File size: 1,471 Bytes
1a4bf79 90b4e54 1a4bf79 90b4e54 1a4bf79 abf420e 1a4bf79 abf420e 1a4bf79 abf420e 1a4bf79 c7a192b 353bd36 2b9c39e 90b4e54 1a4bf79 abf420e 1a4bf79 90b4e54 1a4bf79 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.0028,
"eval_steps": 500,
"global_step": 140,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"grad_norm": 79.12922668457031,
"learning_rate": 1e-06,
"loss": 4.6771,
"step": 20
},
{
"epoch": 0.0,
"grad_norm": 239.7991943359375,
"learning_rate": 2e-06,
"loss": 4.5023,
"step": 40
},
{
"epoch": 0.0,
"grad_norm": 77.5164794921875,
"learning_rate": 3e-06,
"loss": 4.8171,
"step": 60
},
{
"epoch": 0.0,
"grad_norm": 207.87796020507812,
"learning_rate": 4e-06,
"loss": 4.6765,
"step": 80
},
{
"epoch": 0.0,
"grad_norm": 147.12461853027344,
"learning_rate": 4.9999999999999996e-06,
"loss": 4.7237,
"step": 100
},
{
"epoch": 0.0,
"grad_norm": 115.61023712158203,
"learning_rate": 6e-06,
"loss": 4.4426,
"step": 120
},
{
"epoch": 0.0,
"grad_norm": 43.68627166748047,
"learning_rate": 7e-06,
"loss": 5.0142,
"step": 140
}
],
"logging_steps": 20,
"max_steps": 20000,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 20,
"total_flos": 47457760075776.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|