Training in progress, step 250

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:249fffe476058092aeef5b427f5dc1ef1059380afd82cd41f1bba83ca17fafa3
+oid sha256:7489e9bc7d19b0729a77850ca332bf5be718cd0a777d40cb43e8348a3330cc7e
 size 25200088

trainer_log.jsonl

@@ -22,3 +22,9 @@
 {"current_steps": 190, "total_steps": 1500, "loss": 0.9002, "accuracy": 0.6000000238418579, "learning_rate": 4.804657878971252e-06, "epoch": 0.1633003867640739, "percentage": 12.67, "elapsed_time": "0:24:53", "remaining_time": "2:51:40", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 200, "total_steps": 1500, "loss": 0.8773, "accuracy": 0.574999988079071, "learning_rate": 4.783863644106502e-06, "epoch": 0.17189514396218306, "percentage": 13.33, "elapsed_time": "0:26:03", "remaining_time": "2:49:20", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 200, "total_steps": 1500, "eval_loss": 0.8721462488174438, "epoch": 0.17189514396218306, "percentage": 13.33, "elapsed_time": "0:26:28", "remaining_time": "2:52:08", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 210, "total_steps": 1500, "loss": 0.8484, "accuracy": 0.5375000238418579, "learning_rate": 4.762067631165049e-06, "epoch": 0.18048990116029223, "percentage": 14.0, "elapsed_time": "0:27:50", "remaining_time": "2:50:59", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 220, "total_steps": 1500, "loss": 0.8499, "accuracy": 0.637499988079071, "learning_rate": 4.7392794005985324e-06, "epoch": 0.18908465835840138, "percentage": 14.67, "elapsed_time": "0:29:05", "remaining_time": "2:49:14", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 230, "total_steps": 1500, "loss": 0.826, "accuracy": 0.6499999761581421, "learning_rate": 4.715508948078037e-06, "epoch": 0.19767941555651053, "percentage": 15.33, "elapsed_time": "0:30:18", "remaining_time": "2:47:18", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 240, "total_steps": 1500, "loss": 0.7992, "accuracy": 0.637499988079071, "learning_rate": 4.690766700109659e-06, "epoch": 0.20627417275461968, "percentage": 16.0, "elapsed_time": "0:31:33", "remaining_time": "2:45:39", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 250, "total_steps": 1500, "loss": 0.7848, "accuracy": 0.625, "learning_rate": 4.665063509461098e-06, "epoch": 0.21486892995272883, "percentage": 16.67, "elapsed_time": "0:32:47", "remaining_time": "2:43:55", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 250, "total_steps": 1500, "eval_loss": 0.7728626728057861, "epoch": 0.21486892995272883, "percentage": 16.67, "elapsed_time": "0:33:12", "remaining_time": "2:46:04", "throughput": "0.00", "total_tokens": 0}