|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.2060395338355547, |
|
"eval_steps": 500, |
|
"global_step": 4000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 4.9996726480206315e-05, |
|
"loss": 0.7422, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 4.9986906778099784e-05, |
|
"loss": 0.6673, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 4.9970543465279565e-05, |
|
"loss": 0.6749, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 4.994764082699591e-05, |
|
"loss": 0.6481, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 4.991820486102801e-05, |
|
"loss": 0.6505, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 4.9882243276113245e-05, |
|
"loss": 0.6708, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 4.983976548992841e-05, |
|
"loss": 0.6596, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 4.9790782626623436e-05, |
|
"loss": 0.6657, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 4.97353075139081e-05, |
|
"loss": 0.659, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 4.9673354679692785e-05, |
|
"loss": 0.6519, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 4.960494034828381e-05, |
|
"loss": 0.638, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 4.9530082436134614e-05, |
|
"loss": 0.629, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 4.944880054715378e-05, |
|
"loss": 0.6464, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 4.9361115967571094e-05, |
|
"loss": 0.642, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 4.926705166036311e-05, |
|
"loss": 0.6431, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 4.916663225923953e-05, |
|
"loss": 0.6465, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 4.905988406219217e-05, |
|
"loss": 0.6439, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 4.8946835024607885e-05, |
|
"loss": 0.652, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 4.8827514751947656e-05, |
|
"loss": 0.6376, |
|
"step": 1900 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 4.8701954491993426e-05, |
|
"loss": 0.6357, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 4.85701871266649e-05, |
|
"loss": 0.6338, |
|
"step": 2100 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 4.8432247163408365e-05, |
|
"loss": 0.6591, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 4.8288170726159815e-05, |
|
"loss": 0.621, |
|
"step": 2300 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 4.8137995545884794e-05, |
|
"loss": 0.6337, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 4.798176095069731e-05, |
|
"loss": 0.637, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 4.781950785556054e-05, |
|
"loss": 0.6464, |
|
"step": 2600 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 4.7651278751571984e-05, |
|
"loss": 0.6539, |
|
"step": 2700 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 4.747711769483576e-05, |
|
"loss": 0.6233, |
|
"step": 2800 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 4.729707029492521e-05, |
|
"loss": 0.6476, |
|
"step": 2900 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 4.711118370293852e-05, |
|
"loss": 0.6302, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 4.691950659915074e-05, |
|
"loss": 0.632, |
|
"step": 3100 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 4.672208918026535e-05, |
|
"loss": 0.6281, |
|
"step": 3200 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 4.6518983146268604e-05, |
|
"loss": 0.6514, |
|
"step": 3300 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 4.63102416868903e-05, |
|
"loss": 0.6254, |
|
"step": 3400 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 4.609591946767437e-05, |
|
"loss": 0.6412, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 4.587607261566294e-05, |
|
"loss": 0.6647, |
|
"step": 3600 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 4.565075870469777e-05, |
|
"loss": 0.644, |
|
"step": 3700 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 4.542003674034263e-05, |
|
"loss": 0.6328, |
|
"step": 3800 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 4.5183967144430904e-05, |
|
"loss": 0.6454, |
|
"step": 3900 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 4.4942611739242166e-05, |
|
"loss": 0.6619, |
|
"step": 4000 |
|
} |
|
], |
|
"logging_steps": 100, |
|
"max_steps": 19413, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 2000, |
|
"total_flos": 9.069943662622802e+18, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|