Training in progress, step 700

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ca082a0a13623d94c875e84d0b1a70004526df52a189125ab65af0aaddf435a
+oid sha256:16a98f9a5d5751f392e3f2ca3c1e35d7247f5e61970f40b07693cc4fc268c69e
 size 25200088

trainer_log.jsonl

@@ -76,3 +76,9 @@
 {"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}
+{"current_steps": 660, "total_steps": 1500, "loss": 0.2759, "accuracy": 0.887499988079071, "learning_rate": 2.9684532864643123e-06, "epoch": 0.5672539750752041, "percentage": 44.0, "elapsed_time": "1:28:41", "remaining_time": "1:52:52", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 670, "total_steps": 1500, "loss": 0.2586, "accuracy": 0.925000011920929, "learning_rate": 2.9169218667902562e-06, "epoch": 0.5758487322733132, "percentage": 44.67, "elapsed_time": "1:29:52", "remaining_time": "1:51:19", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 680, "total_steps": 1500, "loss": 0.251, "accuracy": 0.9125000238418579, "learning_rate": 2.8652075714060296e-06, "epoch": 0.5844434894714224, "percentage": 45.33, "elapsed_time": "1:31:03", "remaining_time": "1:49:47", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 690, "total_steps": 1500, "loss": 0.2294, "accuracy": 0.9375, "learning_rate": 2.813333083910761e-06, "epoch": 0.5930382466695315, "percentage": 46.0, "elapsed_time": "1:32:18", "remaining_time": "1:48:21", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 700, "total_steps": 1500, "loss": 0.2469, "accuracy": 0.9375, "learning_rate": 2.761321158169134e-06, "epoch": 0.6016330038676407, "percentage": 46.67, "elapsed_time": "1:33:28", "remaining_time": "1:46:49", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 700, "total_steps": 1500, "eval_loss": 0.2584603726863861, "epoch": 0.6016330038676407, "percentage": 46.67, "elapsed_time": "1:33:53", "remaining_time": "1:47:18", "throughput": "0.00", "total_tokens": 0}