Training in progress, step 550

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19d08c5b40c5446d49aa53e9fb300225b7077013e89262596f4d47986b2e129c
+oid sha256:1b885b20c1c312d2cba718c440b75145db55e1a6f6d11eaa5559bbc187fc57dc
 size 25200088

trainer_log.jsonl

@@ -58,3 +58,9 @@
 {"current_steps": 490, "total_steps": 1500, "loss": 0.3974, "accuracy": 0.9125000238418579, "learning_rate": 3.795067523432826e-06, "epoch": 0.5223880597014925, "percentage": 32.67, "elapsed_time": "1:06:04", "remaining_time": "2:16:12", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 500, "total_steps": 1500, "loss": 0.367, "accuracy": 0.925000011920929, "learning_rate": 3.7500000000000005e-06, "epoch": 0.5330490405117271, "percentage": 33.33, "elapsed_time": "1:07:22", "remaining_time": "2:14:44", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 500, "total_steps": 1500, "eval_loss": 0.387028306722641, "epoch": 0.5330490405117271, "percentage": 33.33, "elapsed_time": "1:07:43", "remaining_time": "2:15:27", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 510, "total_steps": 1500, "loss": 0.3776, "accuracy": 0.925000011920929, "learning_rate": 3.7043841852542884e-06, "epoch": 0.5437100213219617, "percentage": 34.0, "elapsed_time": "1:09:03", "remaining_time": "2:14:04", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 520, "total_steps": 1500, "loss": 0.3999, "accuracy": 0.887499988079071, "learning_rate": 3.658240087799655e-06, "epoch": 0.5543710021321961, "percentage": 34.67, "elapsed_time": "1:10:21", "remaining_time": "2:12:36", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 530, "total_steps": 1500, "loss": 0.3346, "accuracy": 0.9125000238418579, "learning_rate": 3.611587947962319e-06, "epoch": 0.5650319829424307, "percentage": 35.33, "elapsed_time": "1:11:39", "remaining_time": "2:11:09", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 540, "total_steps": 1500, "loss": 0.3675, "accuracy": 0.925000011920929, "learning_rate": 3.564448228912682e-06, "epoch": 0.5756929637526652, "percentage": 36.0, "elapsed_time": "1:12:59", "remaining_time": "2:09:45", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 550, "total_steps": 1500, "loss": 0.3921, "accuracy": 0.862500011920929, "learning_rate": 3.516841607689501e-06, "epoch": 0.5863539445628998, "percentage": 36.67, "elapsed_time": "1:14:16", "remaining_time": "2:08:17", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 550, "total_steps": 1500, "eval_loss": 0.35785165429115295, "epoch": 0.5863539445628998, "percentage": 36.67, "elapsed_time": "1:14:38", "remaining_time": "2:08:54", "throughput": "0.00", "total_tokens": 0}