Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -687,3 +687,5 @@
|
|
| 687 |
{"step": 13740, "tokens": 7203717120, "loss": 2.792901611328125, "tokens_per_second": 986272.0580112083, "lr": 0.0015, "gradient_norm": 0.11577098816633224, "benchmark": false}
|
| 688 |
{"step": 13760, "tokens": 7214202880, "loss": 2.7878217697143555, "tokens_per_second": 985767.097813454, "lr": 0.0015, "gradient_norm": 0.10202588886022568, "benchmark": false}
|
| 689 |
{"step": 13780, "tokens": 7224688640, "loss": 2.793878746032715, "tokens_per_second": 984036.116605316, "lr": 0.0015, "gradient_norm": 0.11739112436771393, "benchmark": false}
|
|
|
|
|
|
|
|
|
| 687 |
{"step": 13740, "tokens": 7203717120, "loss": 2.792901611328125, "tokens_per_second": 986272.0580112083, "lr": 0.0015, "gradient_norm": 0.11577098816633224, "benchmark": false}
|
| 688 |
{"step": 13760, "tokens": 7214202880, "loss": 2.7878217697143555, "tokens_per_second": 985767.097813454, "lr": 0.0015, "gradient_norm": 0.10202588886022568, "benchmark": false}
|
| 689 |
{"step": 13780, "tokens": 7224688640, "loss": 2.793878746032715, "tokens_per_second": 984036.116605316, "lr": 0.0015, "gradient_norm": 0.11739112436771393, "benchmark": false}
|
| 690 |
+
{"step": 13800, "tokens": 7235174400, "loss": 2.764632797241211, "tokens_per_second": 987683.8762506432, "lr": 0.0015, "gradient_norm": 0.11182590574026108, "benchmark": false}
|
| 691 |
+
{"step": 13820, "tokens": 7245660160, "loss": 2.7909011840820312, "tokens_per_second": 985738.4816994701, "lr": 0.0015, "gradient_norm": 0.12377017736434937, "benchmark": false}
|