Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -679,3 +679,5 @@
|
|
| 679 |
{"step": 13580, "tokens": 7119831040, "loss": 2.81064453125, "tokens_per_second": 988468.4767134241, "lr": 0.0015, "gradient_norm": 0.11042139679193497, "benchmark": false}
|
| 680 |
{"step": 13600, "tokens": 7130316800, "loss": 2.7997358322143553, "tokens_per_second": 990509.1251335517, "lr": 0.0015, "gradient_norm": 0.11651360243558884, "benchmark": false}
|
| 681 |
{"step": 13620, "tokens": 7140802560, "loss": 2.799270820617676, "tokens_per_second": 985892.9055006963, "lr": 0.0015, "gradient_norm": 0.13365843892097473, "benchmark": false}
|
|
|
|
|
|
|
|
|
| 679 |
{"step": 13580, "tokens": 7119831040, "loss": 2.81064453125, "tokens_per_second": 988468.4767134241, "lr": 0.0015, "gradient_norm": 0.11042139679193497, "benchmark": false}
|
| 680 |
{"step": 13600, "tokens": 7130316800, "loss": 2.7997358322143553, "tokens_per_second": 990509.1251335517, "lr": 0.0015, "gradient_norm": 0.11651360243558884, "benchmark": false}
|
| 681 |
{"step": 13620, "tokens": 7140802560, "loss": 2.799270820617676, "tokens_per_second": 985892.9055006963, "lr": 0.0015, "gradient_norm": 0.13365843892097473, "benchmark": false}
|
| 682 |
+
{"step": 13640, "tokens": 7151288320, "loss": 2.809065246582031, "tokens_per_second": 982371.3983031667, "lr": 0.0015, "gradient_norm": 0.12926508486270905, "benchmark": false}
|
| 683 |
+
{"step": 13660, "tokens": 7161774080, "loss": 2.795080375671387, "tokens_per_second": 978992.4936671671, "lr": 0.0015, "gradient_norm": 0.111018605530262, "benchmark": false}
|