Training in progress, step 650

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:809249302c977550e603e8888ff44ba993f51567e2ea0eacf02f27da53376e3d
+oid sha256:6ca082a0a13623d94c875e84d0b1a70004526df52a189125ab65af0aaddf435a
 size 25200088

trainer_log.jsonl

@@ -70,3 +70,9 @@
 {"current_steps": 590, "total_steps": 1500, "loss": 0.2809, "accuracy": 0.9624999761581421, "learning_rate": 3.3221666168464584e-06, "epoch": 0.50709067468844, "percentage": 39.33, "elapsed_time": "1:19:14", "remaining_time": "2:02:13", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 600, "total_steps": 1500, "loss": 0.2956, "accuracy": 0.887499988079071, "learning_rate": 3.272542485937369e-06, "epoch": 0.5156854318865493, "percentage": 40.0, "elapsed_time": "1:20:26", "remaining_time": "2:00:40", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 600, "total_steps": 1500, "eval_loss": 0.3030374050140381, "epoch": 0.5156854318865493, "percentage": 40.0, "elapsed_time": "1:20:52", "remaining_time": "2:01:18", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 610, "total_steps": 1500, "loss": 0.2898, "accuracy": 0.9375, "learning_rate": 3.222579492361179e-06, "epoch": 0.5242801890846583, "percentage": 40.67, "elapsed_time": "1:22:09", "remaining_time": "1:59:52", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 620, "total_steps": 1500, "loss": 0.2895, "accuracy": 0.9375, "learning_rate": 3.1722995515381644e-06, "epoch": 0.5328749462827675, "percentage": 41.33, "elapsed_time": "1:23:21", "remaining_time": "1:58:18", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 630, "total_steps": 1500, "loss": 0.2634, "accuracy": 0.949999988079071, "learning_rate": 3.121724717912138e-06, "epoch": 0.5414697034808766, "percentage": 42.0, "elapsed_time": "1:24:33", "remaining_time": "1:56:45", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 640, "total_steps": 1500, "loss": 0.2594, "accuracy": 0.9375, "learning_rate": 3.0708771752766397e-06, "epoch": 0.5500644606789858, "percentage": 42.67, "elapsed_time": "1:25:47", "remaining_time": "1:55:16", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 650, "total_steps": 1500, "loss": 0.2399, "accuracy": 0.9750000238418579, "learning_rate": 3.019779227044398e-06, "epoch": 0.5586592178770949, "percentage": 43.33, "elapsed_time": "1:26:56", "remaining_time": "1:53:41", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 650, "total_steps": 1500, "eval_loss": 0.2814938426017761, "epoch": 0.5586592178770949, "percentage": 43.33, "elapsed_time": "1:27:22", "remaining_time": "1:54:15", "throughput": "0.00", "total_tokens": 0}