Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -156,3 +156,5 @@
|
|
| 156 |
{"step": 3120, "tokens": 1635778560, "loss": 3.065006637573242, "tokens_per_second": 978777.848876916, "lr": 0.0015, "gradient_norm": 0.1692066341638565, "benchmark": false}
|
| 157 |
{"step": 3140, "tokens": 1646264320, "loss": 3.057622528076172, "tokens_per_second": 974780.1289945149, "lr": 0.0015, "gradient_norm": 0.14104141294956207, "benchmark": false}
|
| 158 |
{"step": 3160, "tokens": 1656750080, "loss": 3.035442924499512, "tokens_per_second": 972833.7186925057, "lr": 0.0015, "gradient_norm": 0.1703290045261383, "benchmark": false}
|
|
|
|
|
|
|
|
|
| 156 |
{"step": 3120, "tokens": 1635778560, "loss": 3.065006637573242, "tokens_per_second": 978777.848876916, "lr": 0.0015, "gradient_norm": 0.1692066341638565, "benchmark": false}
|
| 157 |
{"step": 3140, "tokens": 1646264320, "loss": 3.057622528076172, "tokens_per_second": 974780.1289945149, "lr": 0.0015, "gradient_norm": 0.14104141294956207, "benchmark": false}
|
| 158 |
{"step": 3160, "tokens": 1656750080, "loss": 3.035442924499512, "tokens_per_second": 972833.7186925057, "lr": 0.0015, "gradient_norm": 0.1703290045261383, "benchmark": false}
|
| 159 |
+
{"step": 3180, "tokens": 1667235840, "loss": 3.041324996948242, "tokens_per_second": 940559.5481778823, "lr": 0.0015, "gradient_norm": 0.15705615282058716, "benchmark": false}
|
| 160 |
+
{"step": 3200, "tokens": 1677721600, "loss": 3.046498107910156, "tokens_per_second": 973834.5066184303, "lr": 0.0015, "gradient_norm": 0.15410611033439636, "benchmark": false}
|