Training in progress, step 500

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aef3a6b8a0f9b729468b7c9d08c649a2663689f3a2d4abed35376b46446ae27
+oid sha256:eb66a8906851fdeb11cd5dcd27c5c962fda60aa4ee06c5196460991700742b9b
 size 25200088

trainer_log.jsonl

@@ -52,3 +52,9 @@
 {"current_steps": 440, "total_steps": 1500, "loss": 0.3739, "accuracy": 0.8125, "learning_rate": 4.011497787155938e-06, "epoch": 0.36632323863045063, "percentage": 29.33, "elapsed_time": "1:01:05", "remaining_time": "2:27:09", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 450, "total_steps": 1500, "loss": 0.2905, "accuracy": 0.8999999761581421, "learning_rate": 3.969463130731183e-06, "epoch": 0.3746487667811427, "percentage": 30.0, "elapsed_time": "1:02:22", "remaining_time": "2:25:31", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 450, "total_steps": 1500, "eval_loss": 0.3302614390850067, "epoch": 0.3746487667811427, "percentage": 30.0, "elapsed_time": "1:02:51", "remaining_time": "2:26:39", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 460, "total_steps": 1500, "loss": 0.2881, "accuracy": 0.8500000238418579, "learning_rate": 3.92678391921108e-06, "epoch": 0.3829742949318347, "percentage": 30.67, "elapsed_time": "1:04:14", "remaining_time": "2:25:14", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 470, "total_steps": 1500, "loss": 0.31, "accuracy": 0.887499988079071, "learning_rate": 3.88347887310836e-06, "epoch": 0.3912998230825268, "percentage": 31.33, "elapsed_time": "1:05:29", "remaining_time": "2:23:31", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 480, "total_steps": 1500, "loss": 0.3194, "accuracy": 0.8999999761581421, "learning_rate": 3.839566987447492e-06, "epoch": 0.39962535123321885, "percentage": 32.0, "elapsed_time": "1:06:50", "remaining_time": "2:22:02", "throughput": "0.00", "total_tokens": 0}
+{"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}