Training in progress, step 3350

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edfec1beb3478ee41909b5ce24ea198317f07af35edd0e3dbe2802570cfa4c2f
+oid sha256:1b41c1be8b974e693981390b4f8ea3183b990f4c6cbeb85e09c310968df2c797
 size 29034840

trainer_log.jsonl

@@ -727,3 +727,14 @@
 {"current_steps": 3295, "total_steps": 3400, "loss": 0.2697, "lr": 2.605168450087514e-07, "epoch": 0.8485706927633273, "percentage": 96.91, "elapsed_time": "3:45:54", "remaining_time": "0:07:11", "throughput": 2552.74, "total_tokens": 34601320}
 {"current_steps": 3300, "total_steps": 3400, "loss": 0.3135, "lr": 2.363155558901542e-07, "epoch": 0.8498583569405099, "percentage": 97.06, "elapsed_time": "3:47:21", "remaining_time": "0:06:53", "throughput": 2540.34, "total_tokens": 34654480}
 {"current_steps": 3300, "total_steps": 3400, "eval_loss": 0.4714098274707794, "epoch": 0.8498583569405099, "percentage": 97.06, "elapsed_time": "3:47:59", "remaining_time": "0:06:54", "throughput": 2533.36, "total_tokens": 34654480}
+{"current_steps": 3305, "total_steps": 3400, "loss": 0.3195, "lr": 2.1329118524827662e-07, "epoch": 0.8511460211176926, "percentage": 97.21, "elapsed_time": "3:49:32", "remaining_time": "0:06:35", "throughput": 2519.96, "total_tokens": 34706600}
+{"current_steps": 3310, "total_steps": 3400, "loss": 0.2817, "lr": 1.9144427761286222e-07, "epoch": 0.8524336852948751, "percentage": 97.35, "elapsed_time": "3:50:59", "remaining_time": "0:06:16", "throughput": 2507.93, "total_tokens": 34759528}
+{"current_steps": 3315, "total_steps": 3400, "loss": 0.3131, "lr": 1.7077534966650766e-07, "epoch": 0.8537213494720577, "percentage": 97.5, "elapsed_time": "3:52:26", "remaining_time": "0:05:57", "throughput": 2496.05, "total_tokens": 34811832}
+{"current_steps": 3320, "total_steps": 3400, "loss": 0.2926, "lr": 1.51284890232406e-07, "epoch": 0.8550090136492403, "percentage": 97.65, "elapsed_time": "3:53:53", "remaining_time": "0:05:38", "throughput": 2484.34, "total_tokens": 34864696}
+{"current_steps": 3325, "total_steps": 3400, "loss": 0.2606, "lr": 1.3297336026280027e-07, "epoch": 0.8562966778264228, "percentage": 97.79, "elapsed_time": "3:55:20", "remaining_time": "0:05:18", "throughput": 2472.84, "total_tokens": 34917584}
+{"current_steps": 3330, "total_steps": 3400, "loss": 0.3203, "lr": 1.158411928280645e-07, "epoch": 0.8575843420036054, "percentage": 97.94, "elapsed_time": "3:56:47", "remaining_time": "0:04:58", "throughput": 2461.38, "total_tokens": 34969720}
+{"current_steps": 3335, "total_steps": 3400, "loss": 0.3211, "lr": 9.988879310649513e-08, "epoch": 0.8588720061807881, "percentage": 98.09, "elapsed_time": "3:58:13", "remaining_time": "0:04:38", "throughput": 2450.16, "total_tokens": 35021296}
+{"current_steps": 3340, "total_steps": 3400, "loss": 0.2923, "lr": 8.511653837470212e-08, "epoch": 0.8601596703579707, "percentage": 98.24, "elapsed_time": "3:59:41", "remaining_time": "0:04:18", "throughput": 2438.82, "total_tokens": 35073120}
+{"current_steps": 3345, "total_steps": 3400, "loss": 0.289, "lr": 7.152477799867719e-08, "epoch": 0.8614473345351532, "percentage": 98.38, "elapsed_time": "4:01:07", "remaining_time": "0:03:57", "throughput": 2427.92, "total_tokens": 35126296}
+{"current_steps": 3350, "total_steps": 3400, "loss": 0.3253, "lr": 5.911383342556143e-08, "epoch": 0.8627349987123358, "percentage": 98.53, "elapsed_time": "4:02:35", "remaining_time": "0:03:37", "throughput": 2416.91, "total_tokens": 35179104}
+{"current_steps": 3350, "total_steps": 3400, "eval_loss": 0.4714648127555847, "epoch": 0.8627349987123358, "percentage": 98.53, "elapsed_time": "4:03:13", "remaining_time": "0:03:37", "throughput": 2410.68, "total_tokens": 35179104}