Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -232,3 +232,5 @@
|
|
| 232 |
{"step": 4640, "tokens": 2432696320, "loss": 2.951999282836914, "tokens_per_second": 937618.4046212843, "lr": 0.0015, "gradient_norm": 0.09763544797897339, "benchmark": false}
|
| 233 |
{"step": 4660, "tokens": 2443182080, "loss": 2.966028022766113, "tokens_per_second": 966263.594087319, "lr": 0.0015, "gradient_norm": 0.10028868168592453, "benchmark": false}
|
| 234 |
{"step": 4680, "tokens": 2453667840, "loss": 2.9490474700927733, "tokens_per_second": 960512.0055085152, "lr": 0.0015, "gradient_norm": 0.09279947727918625, "benchmark": false}
|
|
|
|
|
|
|
|
|
| 232 |
{"step": 4640, "tokens": 2432696320, "loss": 2.951999282836914, "tokens_per_second": 937618.4046212843, "lr": 0.0015, "gradient_norm": 0.09763544797897339, "benchmark": false}
|
| 233 |
{"step": 4660, "tokens": 2443182080, "loss": 2.966028022766113, "tokens_per_second": 966263.594087319, "lr": 0.0015, "gradient_norm": 0.10028868168592453, "benchmark": false}
|
| 234 |
{"step": 4680, "tokens": 2453667840, "loss": 2.9490474700927733, "tokens_per_second": 960512.0055085152, "lr": 0.0015, "gradient_norm": 0.09279947727918625, "benchmark": false}
|
| 235 |
+
{"step": 4700, "tokens": 2464153600, "loss": 2.986806106567383, "tokens_per_second": 971028.7885817649, "lr": 0.0015, "gradient_norm": 0.08970464766025543, "benchmark": false}
|
| 236 |
+
{"step": 4720, "tokens": 2474639360, "loss": 2.962502670288086, "tokens_per_second": 972814.0600136536, "lr": 0.0015, "gradient_norm": 0.09654846042394638, "benchmark": false}
|