Upload sft_metrics.jsonl with huggingface_hub
Browse files- sft_metrics.jsonl +10 -0
sft_metrics.jsonl
CHANGED
|
@@ -338,3 +338,13 @@
|
|
| 338 |
{"timestamp": 1787700154.2530887, "elapsed_hours": 0.7333289891481399, "event": "train_step", "step": 11190, "epoch": 1, "loss": 1.5150245690345765, "perplexity": 4.549532903103726, "muon_lr": 0.0009398779953112853, "adamw_lr": 2.3496949882782135e-05, "tokens_per_sec": 562720.5059729201, "vram_gb": 2.785654067993164, "tokens_processed": 1466695680}
|
| 339 |
{"timestamp": 1787700161.7700543, "elapsed_hours": 0.7354170350895988, "event": "train_step", "step": 11200, "epoch": 1, "loss": 1.50298379778862, "perplexity": 4.495081494482078, "muon_lr": 0.0009376414632946762, "adamw_lr": 2.3441036582366908e-05, "tokens_per_sec": 561603.7083331369, "vram_gb": 2.363706111907959, "tokens_processed": 1468006400}
|
| 340 |
{"timestamp": 1787700174.5957875, "elapsed_hours": 0.7389797388182746, "event": "validation", "step": 11200, "val_loss": 1.4711714816093444, "val_perplexity": 4.354333175589024, "best_loss": 1.4711714816093444}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 338 |
{"timestamp": 1787700154.2530887, "elapsed_hours": 0.7333289891481399, "event": "train_step", "step": 11190, "epoch": 1, "loss": 1.5150245690345765, "perplexity": 4.549532903103726, "muon_lr": 0.0009398779953112853, "adamw_lr": 2.3496949882782135e-05, "tokens_per_sec": 562720.5059729201, "vram_gb": 2.785654067993164, "tokens_processed": 1466695680}
|
| 339 |
{"timestamp": 1787700161.7700543, "elapsed_hours": 0.7354170350895988, "event": "train_step", "step": 11200, "epoch": 1, "loss": 1.50298379778862, "perplexity": 4.495081494482078, "muon_lr": 0.0009376414632946762, "adamw_lr": 2.3441036582366908e-05, "tokens_per_sec": 561603.7083331369, "vram_gb": 2.363706111907959, "tokens_processed": 1468006400}
|
| 340 |
{"timestamp": 1787700174.5957875, "elapsed_hours": 0.7389797388182746, "event": "validation", "step": 11200, "val_loss": 1.4711714816093444, "val_perplexity": 4.354333175589024, "best_loss": 1.4711714816093444}
|
| 341 |
+
{"timestamp": 1787700182.4547226, "elapsed_hours": 0.741162776350975, "event": "train_step", "step": 11210, "epoch": 1, "loss": 1.48387291431427, "perplexity": 4.409992171619771, "muon_lr": 0.0009365235848488977, "adamw_lr": 2.3413089621222445e-05, "tokens_per_sec": 557692.0342627338, "vram_gb": 2.785654067993164, "tokens_processed": 1469317120}
|
| 342 |
+
{"timestamp": 1787700189.8873324, "elapsed_hours": 0.7432273900508881, "event": "train_step", "step": 11220, "epoch": 1, "loss": 1.4723146998882293, "perplexity": 4.359313975395933, "muon_lr": 0.0009354059671556993, "adamw_lr": 2.3385149178892486e-05, "tokens_per_sec": 556619.246650769, "vram_gb": 2.785654067993164, "tokens_processed": 1470627840}
|
| 343 |
+
{"timestamp": 1787700197.3123276, "elapsed_hours": 0.7452898887793223, "event": "train_step", "step": 11230, "epoch": 1, "loss": 1.4495067512989044, "perplexity": 4.261012257982024, "muon_lr": 0.000934288611997734, "adamw_lr": 2.335721529994335e-05, "tokens_per_sec": 555554.0714768968, "vram_gb": 2.785654067993164, "tokens_processed": 1471938560}
|
| 344 |
+
{"timestamp": 1787700204.8335993, "elapsed_hours": 0.7473791309197744, "event": "train_step", "step": 11240, "epoch": 1, "loss": 1.4391969311237336, "perplexity": 4.217307668190252, "muon_lr": 0.0009320546964160167, "adamw_lr": 2.330136741040042e-05, "tokens_per_sec": 554474.7570939781, "vram_gb": 2.363706111907959, "tokens_processed": 1473249280}
|
| 345 |
+
{"timestamp": 1787700212.2664304, "elapsed_hours": 0.749443806277381, "event": "train_step", "step": 11250, "epoch": 1, "loss": 1.4267358016967773, "perplexity": 4.165081326908745, "muon_lr": 0.0009309381395554654, "adamw_lr": 2.3273453488886636e-05, "tokens_per_sec": 553419.9227817524, "vram_gb": 2.785654067993164, "tokens_processed": 1474560000}
|
| 346 |
+
{"timestamp": 1787700219.6979392, "elapsed_hours": 0.7515081142054664, "event": "train_step", "step": 11260, "epoch": 1, "loss": 1.4427095198631286, "perplexity": 4.232147383266095, "muon_lr": 0.0009298218523565425, "adamw_lr": 2.3245546308913565e-05, "tokens_per_sec": 552371.2126979837, "vram_gb": 2.785654067993164, "tokens_processed": 1475870720}
|
| 347 |
+
{"timestamp": 1787700227.1324198, "elapsed_hours": 0.7535732477241093, "event": "train_step", "step": 11270, "epoch": 1, "loss": 1.450342777967453, "perplexity": 4.264576067376983, "muon_lr": 0.0009287058365997786, "adamw_lr": 2.321764591499447e-05, "tokens_per_sec": 551327.7139214695, "vram_gb": 2.785654067993164, "tokens_processed": 1477181440}
|
| 348 |
+
{"timestamp": 1787700234.6585705, "elapsed_hours": 0.7556638451417287, "event": "train_step", "step": 11280, "epoch": 1, "loss": 1.4568647718429566, "perplexity": 4.292480503738766, "muon_lr": 0.0009264746265326828, "adamw_lr": 2.316186566331707e-05, "tokens_per_sec": 550271.1877844172, "vram_gb": 2.363706111907959, "tokens_processed": 1478492160}
|
| 349 |
+
{"timestamp": 1787700242.0943127, "elapsed_hours": 0.7577293290032281, "event": "train_step", "step": 11290, "epoch": 1, "loss": 1.4326110148429871, "perplexity": 4.189624093871692, "muon_lr": 0.0009253594357812361, "adamw_lr": 2.3133985894530904e-05, "tokens_per_sec": 549239.0386710799, "vram_gb": 2.785654067993164, "tokens_processed": 1479802880}
|
| 350 |
+
{"timestamp": 1787700249.5313933, "elapsed_hours": 0.7597951847314834, "event": "train_step", "step": 11300, "epoch": 1, "loss": 1.463402227163315, "perplexity": 4.320634330166113, "muon_lr": 0.0009242445235897127, "adamw_lr": 2.3106113089742817e-05, "tokens_per_sec": 548212.2646218977, "vram_gb": 2.785654067993164, "tokens_processed": 1481113600}
|