Training in progress, step 250

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6964ea93644c5c710cfe022f4870ffafe3ff0cfde1c63c52c50103ee1ebde7a0
+oid sha256:0395a9a4a94869c7ef5b6377172ca90c291ec769effe4a91936239fd47c2a734
 size 25200088

trainer_log.jsonl

@@ -22,3 +22,9 @@
 {"current_steps": 190, "total_steps": 1500, "loss": 0.884, "accuracy": 0.637499988079071, "learning_rate": 4.804657878971252e-06, "epoch": 0.16873889875666073, "percentage": 12.67, "elapsed_time": "0:25:29", "remaining_time": "2:55:45", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 200, "total_steps": 1500, "loss": 0.8767, "accuracy": 0.5874999761581421, "learning_rate": 4.783863644106502e-06, "epoch": 0.17761989342806395, "percentage": 13.33, "elapsed_time": "0:26:49", "remaining_time": "2:54:18", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 200, "total_steps": 1500, "eval_loss": 0.8664290904998779, "epoch": 0.17761989342806395, "percentage": 13.33, "elapsed_time": "0:27:14", "remaining_time": "2:57:03", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 210, "total_steps": 1500, "loss": 0.8556, "accuracy": 0.637499988079071, "learning_rate": 4.762067631165049e-06, "epoch": 0.18650088809946713, "percentage": 14.0, "elapsed_time": "0:28:33", "remaining_time": "2:55:28", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 220, "total_steps": 1500, "loss": 0.8236, "accuracy": 0.550000011920929, "learning_rate": 4.7392794005985324e-06, "epoch": 0.19538188277087035, "percentage": 14.67, "elapsed_time": "0:29:50", "remaining_time": "2:53:37", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 230, "total_steps": 1500, "loss": 0.8027, "accuracy": 0.625, "learning_rate": 4.715508948078037e-06, "epoch": 0.20426287744227353, "percentage": 15.33, "elapsed_time": "0:31:04", "remaining_time": "2:51:34", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 240, "total_steps": 1500, "loss": 0.7898, "accuracy": 0.612500011920929, "learning_rate": 4.690766700109659e-06, "epoch": 0.21314387211367672, "percentage": 16.0, "elapsed_time": "0:32:20", "remaining_time": "2:49:45", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 250, "total_steps": 1500, "loss": 0.7626, "accuracy": 0.6625000238418579, "learning_rate": 4.665063509461098e-06, "epoch": 0.22202486678507993, "percentage": 16.67, "elapsed_time": "0:33:37", "remaining_time": "2:48:09", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 250, "total_steps": 1500, "eval_loss": 0.7631083130836487, "epoch": 0.22202486678507993, "percentage": 16.67, "elapsed_time": "0:34:03", "remaining_time": "2:50:15", "throughput": "0.00", "total_tokens": 0}