Training in progress, step 550

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb66a8906851fdeb11cd5dcd27c5c962fda60aa4ee06c5196460991700742b9b
+oid sha256:f003db2fe87d86cc4cf79728522e52759f7e6898e0e30197ffffa63c51142177
 size 25200088

trainer_log.jsonl

@@ -58,3 +58,9 @@
 {"current_steps": 490, "total_steps": 1500, "loss": 0.3353, "accuracy": 0.8500000238418579, "learning_rate": 3.795067523432826e-06, "epoch": 0.4079508793839109, "percentage": 32.67, "elapsed_time": "1:08:05", "remaining_time": "2:20:21", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 500, "total_steps": 1500, "loss": 0.3018, "accuracy": 0.925000011920929, "learning_rate": 3.7500000000000005e-06, "epoch": 0.416276407534603, "percentage": 33.33, "elapsed_time": "1:09:24", "remaining_time": "2:18:49", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 500, "total_steps": 1500, "eval_loss": 0.3079966604709625, "epoch": 0.416276407534603, "percentage": 33.33, "elapsed_time": "1:09:53", "remaining_time": "2:19:47", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 510, "total_steps": 1500, "loss": 0.3101, "accuracy": 0.8999999761581421, "learning_rate": 3.7043841852542884e-06, "epoch": 0.42460193568529503, "percentage": 34.0, "elapsed_time": "1:11:16", "remaining_time": "2:18:20", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 520, "total_steps": 1500, "loss": 0.2925, "accuracy": 0.875, "learning_rate": 3.658240087799655e-06, "epoch": 0.43292746383598707, "percentage": 34.67, "elapsed_time": "1:12:33", "remaining_time": "2:16:44", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 530, "total_steps": 1500, "loss": 0.3169, "accuracy": 0.9125000238418579, "learning_rate": 3.611587947962319e-06, "epoch": 0.44125299198667917, "percentage": 35.33, "elapsed_time": "1:13:51", "remaining_time": "2:15:10", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 540, "total_steps": 1500, "loss": 0.3271, "accuracy": 0.800000011920929, "learning_rate": 3.564448228912682e-06, "epoch": 0.4495785201373712, "percentage": 36.0, "elapsed_time": "1:15:05", "remaining_time": "2:13:30", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 550, "total_steps": 1500, "loss": 0.3172, "accuracy": 0.824999988079071, "learning_rate": 3.516841607689501e-06, "epoch": 0.45790404828806325, "percentage": 36.67, "elapsed_time": "1:16:22", "remaining_time": "2:11:54", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 550, "total_steps": 1500, "eval_loss": 0.28538385033607483, "epoch": 0.45790404828806325, "percentage": 36.67, "elapsed_time": "1:16:51", "remaining_time": "2:12:44", "throughput": "0.00", "total_tokens": 0}