Upload sft_metrics.jsonl with huggingface_hub
Browse files- sft_metrics.jsonl +21 -0
sft_metrics.jsonl
CHANGED
|
@@ -825,3 +825,24 @@
|
|
| 825 |
{"timestamp": 1787660114.220158, "elapsed_hours": 1.7728083203898535, "event": "train_step", "step": 7790, "epoch": 1, "loss": 1.4768651032447815, "perplexity": 4.379195813226256, "muon_lr": 0.00020334894505106066, "adamw_lr": 5.0837236262765165e-06, "tokens_per_sec": 160184.6590352385, "vram_gb": 3.561209201812744, "tokens_processed": 1021050880}
|
| 826 |
{"timestamp": 1787660121.7267833, "elapsed_hours": 1.7748934939172534, "event": "train_step", "step": 7800, "epoch": 1, "loss": 1.4977083885669709, "perplexity": 4.471430539198194, "muon_lr": 0.00020287355127466517, "adamw_lr": 5.071838781866629e-06, "tokens_per_sec": 160201.62461213488, "vram_gb": 3.1426029205322266, "tokens_processed": 1022361600}
|
| 827 |
{"timestamp": 1787660134.576736, "elapsed_hours": 1.7784629253546398, "event": "validation", "step": 7800, "val_loss": 1.4740193009376525, "val_perplexity": 4.366751203525755, "best_loss": 1.4738919711112977}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 825 |
{"timestamp": 1787660114.220158, "elapsed_hours": 1.7728083203898535, "event": "train_step", "step": 7790, "epoch": 1, "loss": 1.4768651032447815, "perplexity": 4.379195813226256, "muon_lr": 0.00020334894505106066, "adamw_lr": 5.0837236262765165e-06, "tokens_per_sec": 160184.6590352385, "vram_gb": 3.561209201812744, "tokens_processed": 1021050880}
|
| 826 |
{"timestamp": 1787660121.7267833, "elapsed_hours": 1.7748934939172534, "event": "train_step", "step": 7800, "epoch": 1, "loss": 1.4977083885669709, "perplexity": 4.471430539198194, "muon_lr": 0.00020287355127466517, "adamw_lr": 5.071838781866629e-06, "tokens_per_sec": 160201.62461213488, "vram_gb": 3.1426029205322266, "tokens_processed": 1022361600}
|
| 827 |
{"timestamp": 1787660134.576736, "elapsed_hours": 1.7784629253546398, "event": "validation", "step": 7800, "val_loss": 1.4740193009376525, "val_perplexity": 4.366751203525755, "best_loss": 1.4738919711112977}
|
| 828 |
+
{"timestamp": 1787660142.457171, "elapsed_hours": 1.7806519350078371, "event": "train_step", "step": 7810, "epoch": 1, "loss": 1.4905705273151397, "perplexity": 4.439627725474933, "muon_lr": 0.00020264947298649164, "adamw_lr": 5.066236824662291e-06, "tokens_per_sec": 159887.63343939488, "vram_gb": 3.561209201812744, "tokens_processed": 1023672320}
|
| 829 |
+
{"timestamp": 1787660149.87832, "elapsed_hours": 1.7827133652899, "event": "train_step", "step": 7820, "epoch": 1, "loss": 1.5056027042865754, "perplexity": 4.506869121225666, "muon_lr": 0.00020243447681950733, "adamw_lr": 5.0608619204876835e-06, "tokens_per_sec": 159907.0053737089, "vram_gb": 3.561209201812744, "tokens_processed": 1024983040}
|
| 830 |
+
{"timestamp": 1787660157.2975395, "elapsed_hours": 1.7847742596599792, "event": "train_step", "step": 7830, "epoch": 1, "loss": 1.4806248617172242, "perplexity": 4.395691522296844, "muon_lr": 0.00020222856494969734, "adamw_lr": 5.055714123742434e-06, "tokens_per_sec": 159926.38036364704, "vram_gb": 3.561209201812744, "tokens_processed": 1026293760}
|
| 831 |
+
