Training in progress, step 750

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f03e2a4e0e18f7049ffbaefe6ee9f2c83b07d8750fa3b3c674731d073c2db6e5
+oid sha256:9cf22c8ddc949c366cc3dbc9285b091d4854d39f306fd528d7205c971eaecda6
 size 25200088

trainer_log.jsonl

@@ -82,3 +82,9 @@
 {"current_steps": 690, "total_steps": 1500, "loss": 0.2362, "accuracy": 0.925000011920929, "learning_rate": 2.813333083910761e-06, "epoch": 0.7356076759061834, "percentage": 46.0, "elapsed_time": "1:33:21", "remaining_time": "1:49:35", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 700, "total_steps": 1500, "loss": 0.3257, "accuracy": 0.925000011920929, "learning_rate": 2.761321158169134e-06, "epoch": 0.746268656716418, "percentage": 46.67, "elapsed_time": "1:34:37", "remaining_time": "1:48:08", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 700, "total_steps": 1500, "eval_loss": 0.3062504529953003, "epoch": 0.746268656716418, "percentage": 46.67, "elapsed_time": "1:34:58", "remaining_time": "1:48:33", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 710, "total_steps": 1500, "loss": 0.3255, "accuracy": 0.8999999761581421, "learning_rate": 2.70919460833079e-06, "epoch": 0.7569296375266524, "percentage": 47.33, "elapsed_time": "1:36:19", "remaining_time": "1:47:10", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 720, "total_steps": 1500, "loss": 0.2845, "accuracy": 0.8999999761581421, "learning_rate": 2.6569762988232838e-06, "epoch": 0.767590618336887, "percentage": 48.0, "elapsed_time": "1:37:35", "remaining_time": "1:45:43", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 730, "total_steps": 1500, "loss": 0.2696, "accuracy": 0.925000011920929, "learning_rate": 2.604689134322999e-06, "epoch": 0.7782515991471215, "percentage": 48.67, "elapsed_time": "1:38:53", "remaining_time": "1:44:18", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 740, "total_steps": 1500, "loss": 0.2622, "accuracy": 0.949999988079071, "learning_rate": 2.5523560497083927e-06, "epoch": 0.7889125799573561, "percentage": 49.33, "elapsed_time": "1:40:11", "remaining_time": "1:42:53", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 750, "total_steps": 1500, "loss": 0.3243, "accuracy": 0.887499988079071, "learning_rate": 2.5e-06, "epoch": 0.7995735607675906, "percentage": 50.0, "elapsed_time": "1:41:21", "remaining_time": "1:41:21", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 750, "total_steps": 1500, "eval_loss": 0.2867603600025177, "epoch": 0.7995735607675906, "percentage": 50.0, "elapsed_time": "1:41:43", "remaining_time": "1:41:43", "throughput": "0.00", "total_tokens": 0}