Training in progress, step 950

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bf330fb32f980441a20bfec3b99506b5e1cf1d3554bd64285bacfc549115eaf
+oid sha256:7f26a866e727df6712d83d3f6647d4e67a560f550cc65a8099e976ccb53c091d
 size 25200088

trainer_log.jsonl

@@ -106,3 +106,9 @@
 {"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}
+{"current_steps": 910, "total_steps": 1500, "loss": 0.2029, "accuracy": 0.9375, "learning_rate": 1.677833383153542e-06, "epoch": 0.8081705150976909, "percentage": 60.67, "elapsed_time": "2:03:55", "remaining_time": "1:20:20", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 920, "total_steps": 1500, "loss": 0.2054, "accuracy": 0.9125000238418579, "learning_rate": 1.6285698816954626e-06, "epoch": 0.8170515097690941, "percentage": 61.33, "elapsed_time": "2:05:13", "remaining_time": "1:18:56", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 930, "total_steps": 1500, "loss": 0.1958, "accuracy": 0.949999988079071, "learning_rate": 1.5796886182883053e-06, "epoch": 0.8259325044404974, "percentage": 62.0, "elapsed_time": "2:06:28", "remaining_time": "1:17:30", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 940, "total_steps": 1500, "loss": 0.2147, "accuracy": 0.887499988079071, "learning_rate": 1.5312110338697427e-06, "epoch": 0.8348134991119005, "percentage": 62.67, "elapsed_time": "2:07:42", "remaining_time": "1:16:05", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 950, "total_steps": 1500, "loss": 0.1832, "accuracy": 0.9624999761581421, "learning_rate": 1.4831583923105e-06, "epoch": 0.8436944937833037, "percentage": 63.33, "elapsed_time": "2:08:57", "remaining_time": "1:14:39", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 950, "total_steps": 1500, "eval_loss": 0.22471140325069427, "epoch": 0.8436944937833037, "percentage": 63.33, "elapsed_time": "2:09:22", "remaining_time": "1:14:54", "throughput": "0.00", "total_tokens": 0}