Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -228,3 +228,5 @@
|
|
| 228 |
{"step": 4560, "tokens": 2390753280, "loss": 2.969675827026367, "tokens_per_second": 983421.0391750208, "lr": 0.0015, "gradient_norm": 0.08892372250556946, "benchmark": false}
|
| 229 |
{"step": 4580, "tokens": 2401239040, "loss": 2.961945915222168, "tokens_per_second": 969252.2172794534, "lr": 0.0015, "gradient_norm": 0.10147012025117874, "benchmark": false}
|
| 230 |
{"step": 4600, "tokens": 2411724800, "loss": 2.9258108139038086, "tokens_per_second": 982775.4198475868, "lr": 0.0015, "gradient_norm": 0.09514818340539932, "benchmark": false}
|
|
|
|
|
|
|
|
|
| 228 |
{"step": 4560, "tokens": 2390753280, "loss": 2.969675827026367, "tokens_per_second": 983421.0391750208, "lr": 0.0015, "gradient_norm": 0.08892372250556946, "benchmark": false}
|
| 229 |
{"step": 4580, "tokens": 2401239040, "loss": 2.961945915222168, "tokens_per_second": 969252.2172794534, "lr": 0.0015, "gradient_norm": 0.10147012025117874, "benchmark": false}
|
| 230 |
{"step": 4600, "tokens": 2411724800, "loss": 2.9258108139038086, "tokens_per_second": 982775.4198475868, "lr": 0.0015, "gradient_norm": 0.09514818340539932, "benchmark": false}
|
| 231 |
+
{"step": 4620, "tokens": 2422210560, "loss": 2.9655227661132812, "tokens_per_second": 940298.4467211306, "lr": 0.0015, "gradient_norm": 0.0923612043261528, "benchmark": false}
|
| 232 |
+
{"step": 4640, "tokens": 2432696320, "loss": 2.951999282836914, "tokens_per_second": 937618.4046212843, "lr": 0.0015, "gradient_norm": 0.09763544797897339, "benchmark": false}
|