Training in progress, step 900

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89aa50978dd9bb6b676eef7ba40cd4761651038e2f09545246dc32df2b2a9619
+oid sha256:7bf330fb32f980441a20bfec3b99506b5e1cf1d3554bd64285bacfc549115eaf
 size 25200088

trainer_log.jsonl

@@ -100,3 +100,9 @@
 {"current_steps": 840, "total_steps": 1500, "loss": 0.2384, "accuracy": 0.925000011920929, "learning_rate": 2.031546713535688e-06, "epoch": 0.7460035523978685, "percentage": 56.0, "elapsed_time": "1:54:04", "remaining_time": "1:29:37", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 850, "total_steps": 1500, "loss": 0.2229, "accuracy": 0.9624999761581421, "learning_rate": 1.9802207729556023e-06, "epoch": 0.7548845470692718, "percentage": 56.67, "elapsed_time": "1:55:25", "remaining_time": "1:28:15", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 850, "total_steps": 1500, "eval_loss": 0.2361687868833542, "epoch": 0.7548845470692718, "percentage": 56.67, "elapsed_time": "1:55:50", "remaining_time": "1:28:35", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 860, "total_steps": 1500, "loss": 0.2142, "accuracy": 0.9750000238418579, "learning_rate": 1.9291228247233607e-06, "epoch": 0.7637655417406749, "percentage": 57.33, "elapsed_time": "1:57:10", "remaining_time": "1:27:11", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 870, "total_steps": 1500, "loss": 0.1927, "accuracy": 0.9125000238418579, "learning_rate": 1.8782752820878636e-06, "epoch": 0.7726465364120781, "percentage": 58.0, "elapsed_time": "1:58:28", "remaining_time": "1:25:47", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 880, "total_steps": 1500, "loss": 0.1945, "accuracy": 0.9750000238418579, "learning_rate": 1.827700448461836e-06, "epoch": 0.7815275310834814, "percentage": 58.67, "elapsed_time": "1:59:39", "remaining_time": "1:24:17", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 890, "total_steps": 1500, "loss": 0.2228, "accuracy": 0.9125000238418579, "learning_rate": 1.7774205076388207e-06, "epoch": 0.7904085257548845, "percentage": 59.33, "elapsed_time": "2:00:51", "remaining_time": "1:22:50", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 900, "total_steps": 1500, "loss": 0.2134, "accuracy": 0.9125000238418579, "learning_rate": 1.7274575140626318e-06, "epoch": 0.7992895204262878, "percentage": 60.0, "elapsed_time": "2:02:07", "remaining_time": "1:21:24", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 900, "total_steps": 1500, "eval_loss": 0.2303350269794464, "epoch": 0.7992895204262878, "percentage": 60.0, "elapsed_time": "2:02:32", "remaining_time": "1:21:41", "throughput": "0.00", "total_tokens": 0}