TimoImhof's picture
Upload local model to hub
e2c734f
raw
history blame
8.28 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"global_step": 32907,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.05,
"learning_rate": 1.9699759929498285e-05,
"loss": 2.1315,
"step": 500
},
{
"epoch": 0.09,
"learning_rate": 1.9396480991886225e-05,
"loss": 1.298,
"step": 1000
},
{
"epoch": 0.14,
"learning_rate": 1.9092594280852098e-05,
"loss": 1.1595,
"step": 1500
},
{
"epoch": 0.18,
"learning_rate": 1.8788707569817974e-05,
"loss": 1.16,
"step": 2000
},
{
"epoch": 0.23,
"learning_rate": 1.8484820858783847e-05,
"loss": 1.0615,
"step": 2500
},
{
"epoch": 0.27,
"learning_rate": 1.818093414774972e-05,
"loss": 1.0704,
"step": 3000
},
{
"epoch": 0.32,
"learning_rate": 1.7877047436715592e-05,
"loss": 1.029,
"step": 3500
},
{
"epoch": 0.36,
"learning_rate": 1.7573768499103536e-05,
"loss": 1.0325,
"step": 4000
},
{
"epoch": 0.41,
"learning_rate": 1.726988178806941e-05,
"loss": 1.0336,
"step": 4500
},
{
"epoch": 0.46,
"learning_rate": 1.696599507703528e-05,
"loss": 0.9839,
"step": 5000
},
{
"epoch": 0.5,
"learning_rate": 1.6662108366001154e-05,
"loss": 0.9754,
"step": 5500
},
{
"epoch": 0.55,
"learning_rate": 1.635822165496703e-05,
"loss": 1.0014,
"step": 6000
},
{
"epoch": 0.59,
"learning_rate": 1.6054334943932903e-05,
"loss": 0.9806,
"step": 6500
},
{
"epoch": 0.64,
"learning_rate": 1.5751056006320843e-05,
"loss": 0.9233,
"step": 7000
},
{
"epoch": 0.68,
"learning_rate": 1.544716929528672e-05,
"loss": 0.9523,
"step": 7500
},
{
"epoch": 0.73,
"learning_rate": 1.514389035767466e-05,
"loss": 0.9003,
"step": 8000
},
{
"epoch": 0.77,
"learning_rate": 1.4840003646640532e-05,
"loss": 0.9033,
"step": 8500
},
{
"epoch": 0.82,
"learning_rate": 1.4536116935606408e-05,
"loss": 0.9347,
"step": 9000
},
{
"epoch": 0.87,
"learning_rate": 1.4232230224572281e-05,
"loss": 0.9087,
"step": 9500
},
{
"epoch": 0.91,
"learning_rate": 1.3928343513538154e-05,
"loss": 0.8889,
"step": 10000
},
{
"epoch": 0.96,
"learning_rate": 1.3624456802504026e-05,
"loss": 0.8578,
"step": 10500
},
{
"epoch": 1.0,
"learning_rate": 1.3320570091469903e-05,
"loss": 0.8989,
"step": 11000
},
{
"epoch": 1.05,
"learning_rate": 1.3016683380435775e-05,
"loss": 0.7109,
"step": 11500
},
{
"epoch": 1.09,
"learning_rate": 1.2712796669401648e-05,
"loss": 0.6944,
"step": 12000
},
{
"epoch": 1.14,
"learning_rate": 1.240890995836752e-05,
"loss": 0.6717,
"step": 12500
},
{
"epoch": 1.19,
"learning_rate": 1.2105023247333397e-05,
"loss": 0.6784,
"step": 13000
},
{
"epoch": 1.23,
"learning_rate": 1.180113653629927e-05,
"loss": 0.7049,
"step": 13500
},
{
"epoch": 1.28,
"learning_rate": 1.1497249825265142e-05,
"loss": 0.7093,
"step": 14000
},
{
"epoch": 1.32,
"learning_rate": 1.1193363114231015e-05,
"loss": 0.71,
"step": 14500
},
{
"epoch": 1.37,
"learning_rate": 1.0889476403196887e-05,
"loss": 0.7205,
"step": 15000
},
{
"epoch": 1.41,
"learning_rate": 1.0586197465584831e-05,
