Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -264,3 +264,5 @@
|
|
| 264 |
{"step": 5280, "tokens": 2768240640, "loss": 2.9453243255615233, "tokens_per_second": 970850.4842013303, "lr": 0.0015, "gradient_norm": 0.08411432057619095, "benchmark": false}
|
| 265 |
{"step": 5300, "tokens": 2778726400, "loss": 2.9040199279785157, "tokens_per_second": 971363.971749047, "lr": 0.0015, "gradient_norm": 0.08503418415784836, "benchmark": false}
|
| 266 |
{"step": 5320, "tokens": 2789212160, "loss": 2.9312274932861326, "tokens_per_second": 982310.5835244175, "lr": 0.0015, "gradient_norm": 0.0849388912320137, "benchmark": false}
|
|
|
|
|
|
|
|
|
| 264 |
{"step": 5280, "tokens": 2768240640, "loss": 2.9453243255615233, "tokens_per_second": 970850.4842013303, "lr": 0.0015, "gradient_norm": 0.08411432057619095, "benchmark": false}
|
| 265 |
{"step": 5300, "tokens": 2778726400, "loss": 2.9040199279785157, "tokens_per_second": 971363.971749047, "lr": 0.0015, "gradient_norm": 0.08503418415784836, "benchmark": false}
|
| 266 |
{"step": 5320, "tokens": 2789212160, "loss": 2.9312274932861326, "tokens_per_second": 982310.5835244175, "lr": 0.0015, "gradient_norm": 0.0849388912320137, "benchmark": false}
|
| 267 |
+
{"step": 5340, "tokens": 2799697920, "loss": 2.961272430419922, "tokens_per_second": 935002.5997755554, "lr": 0.0015, "gradient_norm": 0.08542951196432114, "benchmark": false}
|
| 268 |
+
{"step": 5360, "tokens": 2810183680, "loss": 2.929550361633301, "tokens_per_second": 965670.9911927925, "lr": 0.0015, "gradient_norm": 0.07830847799777985, "benchmark": false}
|