Training in progress, step 550

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7220c8c908fc484d8977105ad31b36fd4bb56c9593a4159fe735f42de22b721d
+oid sha256:a084a66d77c145f30a3cde671c62547241c343dd17b2c11f137507e95b6a00af
 size 40036488

trainer_log.jsonl

@@ -58,3 +58,9 @@
 {"current_steps": 490, "total_steps": 1500, "loss": 3.5333, "accuracy": 0.7875000238418579, "learning_rate": 3.795067523432826e-06, "epoch": 0.40213377102995485, "percentage": 32.67, "elapsed_time": "1:04:47", "remaining_time": "2:13:32", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 500, "total_steps": 1500, "loss": 3.1958, "accuracy": 0.800000011920929, "learning_rate": 3.7500000000000005e-06, "epoch": 0.4103405826836274, "percentage": 33.33, "elapsed_time": "1:05:58", "remaining_time": "2:11:56", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 500, "total_steps": 1500, "eval_loss": 0.3702296018600464, "epoch": 0.4103405826836274, "percentage": 33.33, "elapsed_time": "1:06:24", "remaining_time": "2:12:48", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 510, "total_steps": 1500, "loss": 2.8418, "accuracy": 0.8999999761581421, "learning_rate": 3.7043841852542884e-06, "epoch": 0.4185473943373, "percentage": 34.0, "elapsed_time": "1:07:49", "remaining_time": "2:11:39", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 520, "total_steps": 1500, "loss": 2.73, "accuracy": 0.8374999761581421, "learning_rate": 3.658240087799655e-06, "epoch": 0.4267542059909725, "percentage": 34.67, "elapsed_time": "1:09:01", "remaining_time": "2:10:04", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 530, "total_steps": 1500, "loss": 2.5886, "accuracy": 0.8999999761581421, "learning_rate": 3.611587947962319e-06, "epoch": 0.43496101764464506, "percentage": 35.33, "elapsed_time": "1:10:10", "remaining_time": "2:08:26", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 540, "total_steps": 1500, "loss": 2.5918, "accuracy": 0.875, "learning_rate": 3.564448228912682e-06, "epoch": 0.4431678292983176, "percentage": 36.0, "elapsed_time": "1:11:22", "remaining_time": "2:06:52", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 550, "total_steps": 1500, "loss": 2.3387, "accuracy": 0.8999999761581421, "learning_rate": 3.516841607689501e-06, "epoch": 0.45137464095199015, "percentage": 36.67, "elapsed_time": "1:12:34", "remaining_time": "2:05:21", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 550, "total_steps": 1500, "eval_loss": 0.28920263051986694, "epoch": 0.45137464095199015, "percentage": 36.67, "elapsed_time": "1:13:00", "remaining_time": "2:06:06", "throughput": "0.00", "total_tokens": 0}