{"timestamp": 1787660164.8035853, "elapsed_hours": 1.7868592723210652, "event": "train_step", "step": 7840, "epoch": 1, "loss": 1.439755721092224, "perplexity": 4.21966491595114, "muon_lr": 0.00020184400234580594, "adamw_lr": 5.046100058645149e-06, "tokens_per_sec": 159943.54766314724, "vram_gb": 3.1426029205322266, "tokens_processed": 1027604480}
|
| 832 |
+
{"timestamp": 1787660172.2227588, "elapsed_hours": 1.788920153843032, "event": "train_step", "step": 7850, "epoch": 1, "loss": 1.4730488193035125, "perplexity": 4.3625154073955015, "muon_lr": 0.00020166535550389833, "adamw_lr": 5.041633887597459e-06, "tokens_per_sec": 159962.83745493996, "vram_gb": 3.561209201812744, "tokens_processed": 1028915200}
|
| 833 |
+
{"timestamp": 1787660179.6403866, "elapsed_hours": 1.7909806060128741, "event": "train_step", "step": 7860, "epoch": 1, "loss": 1.5586447060108184, "perplexity": 4.752376011888232, "muon_lr": 0.00020149580074347315, "adamw_lr": 5.037395018586828e-06, "tokens_per_sec": 159982.1206535994, "vram_gb": 3.561209201812744, "tokens_processed": 1030225920}
|
| 834 |
+
{"timestamp": 1787660187.0647047, "elapsed_hours": 1.7930429166555404, "event": "train_step", "step": 7870, "epoch": 1, "loss": 1.547110298871994, "perplexity": 4.6978750942209775, "muon_lr": 0.00020133533978060081, "adamw_lr": 5.033383494515021e-06, "tokens_per_sec": 160001.1930284749, "vram_gb": 3.561209201812744, "tokens_processed": 1031536640}
|
| 835 |
+
{"timestamp": 1787660194.578549, "elapsed_hours": 1.7951300955481, "event": "train_step", "step": 7880, "epoch": 1, "loss": 1.5624843978881835, "perplexity": 4.770658749035708, "muon_lr": 0.0002010417056515879, "adamw_lr": 5.026042641289698e-06, "tokens_per_sec": 160018.00100372054, "vram_gb": 3.1426029205322266, "tokens_processed": 1032847360}
|
| 836 |
+
{"timestamp": 1787660201.999518, "elapsed_hours": 1.7971914758284886, "event": "train_step", "step": 7890, "epoch": 1, "loss": 1.5764704537391663, "perplexity": 4.837850225343746, "muon_lr": 0.00020090853545733024, "adamw_lr": 5.022713386433256e-06, "tokens_per_sec": 160037.07449155438, "vram_gb": 3.561209201812744, "tokens_processed": 1034158080}
|
| 837 |
+
{"timestamp": 1787660209.4204392, "elapsed_hours": 1.7992528429296282, "event": "train_step", "step": 7900, "epoch": 1, "loss": 1.5322220921516418, "perplexity": 4.628450246792224, "muon_lr": 0.00020078446500436126, "adamw_lr": 5.019611625109032e-06, "tokens_per_sec": 160056.1026651007, "vram_gb": 3.561209201812744, "tokens_processed": 1035468800}
|
| 838 |
+
{"timestamp": 1787660216.8437808, "elapsed_hours": 1.801314882238706, "event": "train_step", "step": 7910, "epoch": 1, "loss": 1.5000002765655518, "perplexity": 4.481690309819047, "muon_lr": 0.0002006694955484033, "adamw_lr": 5.016737388710083e-06, "tokens_per_sec": 160075.02391417685, "vram_gb": 3.561209201812744, "tokens_processed": 1036779520}
|
| 839 |
+
{"timestamp": 1787660224.3544085, "elapsed_hours": 1.8034011676576402, "event": "train_step", "step": 7920, "epoch": 1, "loss": 1.4737587583065033, "perplexity": 4.365613626877655, "muon_lr": 0.00020046686418983905, "adamw_lr": 5.0116716047459765e-06, "tokens_per_sec": 160091.7490587121, "vram_gb": 3.1426029205322266, "tokens_processed": 1038090240}
