Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -54,3 +54,5 @@
|
|
| 54 |
{"step": 1080, "tokens": 566231040, "loss": 3.5009490966796877, "tokens_per_second": 993456.0662475126, "lr": 0.0008100000000000001, "gradient_norm": 0.3382250666618347, "benchmark": false}
|
| 55 |
{"step": 1100, "tokens": 576716800, "loss": 3.4624401092529298, "tokens_per_second": 990775.8492234668, "lr": 0.0008250000000000001, "gradient_norm": 0.3198245167732239, "benchmark": false}
|
| 56 |
{"step": 1120, "tokens": 587202560, "loss": 3.4398429870605467, "tokens_per_second": 850654.6348279766, "lr": 0.0008400000000000001, "gradient_norm": 0.3153975307941437, "benchmark": false}
|
|
|
|
|
|
|
|
|
| 54 |
{"step": 1080, "tokens": 566231040, "loss": 3.5009490966796877, "tokens_per_second": 993456.0662475126, "lr": 0.0008100000000000001, "gradient_norm": 0.3382250666618347, "benchmark": false}
|
| 55 |
{"step": 1100, "tokens": 576716800, "loss": 3.4624401092529298, "tokens_per_second": 990775.8492234668, "lr": 0.0008250000000000001, "gradient_norm": 0.3198245167732239, "benchmark": false}
|
| 56 |
{"step": 1120, "tokens": 587202560, "loss": 3.4398429870605467, "tokens_per_second": 850654.6348279766, "lr": 0.0008400000000000001, "gradient_norm": 0.3153975307941437, "benchmark": false}
|
| 57 |
+
{"step": 1140, "tokens": 597688320, "loss": 3.4438480377197265, "tokens_per_second": 980482.9249238867, "lr": 0.000855, "gradient_norm": 0.32889819145202637, "benchmark": false}
|
| 58 |
+
{"step": 1160, "tokens": 608174080, "loss": 3.4141963958740233, "tokens_per_second": 950779.5897118163, "lr": 0.00087, "gradient_norm": 0.31094542145729065, "benchmark": false}
|