Training in progress, step 272

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53050572e6d32d87f418fb11be50520f613885e4b0708517cfa6e2215b947ed7
+oid sha256:ee915e1b5fcd3e71f045efcc9cbc0312102624597c3d974e5f1950163bd6338e
 size 4969539560

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f7432c6c2d81986a5ed02165a3855e35a452015578c47719de803e320276e4e
+oid sha256:1a36fb710f6fea75a37049aac8d9eacc734dda5a62ef70bf161d89f8941be5c2
 size 1912795688

trainer_log.jsonl

@@ -764,3 +764,20 @@
 {"current_steps": 271, "total_steps": 400, "loss": 0.5967, "lr": 3.598217822166854e-08, "epoch": 67.87272727272727, "percentage": 67.75, "elapsed_time": "0:32:53", "remaining_time": "0:15:39"}
 {"current_steps": 272, "total_steps": 400, "loss": 0.7777, "lr": 3.5627000643626705e-08, "epoch": 68.0, "percentage": 68.0, "elapsed_time": "0:32:56", "remaining_time": "0:15:30"}
 {"current_steps": 272, "total_steps": 400, "eval_loss": 0.6440867185592651, "epoch": 68.0, "percentage": 68.0, "elapsed_time": "0:32:57", "remaining_time": "0:15:30"}
+{"current_steps": 273, "total_steps": 400, "loss": 0.6824, "lr": 3.527329839449151e-08, "epoch": 68.2909090909091, "percentage": 68.25, "elapsed_time": "0:33:28", "remaining_time": "0:15:34"}
+{"current_steps": 274, "total_steps": 400, "loss": 0.5956, "lr": 3.49210984100586e-08, "epoch": 68.58181818181818, "percentage": 68.5, "elapsed_time": "0:33:35", "remaining_time": "0:15:27"}
+{"current_steps": 275, "total_steps": 400, "loss": 0.679, "lr": 3.4570427511720395e-08, "epoch": 68.87272727272727, "percentage": 68.75, "elapsed_time": "0:33:43", "remaining_time": "0:15:19"}
+{"current_steps": 276, "total_steps": 400, "loss": 0.7194, "lr": 3.4221312404423483e-08, "epoch": 69.0, "percentage": 69.0, "elapsed_time": "0:33:46", "remaining_time": "0:15:10"}
+{"current_steps": 277, "total_steps": 400, "loss": 0.5994, "lr": 3.387377967463493e-08, "epoch": 69.2909090909091, "percentage": 69.25, "elapsed_time": "0:33:53", "remaining_time": "0:15:02"}
+{"current_steps": 278, "total_steps": 400, "loss": 0.6582, "lr": 3.3527855788317614e-08, "epoch": 69.58181818181818, "percentage": 69.5, "elapsed_time": "0:34:00", "remaining_time": "0:14:55"}
+{"current_steps": 279, "total_steps": 400, "loss": 0.7129, "lr": 3.3183567088914834e-08, "epoch": 69.87272727272727, "percentage": 69.75, "elapsed_time": "0:34:07", "remaining_time": "0:14:47"}
+{"current_steps": 280, "total_steps": 400, "loss": 0.7197, "lr": 3.2840939795343986e-08, "epoch": 70.0, "percentage": 70.0, "elapsed_time": "0:34:10", "remaining_time": "0:14:38"}
+{"current_steps": 281, "total_steps": 400, "loss": 0.6844, "lr": 3.250000000000001e-08, "epoch": 70.2909090909091, "percentage": 70.25, "elapsed_time": "0:34:16", "remaining_time": "0:14:31"}
+{"current_steps": 282, "total_steps": 400, "loss": 0.7062, "lr": 3.2160773666768325e-08, "epoch": 70.58181818181818, "percentage": 70.5, "elapsed_time": "0:34:23", "remaining_time": "0:14:23"}
+{"current_steps": 283, "total_steps": 400, "loss": 0.597, "lr": 3.182328662904756e-08, "epoch": 70.87272727272727, "percentage": 70.75, "elapsed_time": "0:34:30", "remaining_time": "0:14:16"}
+{"current_steps": 284, "total_steps": 400, "loss": 0.6592, "lr": 3.14875645877823e-08, "epoch": 71.0, "percentage": 71.0, "elapsed_time": "0:34:33", "remaining_time": "0:14:07"}
+{"current_steps": 285, "total_steps": 400, "loss": 0.6398, "lr": 3.1153633109505784e-08, "epoch": 71.2909090909091, "percentage": 71.25, "elapsed_time": "0:34:40", "remaining_time": "0:13:59"}
+{"current_steps": 286, "total_steps": 400, "loss": 0.6979, "lr": 3.082151762439292e-08, "epoch": 71.58181818181818, "percentage": 71.5, "elapsed_time": "0:34:47", "remaining_time": "0:13:52"}
+{"current_steps": 287, "total_steps": 400, "loss": 0.6352, "lr": 3.049124342432378e-08, "epoch": 71.87272727272727, "percentage": 71.75, "elapsed_time": "0:34:54", "remaining_time": "0:13:44"}
+{"current_steps": 288, "total_steps": 400, "loss": 0.6391, "lr": 3.0162835660957385e-08, "epoch": 72.0, "percentage": 72.0, "elapsed_time": "0:34:57", "remaining_time": "0:13:35"}
+{"current_steps": 288, "total_steps": 400, "eval_loss": 0.641921877861023, "epoch": 72.0, "percentage": 72.0, "elapsed_time": "0:34:58", "remaining_time": "0:13:36"}