Training in progress, step 1250

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3213d01b6127c832ca7aac28b39740a1a3324c4ba267f36e0b41906089fd8d2b
+oid sha256:3d80f2c648a0aca0e72371b2c69b66f6dc19cfe220178a7db24f7be8e742472e
 size 25200088

trainer_log.jsonl

@@ -142,3 +142,9 @@
 {"current_steps": 1190, "total_steps": 1500, "loss": 0.2026, "accuracy": 0.9375, "learning_rate": 5.086752049395094e-07, "epoch": 1.0568383658969804, "percentage": 79.33, "elapsed_time": "2:41:41", "remaining_time": "0:42:07", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 1200, "total_steps": 1500, "loss": 0.2233, "accuracy": 0.9375, "learning_rate": 4.774575140626317e-07, "epoch": 1.0657193605683837, "percentage": 80.0, "elapsed_time": "2:42:55", "remaining_time": "0:40:43", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 1200, "total_steps": 1500, "eval_loss": 0.20932108163833618, "epoch": 1.0657193605683837, "percentage": 80.0, "elapsed_time": "2:43:21", "remaining_time": "0:40:50", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1210, "total_steps": 1500, "loss": 0.1761, "accuracy": 0.9125000238418579, "learning_rate": 4.4712697716573994e-07, "epoch": 1.074600355239787, "percentage": 80.67, "elapsed_time": "2:44:42", "remaining_time": "0:39:28", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1220, "total_steps": 1500, "loss": 0.1915, "accuracy": 0.9375, "learning_rate": 4.1769689822475147e-07, "epoch": 1.0834813499111902, "percentage": 81.33, "elapsed_time": "2:45:59", "remaining_time": "0:38:05", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1230, "total_steps": 1500, "loss": 0.1743, "accuracy": 0.987500011920929, "learning_rate": 3.891801862449629e-07, "epoch": 1.0923623445825932, "percentage": 82.0, "elapsed_time": "2:47:17", "remaining_time": "0:36:43", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1240, "total_steps": 1500, "loss": 0.195, "accuracy": 0.925000011920929, "learning_rate": 3.615893495987335e-07, "epoch": 1.1012433392539964, "percentage": 82.67, "elapsed_time": "2:48:32", "remaining_time": "0:35:20", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1250, "total_steps": 1500, "loss": 0.1571, "accuracy": 0.949999988079071, "learning_rate": 3.3493649053890325e-07, "epoch": 1.1101243339253997, "percentage": 83.33, "elapsed_time": "2:49:50", "remaining_time": "0:33:58", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1250, "total_steps": 1500, "eval_loss": 0.2080618292093277, "epoch": 1.1101243339253997, "percentage": 83.33, "elapsed_time": "2:50:15", "remaining_time": "0:34:03", "throughput": "0.00", "total_tokens": 0}