Training in progress, step 650

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:328b21d2c090dc5d8d48f292fea2a2473e00c415504c791f02afa73fa45bba78
+oid sha256:2085ab8d4d2457ed74dedab6db602a59933815e6f950c79017393efbd9785716
 size 25200088

trainer_log.jsonl

@@ -70,3 +70,9 @@
 {"current_steps": 590, "total_steps": 1500, "loss": 0.2839, "accuracy": 0.887499988079071, "learning_rate": 3.3221666168464584e-06, "epoch": 0.47628657921291623, "percentage": 39.33, "elapsed_time": "1:21:57", "remaining_time": "2:06:24", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 600, "total_steps": 1500, "loss": 0.3237, "accuracy": 0.875, "learning_rate": 3.272542485937369e-06, "epoch": 0.4843592330978809, "percentage": 40.0, "elapsed_time": "1:23:10", "remaining_time": "2:04:45", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 600, "total_steps": 1500, "eval_loss": 0.2827170193195343, "epoch": 0.4843592330978809, "percentage": 40.0, "elapsed_time": "1:23:39", "remaining_time": "2:05:29", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 610, "total_steps": 1500, "loss": 0.2986, "accuracy": 0.8500000238418579, "learning_rate": 3.222579492361179e-06, "epoch": 0.4924318869828456, "percentage": 40.67, "elapsed_time": "1:25:14", "remaining_time": "2:04:22", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 620, "total_steps": 1500, "loss": 0.2776, "accuracy": 0.925000011920929, "learning_rate": 3.1722995515381644e-06, "epoch": 0.5005045408678103, "percentage": 41.33, "elapsed_time": "1:26:34", "remaining_time": "2:02:53", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 630, "total_steps": 1500, "loss": 0.2688, "accuracy": 0.8374999761581421, "learning_rate": 3.121724717912138e-06, "epoch": 0.508577194752775, "percentage": 42.0, "elapsed_time": "1:27:51", "remaining_time": "2:01:20", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 640, "total_steps": 1500, "loss": 0.2435, "accuracy": 0.9125000238418579, "learning_rate": 3.0708771752766397e-06, "epoch": 0.5166498486377397, "percentage": 42.67, "elapsed_time": "1:29:02", "remaining_time": "1:59:38", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 650, "total_steps": 1500, "loss": 0.2865, "accuracy": 0.8999999761581421, "learning_rate": 3.019779227044398e-06, "epoch": 0.5247225025227044, "percentage": 43.33, "elapsed_time": "1:30:16", "remaining_time": "1:58:02", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 650, "total_steps": 1500, "eval_loss": 0.25649499893188477, "epoch": 0.5247225025227044, "percentage": 43.33, "elapsed_time": "1:30:45", "remaining_time": "1:58:41", "throughput": "0.00", "total_tokens": 0}