Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -66,3 +66,5 @@
|
|
| 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}
|
|
|
|
|
|
|
|
|
| 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}
|
| 69 |
+
{"step": 1380, "tokens": 723517440, "loss": 3.356670379638672, "tokens_per_second": 983891.7629701059, "lr": 0.001035, "gradient_norm": 0.32045817375183105, "benchmark": false}
|
| 70 |
+
{"step": 1400, "tokens": 734003200, "loss": 3.3711917877197264, "tokens_per_second": 984612.4124598544, "lr": 0.00105, "gradient_norm": 0.25579288601875305, "benchmark": false}
|