Training in progress, step 550

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4de7bd14acccd57374f2a3b4d98a2018109523d7d21790a45c40a54730383744
+oid sha256:6281a33eda942518b50d9b920995d95366ff1b3af5aeaa5d4b68d339b7e7d21e
 size 40036488

trainer_log.jsonl

@@ -58,3 +58,9 @@
 {"current_steps": 490, "total_steps": 1500, "loss": 2.5705, "accuracy": 0.8999999761581421, "learning_rate": 3.795067523432826e-06, "epoch": 0.40213377102995485, "percentage": 32.67, "elapsed_time": "1:04:05", "remaining_time": "2:12:07", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 500, "total_steps": 1500, "loss": 2.6946, "accuracy": 0.887499988079071, "learning_rate": 3.7500000000000005e-06, "epoch": 0.4103405826836274, "percentage": 33.33, "elapsed_time": "1:05:15", "remaining_time": "2:10:30", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 500, "total_steps": 1500, "eval_loss": 0.28886228799819946, "epoch": 0.4103405826836274, "percentage": 33.33, "elapsed_time": "1:05:41", "remaining_time": "2:11:22", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 510, "total_steps": 1500, "loss": 2.0307, "accuracy": 0.887499988079071, "learning_rate": 3.7043841852542884e-06, "epoch": 0.4185473943373, "percentage": 34.0, "elapsed_time": "1:07:04", "remaining_time": "2:10:12", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 520, "total_steps": 1500, "loss": 1.9227, "accuracy": 0.887499988079071, "learning_rate": 3.658240087799655e-06, "epoch": 0.4267542059909725, "percentage": 34.67, "elapsed_time": "1:08:13", "remaining_time": "2:08:35", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 530, "total_steps": 1500, "loss": 2.1664, "accuracy": 0.8999999761581421, "learning_rate": 3.611587947962319e-06, "epoch": 0.43496101764464506, "percentage": 35.33, "elapsed_time": "1:09:26", "remaining_time": "2:07:06", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 540, "total_steps": 1500, "loss": 1.9159, "accuracy": 0.887499988079071, "learning_rate": 3.564448228912682e-06, "epoch": 0.4431678292983176, "percentage": 36.0, "elapsed_time": "1:10:38", "remaining_time": "2:05:34", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 550, "total_steps": 1500, "loss": 1.7838, "accuracy": 0.9624999761581421, "learning_rate": 3.516841607689501e-06, "epoch": 0.45137464095199015, "percentage": 36.67, "elapsed_time": "1:11:48", "remaining_time": "2:04:01", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 550, "total_steps": 1500, "eval_loss": 0.2348441481590271, "epoch": 0.45137464095199015, "percentage": 36.67, "elapsed_time": "1:12:14", "remaining_time": "2:04:47", "throughput": "0.00", "total_tokens": 0}