Training in progress, step 1000

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48ed3fabc85a2ed0b06d815a7c3f2ef1aaa73f8485ee9348fe9529abc84589e3
+oid sha256:1232a9ad92563023ac9bcffa45f71e8476092490ecc3e9f5f2513bb892527267
 size 25200088

trainer_log.jsonl

@@ -100,3 +100,21 @@
 {"current_steps": 840, "total_steps": 1500, "loss": 0.1964, "accuracy": 0.949999988079071, "learning_rate": 2.031546713535688e-06, "epoch": 0.639269406392694, "percentage": 56.0, "elapsed_time": "1:55:55", "remaining_time": "1:31:04", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 850, "total_steps": 1500, "loss": 0.1882, "accuracy": 0.9750000238418579, "learning_rate": 1.9802207729556023e-06, "epoch": 0.6468797564687976, "percentage": 56.67, "elapsed_time": "1:57:09", "remaining_time": "1:29:35", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 850, "total_steps": 1500, "eval_loss": 0.21778903901576996, "epoch": 0.6468797564687976, "percentage": 56.67, "elapsed_time": "1:57:39", "remaining_time": "1:29:58", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 860, "total_steps": 1500, "loss": 0.1916, "accuracy": 0.949999988079071, "learning_rate": 1.9291228247233607e-06, "epoch": 0.654490106544901, "percentage": 57.33, "elapsed_time": "1:59:01", "remaining_time": "1:28:34", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 870, "total_steps": 1500, "loss": 0.2013, "accuracy": 0.9375, "learning_rate": 1.8782752820878636e-06, "epoch": 0.6621004566210046, "percentage": 58.0, "elapsed_time": "2:00:17", "remaining_time": "1:27:06", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 880, "total_steps": 1500, "loss": 0.2163, "accuracy": 0.925000011920929, "learning_rate": 1.827700448461836e-06, "epoch": 0.669710806697108, "percentage": 58.67, "elapsed_time": "2:01:32", "remaining_time": "1:25:38", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 890, "total_steps": 1500, "loss": 0.1935, "accuracy": 0.949999988079071, "learning_rate": 1.7774205076388207e-06, "epoch": 0.6773211567732116, "percentage": 59.33, "elapsed_time": "2:02:46", "remaining_time": "1:24:08", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 900, "total_steps": 1500, "loss": 0.1903, "accuracy": 0.9750000238418579, "learning_rate": 1.7274575140626318e-06, "epoch": 0.684931506849315, "percentage": 60.0, "elapsed_time": "2:04:02", "remaining_time": "1:22:41", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 900, "total_steps": 1500, "eval_loss": 0.2161051481962204, "epoch": 0.684931506849315, "percentage": 60.0, "elapsed_time": "2:04:33", "remaining_time": "1:23:02", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 910, "total_steps": 1500, "loss": 0.1687, "accuracy": 0.949999988079071, "learning_rate": 1.677833383153542e-06, "epoch": 0.6925418569254186, "percentage": 60.67, "elapsed_time": "2:06:03", "remaining_time": "1:21:44", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 920, "total_steps": 1500, "loss": 0.2161, "accuracy": 0.987500011920929, "learning_rate": 1.6285698816954626e-06, "epoch": 0.700152207001522, "percentage": 61.33, "elapsed_time": "2:07:16", "remaining_time": "1:20:14", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 930, "total_steps": 1500, "loss": 0.2007, "accuracy": 0.9624999761581421, "learning_rate": 1.5796886182883053e-06, "epoch": 0.7077625570776256, "percentage": 62.0, "elapsed_time": "2:08:28", "remaining_time": "1:18:44", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 940, "total_steps": 1500, "loss": 0.1907, "accuracy": 0.987500011920929, "learning_rate": 1.5312110338697427e-06, "epoch": 0.715372907153729, "percentage": 62.67, "elapsed_time": "2:09:42", "remaining_time": "1:17:16", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 950, "total_steps": 1500, "loss": 0.2074, "accuracy": 0.9624999761581421, "learning_rate": 1.4831583923105e-06, "epoch": 0.7229832572298326, "percentage": 63.33, "elapsed_time": "2:10:56", "remaining_time": "1:15:48", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 950, "total_steps": 1500, "eval_loss": 0.21113382279872894, "epoch": 0.7229832572298326, "percentage": 63.33, "elapsed_time": "2:11:27", "remaining_time": "1:16:06", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 960, "total_steps": 1500, "loss": 0.187, "accuracy": 0.9750000238418579, "learning_rate": 1.4355517710873184e-06, "epoch": 0.730593607305936, "percentage": 64.0, "elapsed_time": "2:12:58", "remaining_time": "1:14:47", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 970, "total_steps": 1500, "loss": 0.1823, "accuracy": 0.949999988079071, "learning_rate": 1.388412052037682e-06, "epoch": 0.7382039573820396, "percentage": 64.67, "elapsed_time": "2:14:11", "remaining_time": "1:13:19", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 980, "total_steps": 1500, "loss": 0.2122, "accuracy": 0.925000011920929, "learning_rate": 1.3417599122003464e-06, "epoch": 0.745814307458143, "percentage": 65.33, "elapsed_time": "2:15:31", "remaining_time": "1:11:54", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 990, "total_steps": 1500, "loss": 0.2058, "accuracy": 0.9624999761581421, "learning_rate": 1.2956158147457116e-06, "epoch": 0.7534246575342466, "percentage": 66.0, "elapsed_time": "2:16:46", "remaining_time": "1:10:27", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1000, "total_steps": 1500, "loss": 0.2135, "accuracy": 0.9750000238418579, "learning_rate": 1.2500000000000007e-06, "epoch": 0.76103500761035, "percentage": 66.67, "elapsed_time": "2:18:00", "remaining_time": "1:09:00", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1000, "total_steps": 1500, "eval_loss": 0.20949731767177582, "epoch": 0.76103500761035, "percentage": 66.67, "elapsed_time": "2:18:31", "remaining_time": "1:09:15", "throughput": "0.00", "total_tokens": 0}