Training in progress, step 2250

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce36e87ead430510e59f496a26ace5905d198e41651fda96953f593c5677ca2b
+oid sha256:cfdde134a211d113ac15985ca670d8214e7b0ef4860c3a3926ee43121c0822b6
 size 29034840

trainer_log.jsonl

@@ -486,3 +486,14 @@
 {"current_steps": 2195, "total_steps": 3400, "loss": 0.3615, "lr": 3.058537355076683e-05, "epoch": 0.5652845737831573, "percentage": 64.56, "elapsed_time": "8:13:54", "remaining_time": "4:31:08", "throughput": 777.76, "total_tokens": 23048848}
 {"current_steps": 2200, "total_steps": 3400, "loss": 0.3232, "lr": 3.0361525742465973e-05, "epoch": 0.56657223796034, "percentage": 64.71, "elapsed_time": "8:15:22", "remaining_time": "4:30:12", "throughput": 777.25, "total_tokens": 23101488}
 {"current_steps": 2200, "total_steps": 3400, "eval_loss": 0.45173853635787964, "epoch": 0.56657223796034, "percentage": 64.71, "elapsed_time": "8:16:00", "remaining_time": "4:30:32", "throughput": 776.25, "total_tokens": 23101488}
+{"current_steps": 2205, "total_steps": 3400, "loss": 0.3453, "lr": 3.0138142386977787e-05, "epoch": 0.5678599021375226, "percentage": 64.85, "elapsed_time": "8:17:33", "remaining_time": "4:29:38", "throughput": 775.61, "total_tokens": 23154320}
+{"current_steps": 2210, "total_steps": 3400, "loss": 0.3277, "lr": 2.991522876735154e-05, "epoch": 0.5691475663147051, "percentage": 65.0, "elapsed_time": "8:19:00", "remaining_time": "4:28:41", "throughput": 775.09, "total_tokens": 23206640}
+{"current_steps": 2215, "total_steps": 3400, "loss": 0.3368, "lr": 2.9692790155527227e-05, "epoch": 0.5704352304918877, "percentage": 65.15, "elapsed_time": "8:20:27", "remaining_time": "4:27:44", "throughput": 774.58, "total_tokens": 23258992}
+{"current_steps": 2220, "total_steps": 3400, "loss": 0.3518, "lr": 2.9470831812210837e-05, "epoch": 0.5717228946690703, "percentage": 65.29, "elapsed_time": "8:21:55", "remaining_time": "4:26:47", "throughput": 774.08, "total_tokens": 23311640}
+{"current_steps": 2225, "total_steps": 3400, "loss": 0.3142, "lr": 2.924935898674992e-05, "epoch": 0.5730105588462528, "percentage": 65.44, "elapsed_time": "8:23:22", "remaining_time": "4:25:49", "throughput": 773.58, "total_tokens": 23364048}
+{"current_steps": 2230, "total_steps": 3400, "loss": 0.347, "lr": 2.902837691700945e-05, "epoch": 0.5742982230234355, "percentage": 65.59, "elapsed_time": "8:24:49", "remaining_time": "4:24:51", "throughput": 773.1, "total_tokens": 23416632}
+{"current_steps": 2235, "total_steps": 3400, "loss": 0.3807, "lr": 2.880789082924798e-05, "epoch": 0.5755858872006181, "percentage": 65.74, "elapsed_time": "8:26:16", "remaining_time": "4:23:54", "throughput": 772.58, "total_tokens": 23468608}
+{"current_steps": 2240, "total_steps": 3400, "loss": 0.3271, "lr": 2.858790593799405e-05, "epoch": 0.5768735513778007, "percentage": 65.88, "elapsed_time": "8:27:43", "remaining_time": "4:22:55", "throughput": 772.12, "total_tokens": 23521312}
+{"current_steps": 2245, "total_steps": 3400, "loss": 0.296, "lr": 2.8368427445922696e-05, "epoch": 0.5781612155549832, "percentage": 66.03, "elapsed_time": "8:29:11", "remaining_time": "4:21:57", "throughput": 771.62, "total_tokens": 23574104}
+{"current_steps": 2250, "total_steps": 3400, "loss": 0.325, "lr": 2.8149460543732664e-05, "epoch": 0.5794488797321659, "percentage": 66.18, "elapsed_time": "8:30:37", "remaining_time": "4:20:59", "throughput": 771.17, "total_tokens": 23626952}
+{"current_steps": 2250, "total_steps": 3400, "eval_loss": 0.4990580379962921, "epoch": 0.5794488797321659, "percentage": 66.18, "elapsed_time": "8:31:15", "remaining_time": "4:21:18", "throughput": 770.21, "total_tokens": 23626952}