|
| 840 |
+
{"timestamp": 1787660231.7761369, "elapsed_hours": 1.8054627589384715, "event": "train_step", "step": 7930, "epoch": 1, "loss": 1.4766586172580718, "perplexity": 4.378291664008051, "muon_lr": 0.00020037920433807295, "adamw_lr": 5.009480108451824e-06, "tokens_per_sec": 160110.62995507853, "vram_gb": 3.561209201812744, "tokens_processed": 1039400960}
|
| 841 |
+
{"timestamp": 1787660239.2050512, "elapsed_hours": 1.807526346180174, "event": "train_step", "step": 7940, "epoch": 1, "loss": 1.4780614483356476, "perplexity": 4.384437977733003, "muon_lr": 0.00020030064958497749, "adamw_lr": 5.007516239624437e-06, "tokens_per_sec": 160129.28961693225, "vram_gb": 3.561209201812744, "tokens_processed": 1040711680}
|
| 842 |
+
{"timestamp": 1787660246.6268055, "elapsed_hours": 1.8095879445473353, "event": "train_step", "step": 7950, "epoch": 1, "loss": 1.4680641400814056, "perplexity": 4.340823775316356, "muon_lr": 0.00020023120072560857, "adamw_lr": 5.005780018140214e-06, "tokens_per_sec": 160148.08444134626, "vram_gb": 3.561209201812744, "tokens_processed": 1042022400}
|
| 843 |
+
{"timestamp": 1787660254.1373665, "elapsed_hours": 1.8116742114888298, "event": "train_step", "step": 7960, "epoch": 1, "loss": 1.4661862790584563, "perplexity": 4.332679960410664, "muon_lr": 0.00020011962340746065, "adamw_lr": 5.002990585186516e-06, "tokens_per_sec": 160164.6483586644, "vram_gb": 3.1426029205322266, "tokens_processed": 1043333120}
|
| 844 |
+
{"timestamp": 1787660261.5717862, "elapsed_hours": 1.8137393282519447, "event": "train_step", "step": 7970, "epoch": 1, "loss": 1.48315913438797, "perplexity": 4.406845530870626, "muon_lr": 0.00020007749607796042, "adamw_lr": 5.001937401949011e-06, "tokens_per_sec": 160183.0490462424, "vram_gb": 3.561209201812744, "tokens_processed": 1044643840}
|
| 845 |
+
{"timestamp": 1787660268.9921649, "elapsed_hours": 1.815800544420878, "event": "train_step", "step": 7980, "epoch": 1, "loss": 1.5077255654335022, "perplexity": 4.51644674095898, "muon_lr": 0.0002000444769007323, "adamw_lr": 5.001111922518308e-06, "tokens_per_sec": 160201.749637107, "vram_gb": 3.561209201812744, "tokens_processed": 1045954560}
|
| 846 |
+
{"timestamp": 1787660276.4123886, "elapsed_hours": 1.8178617177406946, "event": "train_step", "step": 7990, "epoch": 1, "loss": 1.5254255557060241, "perplexity": 4.597099475016507, "muon_lr": 0.00020002056620996485, "adamw_lr": 5.000514155249121e-06, "tokens_per_sec": 160220.41262497663, "vram_gb": 3.561209201812744, "tokens_processed": 1047265280}
|
| 847 |
+
{"timestamp": 1787660283.923845, "elapsed_hours": 1.8199482333660126, "event": "train_step", "step": 8000, "epoch": 1, "loss": 1.5243780636787414, "perplexity": 4.592286571147093, "muon_lr": 0.0002000000711636264, "adamw_lr": 5.00000177909066e-06, "tokens_per_sec": 160236.79738136733, "vram_gb": 3.1426029205322266, "tokens_processed": 1048576000}
|
| 848 |
+
{"timestamp": 1787660296.7712784, "elapsed_hours": 1.823516964846187, "event": "validation", "step": 8000, "val_loss": 1.4739431405067445, "val_perplexity": 4.366418642536581, "best_loss": 1.4738919711112977}
|