Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -83,3 +83,5 @@
|
|
| 83 |
{"step": 1660, "tokens": 870318080, "loss": 3.2745872497558595, "tokens_per_second": 982150.9602999857, "lr": 0.001245, "gradient_norm": 0.2505227327346802, "benchmark": false}
|
| 84 |
{"step": 1680, "tokens": 880803840, "loss": 3.2768791198730467, "tokens_per_second": 986788.4008772722, "lr": 0.00126, "gradient_norm": 0.23133485019207, "benchmark": false}
|
| 85 |
{"step": 1700, "tokens": 891289600, "loss": 3.2841224670410156, "tokens_per_second": 935487.5310804343, "lr": 0.001275, "gradient_norm": 0.26458561420440674, "benchmark": false}
|
|
|
|
|
|
|
|
|
| 83 |
{"step": 1660, "tokens": 870318080, "loss": 3.2745872497558595, "tokens_per_second": 982150.9602999857, "lr": 0.001245, "gradient_norm": 0.2505227327346802, "benchmark": false}
|
| 84 |
{"step": 1680, "tokens": 880803840, "loss": 3.2768791198730467, "tokens_per_second": 986788.4008772722, "lr": 0.00126, "gradient_norm": 0.23133485019207, "benchmark": false}
|
| 85 |
{"step": 1700, "tokens": 891289600, "loss": 3.2841224670410156, "tokens_per_second": 935487.5310804343, "lr": 0.001275, "gradient_norm": 0.26458561420440674, "benchmark": false}
|
| 86 |
+
{"step": 1720, "tokens": 901775360, "loss": 3.272447967529297, "tokens_per_second": 983097.8905470619, "lr": 0.00129, "gradient_norm": 0.23839032649993896, "benchmark": false}
|
| 87 |
+
{"step": 1740, "tokens": 912261120, "loss": 3.2812328338623047, "tokens_per_second": 980146.4442826945, "lr": 0.001305, "gradient_norm": 0.2654002904891968, "benchmark": false}
|