Training in progress, step 950

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:537390d5f60a55d2c33cd1b56c2703145be6586fb388ec42dbac494b54c08997
+oid sha256:2f718306dabc3f787928043cf86d9169034e75c6fcef4758923ca1b2eb0e3e4c
 size 25200088

trainer_log.jsonl

@@ -106,3 +106,9 @@
 {"current_steps": 890, "total_steps": 1500, "loss": 0.3063, "accuracy": 0.8500000238418579, "learning_rate": 1.7774205076388207e-06, "epoch": 1.1295238095238096, "percentage": 59.33, "elapsed_time": "2:01:51", "remaining_time": "1:23:31", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 900, "total_steps": 1500, "loss": 0.3479, "accuracy": 0.9375, "learning_rate": 1.7274575140626318e-06, "epoch": 1.1422222222222222, "percentage": 60.0, "elapsed_time": "2:03:10", "remaining_time": "1:22:07", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 900, "total_steps": 1500, "eval_loss": 0.3475661873817444, "epoch": 1.1422222222222222, "percentage": 60.0, "elapsed_time": "2:03:29", "remaining_time": "1:22:19", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 910, "total_steps": 1500, "loss": 0.3325, "accuracy": 0.925000011920929, "learning_rate": 1.677833383153542e-06, "epoch": 1.154920634920635, "percentage": 60.67, "elapsed_time": "2:04:54", "remaining_time": "1:20:59", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 920, "total_steps": 1500, "loss": 0.3216, "accuracy": 0.949999988079071, "learning_rate": 1.6285698816954626e-06, "epoch": 1.1676190476190476, "percentage": 61.33, "elapsed_time": "2:06:14", "remaining_time": "1:19:35", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 930, "total_steps": 1500, "loss": 0.372, "accuracy": 0.8999999761581421, "learning_rate": 1.5796886182883053e-06, "epoch": 1.1803174603174602, "percentage": 62.0, "elapsed_time": "2:07:35", "remaining_time": "1:18:11", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 940, "total_steps": 1500, "loss": 0.3265, "accuracy": 0.925000011920929, "learning_rate": 1.5312110338697427e-06, "epoch": 1.193015873015873, "percentage": 62.67, "elapsed_time": "2:08:55", "remaining_time": "1:16:48", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 950, "total_steps": 1500, "loss": 0.3288, "accuracy": 0.9375, "learning_rate": 1.4831583923105e-06, "epoch": 1.2057142857142857, "percentage": 63.33, "elapsed_time": "2:10:12", "remaining_time": "1:15:23", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 950, "total_steps": 1500, "eval_loss": 0.3351227343082428, "epoch": 1.2057142857142857, "percentage": 63.33, "elapsed_time": "2:10:31", "remaining_time": "1:15:34", "throughput": "0.00", "total_tokens": 0}