Training in progress, step 2300

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfdde134a211d113ac15985ca670d8214e7b0ef4860c3a3926ee43121c0822b6
+oid sha256:83713538d7c41870e13178745ef172d71bfaba5ed873b0c7d6d31c872dec52a0
 size 29034840

trainer_log.jsonl

@@ -497,3 +497,14 @@
 {"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}
+{"current_steps": 2255, "total_steps": 3400, "loss": 0.3544, "lr": 2.7931010410023518e-05, "epoch": 0.5807365439093485, "percentage": 66.32, "elapsed_time": "8:32:49", "remaining_time": "4:20:23", "throughput": 769.6, "total_tokens": 23680112}
+{"current_steps": 2260, "total_steps": 3400, "loss": 0.3467, "lr": 2.771308221117309e-05, "epoch": 0.582024208086531, "percentage": 66.47, "elapsed_time": "8:34:15", "remaining_time": "4:19:24", "throughput": 769.13, "total_tokens": 23731896}
+{"current_steps": 2265, "total_steps": 3400, "loss": 0.3374, "lr": 2.749568110121545e-05, "epoch": 0.5833118722637136, "percentage": 66.62, "elapsed_time": "8:35:43", "remaining_time": "4:18:26", "throughput": 768.64, "total_tokens": 23784616}
+{"current_steps": 2270, "total_steps": 3400, "loss": 0.3509, "lr": 2.7278812221718924e-05, "epoch": 0.5845995364408962, "percentage": 66.76, "elapsed_time": "8:37:09", "remaining_time": "4:17:26", "throughput": 768.19, "total_tokens": 23836920}
+{"current_steps": 2275, "total_steps": 3400, "loss": 0.3014, "lr": 2.7062480701664488e-05, "epoch": 0.5858872006180788, "percentage": 66.91, "elapsed_time": "8:38:37", "remaining_time": "4:16:27", "throughput": 767.75, "total_tokens": 23890792}
+{"current_steps": 2280, "total_steps": 3400, "loss": 0.4672, "lr": 2.6846691657324473e-05, "epoch": 0.5871748647952614, "percentage": 67.06, "elapsed_time": "8:40:05", "remaining_time": "4:15:28", "throughput": 767.29, "total_tokens": 23943264}
+{"current_steps": 2285, "total_steps": 3400, "loss": 0.2817, "lr": 2.663145019214163e-05, "epoch": 0.588462528972444, "percentage": 67.21, "elapsed_time": "8:41:32", "remaining_time": "4:14:29", "throughput": 766.81, "total_tokens": 23995760}
+{"current_steps": 2290, "total_steps": 3400, "loss": 0.3538, "lr": 2.6416761396608362e-05, "epoch": 0.5897501931496266, "percentage": 67.35, "elapsed_time": "8:43:00", "remaining_time": "4:13:30", "throughput": 766.36, "total_tokens": 24048696}
+{"current_steps": 2295, "total_steps": 3400, "loss": 0.3018, "lr": 2.6202630348146324e-05, "epoch": 0.5910378573268091, "percentage": 67.5, "elapsed_time": "8:44:27", "remaining_time": "4:12:31", "throughput": 765.93, "total_tokens": 24102248}
+{"current_steps": 2300, "total_steps": 3400, "loss": 0.3322, "lr": 2.598906211098643e-05, "epoch": 0.5923255215039918, "percentage": 67.65, "elapsed_time": "8:45:55", "remaining_time": "4:11:31", "throughput": 765.47, "total_tokens": 24154624}
+{"current_steps": 2300, "total_steps": 3400, "eval_loss": 0.4960116744041443, "epoch": 0.5923255215039918, "percentage": 67.65, "elapsed_time": "8:46:33", "remaining_time": "4:11:49", "throughput": 764.54, "total_tokens": 24154624}