656770018e-06, "epoch": 0.6617963042544048, "percentage": 51.33, "elapsed_time": "1:41:13", "remaining_time": "1:35:57", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 780, "total_steps": 1500, "loss": 0.2493, "accuracy": 0.987500011920929, "learning_rate": 2.3430237011767166e-06, "epoch": 0.6703910614525139, "percentage": 52.0, "elapsed_time": "1:42:26", "remaining_time": "1:34:34", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 790, "total_steps": 1500, "loss": 0.2461, "accuracy": 0.925000011920929, "learning_rate": 2.290805391669212e-06, "epoch": 0.6789858186506231, "percentage": 52.67, "elapsed_time": "1:43:39", "remaining_time": "1:33:09", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 800, "total_steps": 1500, "loss": 0.2483, "accuracy": 0.925000011920929, "learning_rate": 2.238678841830867e-06, "epoch": 0.6875805758487322, "percentage": 53.33, "elapsed_time": "1:44:51", "remaining_time": "1:31:45", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 800, "total_steps": 1500, "eval_loss": 0.24035032093524933, "epoch": 0.6875805758487322, "percentage": 53.33, "elapsed_time": "1:45:17", "remaining_time": "1:32:07", "throughput": "0.00", "total_tokens": 0}