Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -653,3 +653,5 @@
|
|
| 653 |
{"step": 13060, "tokens": 6847201280, "loss": 2.7823381423950195, "tokens_per_second": 977186.2934301094, "lr": 0.0015, "gradient_norm": 0.10892217606306076, "benchmark": false}
|
| 654 |
{"step": 13080, "tokens": 6857687040, "loss": 2.7726795196533205, "tokens_per_second": 978850.6546447634, "lr": 0.0015, "gradient_norm": 0.09092258661985397, "benchmark": false}
|
| 655 |
{"step": 13100, "tokens": 6868172800, "loss": 2.800714683532715, "tokens_per_second": 980305.0475917425, "lr": 0.0015, "gradient_norm": 0.12226828932762146, "benchmark": false}
|
|
|
|
|
|
|
|
|
| 653 |
{"step": 13060, "tokens": 6847201280, "loss": 2.7823381423950195, "tokens_per_second": 977186.2934301094, "lr": 0.0015, "gradient_norm": 0.10892217606306076, "benchmark": false}
|
| 654 |
{"step": 13080, "tokens": 6857687040, "loss": 2.7726795196533205, "tokens_per_second": 978850.6546447634, "lr": 0.0015, "gradient_norm": 0.09092258661985397, "benchmark": false}
|
| 655 |
{"step": 13100, "tokens": 6868172800, "loss": 2.800714683532715, "tokens_per_second": 980305.0475917425, "lr": 0.0015, "gradient_norm": 0.12226828932762146, "benchmark": false}
|
| 656 |
+
{"step": 13120, "tokens": 6878658560, "loss": 2.8094324111938476, "tokens_per_second": 971826.2870966541, "lr": 0.0015, "gradient_norm": 0.1026187464594841, "benchmark": false}
|
| 657 |
+
{"step": 13140, "tokens": 6889144320, "loss": 2.798151969909668, "tokens_per_second": 971155.9418639137, "lr": 0.0015, "gradient_norm": 0.11680211126804352, "benchmark": false}
|