382 lines
7.5 KiB
JSON
382 lines
7.5 KiB
JSON
|
|
{
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 0.21150219433526624,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 3000,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"epoch": 0.0,
|
||
|
|
"learning_rate": 4.9823745064861824e-05,
|
||
|
|
"loss": 1.064,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.01,
|
||
|
|
"learning_rate": 4.964749012972363e-05,
|
||
|
|
"loss": 0.9951,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.01,
|
||
|
|
"learning_rate": 4.9471235194585454e-05,
|
||
|
|
"loss": 1.0051,
|
||
|
|
"step": 150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.01,
|
||
|
|
"learning_rate": 4.929498025944726e-05,
|
||
|
|
"loss": 1.0086,
|
||
|
|
"step": 200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.02,
|
||
|
|
"learning_rate": 4.9118725324309084e-05,
|
||
|
|
"loss": 1.1256,
|
||
|
|
"step": 250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.02,
|
||
|
|
"learning_rate": 4.89424703891709e-05,
|
||
|
|
"loss": 1.0419,
|
||
|
|
"step": 300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.02,
|
||
|
|
"learning_rate": 4.8766215454032714e-05,
|
||
|
|
"loss": 1.0368,
|
||
|
|
"step": 350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.03,
|
||
|
|
"learning_rate": 4.8589960518894536e-05,
|
||
|
|
"loss": 0.9884,
|
||
|
|
"step": 400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.03,
|
||
|
|
"learning_rate": 4.8413705583756344e-05,
|
||
|
|
"loss": 1.01,
|
||
|
|
"step": 450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.04,
|
||
|
|
"learning_rate": 4.8237450648618166e-05,
|
||
|
|
"loss": 1.0734,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.04,
|
||
|
|
"learning_rate": 4.806119571347998e-05,
|
||
|
|
"loss": 1.0388,
|
||
|
|
"step": 550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.04,
|
||
|
|
"learning_rate": 4.7884940778341796e-05,
|
||
|
|
"loss": 1.0576,
|
||
|
|
"step": 600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.05,
|
||
|
|
"learning_rate": 4.770868584320361e-05,
|
||
|
|
"loss": 1.0449,
|
||
|
|
"step": 650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.05,
|
||
|
|
"learning_rate": 4.7532430908065426e-05,
|
||
|
|
"loss": 1.0809,
|
||
|
|
"step": 700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.05,
|
||
|
|
"learning_rate": 4.735617597292725e-05,
|
||
|
|
"loss": 1.0888,
|
||
|
|
"step": 750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.06,
|
||
|
|
"learning_rate": 4.717992103778906e-05,
|
||
|
|
"loss": 1.031,
|
||
|
|
"step": 800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.06,
|
||
|
|
"learning_rate": 4.700366610265088e-05,
|
||
|
|
"loss": 1.0546,
|
||
|
|
"step": 850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.06,
|
||
|
|
"learning_rate": 4.682741116751269e-05,
|
||
|
|
"loss": 1.093,
|
||
|
|
"step": 900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.07,
|
||
|
|
"learning_rate": 4.665468133107727e-05,
|
||
|
|
"loss": 1.0729,
|
||
|
|
"step": 950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.07,
|
||
|
|
"learning_rate": 4.647842639593909e-05,
|
||
|
|
"loss": 1.0771,
|
||
|
|
"step": 1000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.07,
|
||
|
|
"learning_rate": 4.6302171460800905e-05,
|
||
|
|
"loss": 1.1318,
|
||
|
|
"step": 1050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.08,
|
||
|
|
"learning_rate": 4.612591652566272e-05,
|
||
|
|
"loss": 1.0114,
|
||
|
|
"step": 1100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.08,
|
||
|
|
"learning_rate": 4.5949661590524535e-05,
|
||
|
|
"loss": 1.0272,
|
||
|
|
"step": 1150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.08,
|
||
|
|
"learning_rate": 4.577340665538635e-05,
|
||
|
|
"loss": 1.0503,
|
||
|
|
"step": 1200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.09,
|
||
|
|
"learning_rate": 4.559715172024817e-05,
|
||
|
|
"loss": 0.9816,
|
||
|
|
"step": 1250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.09,
|
||
|
|
"learning_rate": 4.542794698251551e-05,
|
||
|
|
"loss": 1.001,
|
||
|
|
"step": 1300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.1,
|
||
|
|
"learning_rate": 4.525169204737733e-05,
|
||
|
|
"loss": 1.1184,
|
||
|
|
"step": 1350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.1,
|
||
|
|
"learning_rate": 4.507543711223914e-05,
|
||
|
|
"loss": 1.0958,
|
||
|
|
"step": 1400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.1,
|
||
|
|
"learning_rate": 4.4899182177100965e-05,
|
||
|
|
"loss": 1.0912,
|
||
|
|
"step": 1450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.11,
|
||
|
|
"learning_rate": 4.472292724196277e-05,
|
||
|
|
"loss": 1.0226,
|
||
|
|
"step": 1500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.11,
|
||
|
|
"learning_rate": 4.4546672306824595e-05,
