Training in progress, step 350

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6ded9effaf26b814fa2662f4f5f5fc018391f7e8695803e30a06e8986d4d894
+oid sha256:0dccd1fce176fe5c96d5f08fb149a451a292414d1d1b0fadf466632d2a969e60
 size 40036488

trainer_log.jsonl

@@ -34,3 +34,9 @@
 {"current_steps": 290, "total_steps": 1500, "loss": 6.2071, "accuracy": 0.4749999940395355, "learning_rate": 4.55287302283426e-06, "epoch": 0.23799753795650389, "percentage": 19.33, "elapsed_time": "0:37:36", "remaining_time": "2:36:53", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 300, "total_steps": 1500, "loss": 6.1801, "accuracy": 0.5874999761581421, "learning_rate": 4.522542485937369e-06, "epoch": 0.24620434961017645, "percentage": 20.0, "elapsed_time": "0:38:47", "remaining_time": "2:35:09", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.738965630531311, "epoch": 0.24620434961017645, "percentage": 20.0, "elapsed_time": "0:39:13", "remaining_time": "2:36:53", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 310, "total_steps": 1500, "loss": 5.98, "accuracy": 0.5375000238418579, "learning_rate": 4.491324795060491e-06, "epoch": 0.254411161263849, "percentage": 20.67, "elapsed_time": "0:40:37", "remaining_time": "2:35:57", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 320, "total_steps": 1500, "loss": 5.608, "accuracy": 0.612500011920929, "learning_rate": 4.4592336433146e-06, "epoch": 0.26261797291752154, "percentage": 21.33, "elapsed_time": "0:41:51", "remaining_time": "2:34:21", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 330, "total_steps": 1500, "loss": 5.5189, "accuracy": 0.6000000238418579, "learning_rate": 4.426283106939474e-06, "epoch": 0.2708247845711941, "percentage": 22.0, "elapsed_time": "0:43:00", "remaining_time": "2:32:30", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 340, "total_steps": 1500, "loss": 5.3992, "accuracy": 0.675000011920929, "learning_rate": 4.3924876391293915e-06, "epoch": 0.2790315962248666, "percentage": 22.67, "elapsed_time": "0:44:14", "remaining_time": "2:30:56", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 350, "total_steps": 1500, "loss": 5.0093, "accuracy": 0.699999988079071, "learning_rate": 4.357862063693486e-06, "epoch": 0.2872384078785392, "percentage": 23.33, "elapsed_time": "0:45:27", "remaining_time": "2:29:23", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 350, "total_steps": 1500, "eval_loss": 0.610858678817749, "epoch": 0.2872384078785392, "percentage": 23.33, "elapsed_time": "0:45:54", "remaining_time": "2:30:48", "throughput": "0.00", "total_tokens": 0}