Training in progress, step 500

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5287152d9213dbfa3c38e13847adf3c7b00c332045ff875824d2b8640619101d
+oid sha256:dac859c7ff908cd4d01ff89bc83ea5fee5cc4658a79bf64ca31885662e69f632
 size 25200088

trainer_log.jsonl

@@ -52,3 +52,9 @@
 {"current_steps": 440, "total_steps": 1500, "loss": 0.5665, "accuracy": 0.8500000238418579, "learning_rate": 4.011497787155938e-06, "epoch": 0.5587301587301587, "percentage": 29.33, "elapsed_time": "1:00:04", "remaining_time": "2:24:43", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 450, "total_steps": 1500, "loss": 0.5118, "accuracy": 0.824999988079071, "learning_rate": 3.969463130731183e-06, "epoch": 0.5714285714285714, "percentage": 30.0, "elapsed_time": "1:01:23", "remaining_time": "2:23:15", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 450, "total_steps": 1500, "eval_loss": 0.5201926827430725, "epoch": 0.5714285714285714, "percentage": 30.0, "elapsed_time": "1:01:42", "remaining_time": "2:23:59", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 460, "total_steps": 1500, "loss": 0.4783, "accuracy": 0.875, "learning_rate": 3.92678391921108e-06, "epoch": 0.5841269841269842, "percentage": 30.67, "elapsed_time": "1:03:08", "remaining_time": "2:22:46", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 470, "total_steps": 1500, "loss": 0.534, "accuracy": 0.875, "learning_rate": 3.88347887310836e-06, "epoch": 0.5968253968253968, "percentage": 31.33, "elapsed_time": "1:04:27", "remaining_time": "2:21:14", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 480, "total_steps": 1500, "loss": 0.4829, "accuracy": 0.925000011920929, "learning_rate": 3.839566987447492e-06, "epoch": 0.6095238095238096, "percentage": 32.0, "elapsed_time": "1:05:47", "remaining_time": "2:19:47", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 490, "total_steps": 1500, "loss": 0.4437, "accuracy": 0.949999988079071, "learning_rate": 3.795067523432826e-06, "epoch": 0.6222222222222222, "percentage": 32.67, "elapsed_time": "1:07:02", "remaining_time": "2:18:10", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 500, "total_steps": 1500, "loss": 0.4411, "accuracy": 0.887499988079071, "learning_rate": 3.7500000000000005e-06, "epoch": 0.6349206349206349, "percentage": 33.33, "elapsed_time": "1:08:17", "remaining_time": "2:16:34", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 500, "total_steps": 1500, "eval_loss": 0.4819534122943878, "epoch": 0.6349206349206349, "percentage": 33.33, "elapsed_time": "1:08:35", "remaining_time": "2:17:11", "throughput": "0.00", "total_tokens": 0}