Training in progress, step 950

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e98fca858842e7fa2ad16e3d18b2e6d95e9f271d2650063c977b26872b359b1
+oid sha256:b85082754ebd16f8ce3cd8f5ce0ed26ba238e4624ff1345f5a9fb8ecffb27f4b
 size 40036488

trainer_log.jsonl

@@ -106,3 +106,9 @@
 {"current_steps": 890, "total_steps": 1500, "loss": 0.8304, "accuracy": 0.987500011920929, "learning_rate": 1.7774205076388207e-06, "epoch": 0.7304062371768568, "percentage": 59.33, "elapsed_time": "1:57:45", "remaining_time": "1:20:42", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 900, "total_steps": 1500, "loss": 0.7794, "accuracy": 0.925000011920929, "learning_rate": 1.7274575140626318e-06, "epoch": 0.7386130488305294, "percentage": 60.0, "elapsed_time": "1:58:56", "remaining_time": "1:19:17", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 900, "total_steps": 1500, "eval_loss": 0.11225885152816772, "epoch": 0.7386130488305294, "percentage": 60.0, "elapsed_time": "1:59:22", "remaining_time": "1:19:34", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 910, "total_steps": 1500, "loss": 0.8783, "accuracy": 0.9624999761581421, "learning_rate": 1.677833383153542e-06, "epoch": 0.7468198604842019, "percentage": 60.67, "elapsed_time": "2:00:46", "remaining_time": "1:18:18", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 920, "total_steps": 1500, "loss": 0.88, "accuracy": 0.949999988079071, "learning_rate": 1.6285698816954626e-06, "epoch": 0.7550266721378744, "percentage": 61.33, "elapsed_time": "2:02:00", "remaining_time": "1:16:55", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 930, "total_steps": 1500, "loss": 0.8804, "accuracy": 0.987500011920929, "learning_rate": 1.5796886182883053e-06, "epoch": 0.763233483791547, "percentage": 62.0, "elapsed_time": "2:03:10", "remaining_time": "1:15:29", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 940, "total_steps": 1500, "loss": 0.9232, "accuracy": 0.987500011920929, "learning_rate": 1.5312110338697427e-06, "epoch": 0.7714402954452195, "percentage": 62.67, "elapsed_time": "2:04:22", "remaining_time": "1:14:05", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 950, "total_steps": 1500, "loss": 0.6239, "accuracy": 0.9750000238418579, "learning_rate": 1.4831583923105e-06, "epoch": 0.7796471070988921, "percentage": 63.33, "elapsed_time": "2:05:37", "remaining_time": "1:12:43", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 950, "total_steps": 1500, "eval_loss": 0.09784827381372452, "epoch": 0.7796471070988921, "percentage": 63.33, "elapsed_time": "2:06:03", "remaining_time": "1:12:58", "throughput": "0.00", "total_tokens": 0}