Training in progress, step 200

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09a1c9d1a5f4464e93651666d40af604f40172387423b6f4b911a81b5dc8df4c
+oid sha256:6964ea93644c5c710cfe022f4870ffafe3ff0cfde1c63c52c50103ee1ebde7a0
 size 25200088

trainer_log.jsonl

@@ -16,3 +16,9 @@
 {"current_steps": 140, "total_steps": 1500, "loss": 0.9098, "accuracy": 0.574999988079071, "learning_rate": 4.893298743830168e-06, "epoch": 0.12433392539964476, "percentage": 9.33, "elapsed_time": "0:18:52", "remaining_time": "3:03:24", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 150, "total_steps": 1500, "loss": 0.9104, "accuracy": 0.5249999761581421, "learning_rate": 4.8776412907378845e-06, "epoch": 0.13321492007104796, "percentage": 10.0, "elapsed_time": "0:20:07", "remaining_time": "3:01:05", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 150, "total_steps": 1500, "eval_loss": 0.9143257737159729, "epoch": 0.13321492007104796, "percentage": 10.0, "elapsed_time": "0:20:32", "remaining_time": "3:04:53", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 160, "total_steps": 1500, "loss": 0.9051, "accuracy": 0.550000011920929, "learning_rate": 4.860940925593703e-06, "epoch": 0.14209591474245115, "percentage": 10.67, "elapsed_time": "0:21:52", "remaining_time": "3:03:11", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 170, "total_steps": 1500, "loss": 0.8906, "accuracy": 0.5625, "learning_rate": 4.84320497372973e-06, "epoch": 0.15097690941385436, "percentage": 11.33, "elapsed_time": "0:23:05", "remaining_time": "3:00:43", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 180, "total_steps": 1500, "loss": 0.8766, "accuracy": 0.5874999761581421, "learning_rate": 4.824441214720629e-06, "epoch": 0.15985790408525755, "percentage": 12.0, "elapsed_time": "0:24:17", "remaining_time": "2:58:10", "throughput": "0.00", "total_tokens": 0}
+{"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}