Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -693,3 +693,5 @@
|
|
| 693 |
{"step": 13860, "tokens": 7266631680, "loss": 2.7674882888793944, "tokens_per_second": 946431.3417039429, "lr": 0.0015, "gradient_norm": 0.125955730676651, "benchmark": false}
|
| 694 |
{"step": 13880, "tokens": 7277117440, "loss": 2.7438486099243162, "tokens_per_second": 971311.9990196545, "lr": 0.0015, "gradient_norm": 0.12266208976507187, "benchmark": false}
|
| 695 |
{"step": 13900, "tokens": 7287603200, "loss": 2.7603336334228517, "tokens_per_second": 963924.6459587925, "lr": 0.0015, "gradient_norm": 0.11117645353078842, "benchmark": false}
|
|
|
|
|
|
|
|
|
| 693 |
{"step": 13860, "tokens": 7266631680, "loss": 2.7674882888793944, "tokens_per_second": 946431.3417039429, "lr": 0.0015, "gradient_norm": 0.125955730676651, "benchmark": false}
|
| 694 |
{"step": 13880, "tokens": 7277117440, "loss": 2.7438486099243162, "tokens_per_second": 971311.9990196545, "lr": 0.0015, "gradient_norm": 0.12266208976507187, "benchmark": false}
|
| 695 |
{"step": 13900, "tokens": 7287603200, "loss": 2.7603336334228517, "tokens_per_second": 963924.6459587925, "lr": 0.0015, "gradient_norm": 0.11117645353078842, "benchmark": false}
|
| 696 |
+
{"step": 13920, "tokens": 7298088960, "loss": 2.7700157165527344, "tokens_per_second": 969788.082572308, "lr": 0.0015, "gradient_norm": 0.11690377444028854, "benchmark": false}
|
| 697 |
+
{"step": 13940, "tokens": 7308574720, "loss": 2.768319320678711, "tokens_per_second": 964042.0161144747, "lr": 0.0015, "gradient_norm": 0.1116306260228157, "benchmark": false}
|