Training in progress, step 1800

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adf72d38ec00ef740c0dd6070b4c5e7e4025640731572f71c655ba6e0033d445
+oid sha256:69a5ff5ee90349b6b28053c5cfac6617d1d42ea2529e5b55624923cc2833ed0a
 size 29034840

trainer_log.jsonl

@@ -383,3 +383,14 @@
 {"current_steps": 1745, "total_steps": 3882, "loss": 0.3148, "lr": 6.237423760163156e-05, "epoch": 0.8987895956734484, "percentage": 44.95, "elapsed_time": "8:53:36", "remaining_time": "10:53:29", "throughput": 637.47, "total_tokens": 20409744}
 {"current_steps": 1750, "total_steps": 3882, "loss": 0.3233, "lr": 6.216773432508325e-05, "epoch": 0.9013649240278135, "percentage": 45.08, "elapsed_time": "8:55:06", "remaining_time": "10:51:54", "throughput": 637.52, "total_tokens": 20468200}
 {"current_steps": 1750, "total_steps": 3882, "eval_loss": 0.3325226604938507, "epoch": 0.9013649240278135, "percentage": 45.08, "elapsed_time": "8:55:25", "remaining_time": "10:52:18", "throughput": 637.13, "total_tokens": 20468200}
+{"current_steps": 1755, "total_steps": 3882, "loss": 0.3731, "lr": 6.196101019592264e-05, "epoch": 0.9039402523821787, "percentage": 45.21, "elapsed_time": "8:56:59", "remaining_time": "10:50:49", "throughput": 637.08, "total_tokens": 20526696}
+{"current_steps": 1760, "total_steps": 3882, "loss": 0.3092, "lr": 6.175406896633258e-05, "epoch": 0.9065155807365439, "percentage": 45.34, "elapsed_time": "8:58:28", "remaining_time": "10:49:14", "throughput": 637.14, "total_tokens": 20585160}
+{"current_steps": 1765, "total_steps": 3882, "loss": 0.311, "lr": 6.154691439243644e-05, "epoch": 0.9090909090909091, "percentage": 45.47, "elapsed_time": "8:59:57", "remaining_time": "10:47:38", "throughput": 637.2, "total_tokens": 20643672}
+{"current_steps": 1770, "total_steps": 3882, "loss": 0.3085, "lr": 6.133955023422991e-05, "epoch": 0.9116662374452743, "percentage": 45.6, "elapsed_time": "9:01:26", "remaining_time": "10:46:03", "throughput": 637.26, "total_tokens": 20702152}
+{"current_steps": 1775, "total_steps": 3882, "loss": 0.3236, "lr": 6.11319802555128e-05, "epoch": 0.9142415657996394, "percentage": 45.72, "elapsed_time": "9:02:54", "remaining_time": "10:44:27", "throughput": 637.32, "total_tokens": 20760664}
+{"current_steps": 1780, "total_steps": 3882, "loss": 0.4067, "lr": 6.092420822382069e-05, "epoch": 0.9168168941540046, "percentage": 45.85, "elapsed_time": "9:04:23", "remaining_time": "10:42:52", "throughput": 637.37, "total_tokens": 20819144}
+{"current_steps": 1785, "total_steps": 3882, "loss": 0.3228, "lr": 6.071623791035657e-05, "epoch": 0.9193922225083698, "percentage": 45.98, "elapsed_time": "9:05:52", "remaining_time": "10:41:17", "throughput": 637.43, "total_tokens": 20877624}
+{"current_steps": 1790, "total_steps": 3882, "loss": 0.2672, "lr": 6.050807308992234e-05, "epoch": 0.921967550862735, "percentage": 46.11, "elapsed_time": "9:07:21", "remaining_time": "10:39:41", "throughput": 637.5, "total_tokens": 20936112}
+{"current_steps": 1795, "total_steps": 3882, "loss": 0.3308, "lr": 6.02997175408504e-05, "epoch": 0.9245428792171002, "percentage": 46.24, "elapsed_time": "9:08:50", "remaining_time": "10:38:07", "throughput": 637.55, "total_tokens": 20994608}
+{"current_steps": 1800, "total_steps": 3882, "loss": 0.3279, "lr": 6.009117504493493e-05, "epoch": 0.9271182075714653, "percentage": 46.37, "elapsed_time": "9:10:18", "remaining_time": "10:36:31", "throughput": 637.61, "total_tokens": 21053080}
+{"current_steps": 1800, "total_steps": 3882, "eval_loss": 0.3501794636249542, "epoch": 0.9271182075714653, "percentage": 46.37, "elapsed_time": "9:10:37", "remaining_time": "10:36:53", "throughput": 637.24, "total_tokens": 21053080}