|
||
|
|
"loss": 1.0038,
|
||
|
|
"step": 1550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.11,
|
||
|
|
"learning_rate": 4.437041737168641e-05,
|
||
|
|
"loss": 0.9825,
|
||
|
|
"step": 1600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.12,
|
||
|
|
"learning_rate": 4.4194162436548225e-05,
|
||
|
|
"loss": 1.0476,
|
||
|
|
"step": 1650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.12,
|
||
|
|
"learning_rate": 4.401790750141005e-05,
|
||
|
|
"loss": 1.0642,
|
||
|
|
"step": 1700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.12,
|
||
|
|
"learning_rate": 4.3841652566271855e-05,
|
||
|
|
"loss": 1.0254,
|
||
|
|
"step": 1750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.13,
|
||
|
|
"learning_rate": 4.366539763113368e-05,
|
||
|
|
"loss": 1.0941,
|
||
|
|
"step": 1800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.13,
|
||
|
|
"learning_rate": 4.3489142695995485e-05,
|
||
|
|
"loss": 0.9739,
|
||
|
|
"step": 1850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.13,
|
||
|
|
"learning_rate": 4.331288776085731e-05,
|
||
|
|
"loss": 1.0468,
|
||
|
|
"step": 1900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.14,
|
||
|
|
"learning_rate": 4.313663282571912e-05,
|
||
|
|
"loss": 1.0706,
|
||
|
|
"step": 1950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.14,
|
||
|
|
"learning_rate": 4.296037789058094e-05,
|
||
|
|
"loss": 0.9796,
|
||
|
|
"step": 2000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.14,
|
||
|
|
"learning_rate": 4.278412295544276e-05,
|
||
|
|
"loss": 1.0202,
|
||
|
|
"step": 2050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.15,
|
||
|
|
"learning_rate": 4.260786802030457e-05,
|
||
|
|
"loss": 1.0263,
|
||
|
|
"step": 2100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.15,
|
||
|
|
"learning_rate": 4.243161308516639e-05,
|
||
|
|
"loss": 0.9823,
|
||
|
|
"step": 2150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.16,
|
||
|
|
"learning_rate": 4.2255358150028204e-05,
|
||
|
|
"loss": 1.0187,
|
||
|
|
"step": 2200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.16,
|
||
|
|
"learning_rate": 4.207910321489002e-05,
|
||
|
|
"loss": 1.0219,
|
||
|
|
"step": 2250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.16,
|
||
|
|
"learning_rate": 4.1902848279751834e-05,
|
||
|
|
"loss": 1.0641,
|
||
|
|
"step": 2300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.17,
|
||
|
|
"learning_rate": 4.172659334461365e-05,
|
||
|
|
"loss": 0.9979,
|
||
|
|
"step": 2350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.17,
|
||
|
|
"learning_rate": 4.155033840947547e-05,
|
||
|
|
"loss": 0.9762,
|
||
|
|
"step": 2400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.17,
|
||
|
|
"learning_rate": 4.1374083474337286e-05,
|
||
|
|
"loss": 0.983,
|
||
|
|
"step": 2450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.18,
|
||
|
|
"learning_rate": 4.11978285391991e-05,
|
||
|
|
"loss": 1.0849,
|
||
|
|
"step": 2500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.18,
|
||
|
|
"learning_rate": 4.1021573604060916e-05,
|
||
|
|
"loss": 1.0281,
|
||
|
|
"step": 2550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.18,
|
||
|
|
"learning_rate": 4.084531866892273e-05,
|
||
|
|
"loss": 1.0041,
|
||
|
|
"step": 2600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.19,
|
||
|
|
"learning_rate": 4.0669063733784546e-05,
|
||
|
|
"loss": 1.0055,
|
||
|
|
"step": 2650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.19,
|
||
|
|
"learning_rate": 4.049280879864636e-05,
|
||
|
|
"loss": 1.014,
|
||
|
|
"step": 2700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.19,
|
||
|
|
"learning_rate": 4.0316553863508176e-05,
|
||
|
|
"loss": 1.0347,
|
||
|
|
"step": 2750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.2,
|
||
|
|
"learning_rate": 4.014029892837e-05,
|
||
|
|
"loss": 0.9675,
|
||
|
|
"step": 2800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.2,
|
||
|
|
"learning_rate": 3.996404399323181e-05,
|
||
|
|
"loss": 1.0086,
|
||
|
|
"step": 2850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.2,
|
||
|
|
"learning_rate": 3.978778905809363e-05,
|
||
|
|
"loss": 0.9836,
|
||
|
|
"step": 2900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.21,
|
||
|
|
"learning_rate": 3.961153412295544e-05,
|
||
|
|
"loss": 1.0441,
|
||
|
|
"step": 2950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.21,
|
||
|
|
"learning_rate": 3.943527918781726e-05,
|
||
|
|
"loss": 1.0613,
|
||
|
|
"step": 3000
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 50,
|
||
|
|
"max_steps": 14184,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 1,
|
||
|
|
"save_steps": 1000,
|
||
|
|
"total_flos": 1.0058830184448e+17,
|
||
|
|
"train_batch_size": 1,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|