Update tokenizer, configuration and training reports
Browse files
reports/run/metrics.jsonl
CHANGED
|
@@ -135,3 +135,5 @@
|
|
| 135 |
{"step": 2700, "tokens": 1415577600, "loss": 3.105073928833008, "tokens_per_second": 979995.0214306681, "lr": 0.0015, "gradient_norm": 0.24327975511550903, "benchmark": false}
|
| 136 |
{"step": 2720, "tokens": 1426063360, "loss": 3.1123846054077147, "tokens_per_second": 994175.0496723149, "lr": 0.0015, "gradient_norm": 0.2370196431875229, "benchmark": false}
|
| 137 |
{"step": 2740, "tokens": 1436549120, "loss": 3.092816162109375, "tokens_per_second": 838924.7631111884, "lr": 0.0015, "gradient_norm": 0.2178315669298172, "benchmark": false}
|
|
|
|
|
|
|
|
|
| 135 |
{"step": 2700, "tokens": 1415577600, "loss": 3.105073928833008, "tokens_per_second": 979995.0214306681, "lr": 0.0015, "gradient_norm": 0.24327975511550903, "benchmark": false}
|
| 136 |
{"step": 2720, "tokens": 1426063360, "loss": 3.1123846054077147, "tokens_per_second": 994175.0496723149, "lr": 0.0015, "gradient_norm": 0.2370196431875229, "benchmark": false}
|
| 137 |
{"step": 2740, "tokens": 1436549120, "loss": 3.092816162109375, "tokens_per_second": 838924.7631111884, "lr": 0.0015, "gradient_norm": 0.2178315669298172, "benchmark": false}
|
| 138 |
+
{"step": 2760, "tokens": 1447034880, "loss": 3.105674934387207, "tokens_per_second": 967719.704454244, "lr": 0.0015, "gradient_norm": 0.19153432548046112, "benchmark": false}
|
| 139 |
+
{"step": 2780, "tokens": 1457520640, "loss": 3.0968559265136717, "tokens_per_second": 970148.9990081738, "lr": 0.0015, "gradient_norm": 0.2842233180999756, "benchmark": false}
|