Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -238,3 +238,5 @@
|
|
| 238 |
{"step": 4760, "tokens": 2495610880, "loss": 2.9715957641601562, "tokens_per_second": 969051.8322886985, "lr": 0.0015, "gradient_norm": 0.09438515454530716, "benchmark": false}
|
| 239 |
{"step": 4780, "tokens": 2506096640, "loss": 2.970972442626953, "tokens_per_second": 961760.1791516629, "lr": 0.0015, "gradient_norm": 0.07773580402135849, "benchmark": false}
|
| 240 |
{"step": 4800, "tokens": 2516582400, "loss": 2.9481992721557617, "tokens_per_second": 971270.9862248712, "lr": 0.0015, "gradient_norm": 0.11723429709672928, "benchmark": false}
|
|
|
|
|
|
|
|
|
| 238 |
{"step": 4760, "tokens": 2495610880, "loss": 2.9715957641601562, "tokens_per_second": 969051.8322886985, "lr": 0.0015, "gradient_norm": 0.09438515454530716, "benchmark": false}
|
| 239 |
{"step": 4780, "tokens": 2506096640, "loss": 2.970972442626953, "tokens_per_second": 961760.1791516629, "lr": 0.0015, "gradient_norm": 0.07773580402135849, "benchmark": false}
|
| 240 |
{"step": 4800, "tokens": 2516582400, "loss": 2.9481992721557617, "tokens_per_second": 971270.9862248712, "lr": 0.0015, "gradient_norm": 0.11723429709672928, "benchmark": false}
|
| 241 |
+
{"step": 4820, "tokens": 2527068160, "loss": 2.9477846145629885, "tokens_per_second": 966117.5754807027, "lr": 0.0015, "gradient_norm": 0.08931349217891693, "benchmark": false}
|
| 242 |
+
{"step": 4840, "tokens": 2537553920, "loss": 2.9338357925415037, "tokens_per_second": 972008.3428573115, "lr": 0.0015, "gradient_norm": 0.08552338927984238, "benchmark": false}
|