Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -64,3 +64,5 @@
|
|
| 64 |
{"step": 1280, "tokens": 671088640, "loss": 3.361439895629883, "tokens_per_second": 991867.7331378494, "lr": 0.00096, "gradient_norm": 0.2679154574871063, "benchmark": false}
|
| 65 |
{"step": 1300, "tokens": 681574400, "loss": 3.3786773681640625, "tokens_per_second": 994066.2303459286, "lr": 0.0009750000000000001, "gradient_norm": 0.27311596274375916, "benchmark": false}
|
| 66 |
{"step": 1320, "tokens": 692060160, "loss": 3.3780323028564454, "tokens_per_second": 999815.6838591986, "lr": 0.00099, "gradient_norm": 0.28089940547943115, "benchmark": false}
|
|
|
|
|
|
|
|
|
| 64 |
{"step": 1280, "tokens": 671088640, "loss": 3.361439895629883, "tokens_per_second": 991867.7331378494, "lr": 0.00096, "gradient_norm": 0.2679154574871063, "benchmark": false}
|
| 65 |
{"step": 1300, "tokens": 681574400, "loss": 3.3786773681640625, "tokens_per_second": 994066.2303459286, "lr": 0.0009750000000000001, "gradient_norm": 0.27311596274375916, "benchmark": false}
|
| 66 |
{"step": 1320, "tokens": 692060160, "loss": 3.3780323028564454, "tokens_per_second": 999815.6838591986, "lr": 0.00099, "gradient_norm": 0.28089940547943115, "benchmark": false}
|
| 67 |
+
{"step": 1340, "tokens": 702545920, "loss": 3.3420379638671873, "tokens_per_second": 983372.1879870299, "lr": 0.001005, "gradient_norm": 0.265042781829834, "benchmark": false}
|
| 68 |
+
{"step": 1360, "tokens": 713031680, "loss": 3.3285560607910156, "tokens_per_second": 983311.0842673131, "lr": 0.00102, "gradient_norm": 0.251801073551178, "benchmark": false}
|