"loss": 0.7111,
"step": 15500
},
{
"epoch": 1.46,
"learning_rate": 1.0282310754550704e-05,
"loss": 0.6918,
"step": 16000
},
{
"epoch": 1.5,
"learning_rate": 9.978424043516578e-06,
"loss": 0.6958,
"step": 16500
},
{
"epoch": 1.55,
"learning_rate": 9.674537332482451e-06,
"loss": 0.6566,
"step": 17000
},
{
"epoch": 1.6,
"learning_rate": 9.370650621448325e-06,
"loss": 0.693,
"step": 17500
},
{
"epoch": 1.64,
"learning_rate": 9.066763910414198e-06,
"loss": 0.6783,
"step": 18000
},
{
"epoch": 1.69,
"learning_rate": 8.76348497280214e-06,
"loss": 0.6855,
"step": 18500
},
{
"epoch": 1.73,
"learning_rate": 8.459598261768015e-06,
"loss": 0.6932,
"step": 19000
},
{
"epoch": 1.78,
"learning_rate": 8.155711550733887e-06,
"loss": 0.6796,
"step": 19500
},
{
"epoch": 1.82,
"learning_rate": 7.85182483969976e-06,
"loss": 0.6847,
"step": 20000
},
{
"epoch": 1.87,
"learning_rate": 7.547938128665634e-06,
"loss": 0.7063,
"step": 20500
},
{
"epoch": 1.91,
"learning_rate": 7.244051417631508e-06,
"loss": 0.6352,
"step": 21000
},
{
"epoch": 1.96,
"learning_rate": 6.940164706597381e-06,
"loss": 0.6636,
"step": 21500
},
{
"epoch": 2.01,
"learning_rate": 6.636277995563255e-06,
"loss": 0.6795,
"step": 22000
},
{
"epoch": 2.05,
"learning_rate": 6.332391284529128e-06,
"loss": 0.5144,
"step": 22500
},
{
"epoch": 2.1,
"learning_rate": 6.028504573495002e-06,
"loss": 0.5223,
"step": 23000
},
{
"epoch": 2.14,
"learning_rate": 5.724617862460875e-06,
"loss": 0.5364,
"step": 23500
},
{
"epoch": 2.19,
"learning_rate": 5.420731151426749e-06,
"loss": 0.5147,
"step": 24000
},
{
"epoch": 2.23,
"learning_rate": 5.116844440392622e-06,
"loss": 0.5244,
"step": 24500
},
{
"epoch": 2.28,
"learning_rate": 4.813565502780564e-06,
"loss": 0.55,
"step": 25000
},
{
"epoch": 2.32,
"learning_rate": 4.5102865651685055e-06,
"loss": 0.5239,
"step": 25500
},
{
"epoch": 2.37,
"learning_rate": 4.207007627556448e-06,
"loss": 0.4953,
"step": 26000
},
{
"epoch": 2.42,
"learning_rate": 3.903120916522321e-06,
"loss": 0.4877,
"step": 26500
},
{
"epoch": 2.46,
"learning_rate": 3.599234205488194e-06,
"loss": 0.5073,
"step": 27000
},
{
"epoch": 2.51,
"learning_rate": 3.2953474944540674e-06,
"loss": 0.5149,
"step": 27500
},
{
"epoch": 2.55,
"learning_rate": 2.992068556842009e-06,
"loss": 0.4993,
"step": 28000
},
{
"epoch": 2.6,
"learning_rate": 2.6881818458078827e-06,
"loss": 0.5198,
"step": 28500
},
{
"epoch": 2.64,
"learning_rate": 2.3842951347737562e-06,
"loss": 0.4992,
"step": 29000
},
{
"epoch": 2.69,
"learning_rate": 2.0804084237396298e-06,
"loss": 0.5126,
"step": 29500
},
{
"epoch": 2.73,
"learning_rate": 1.7765217127055035e-06,
"loss": 0.5029,
"step": 30000
},
{
"epoch": 2.78,
"learning_rate": 1.472635001671377e-06,
"loss": 0.514,
"step": 30500
},
{
"epoch": 2.83,
"learning_rate": 1.1687482906372504e-06,
"loss": 0.5053,
"step": 31000
},
{
"epoch": 2.87,
"learning_rate": 8.64861579603124e-07,
"loss": 0.4981,
"step": 31500
},
{
"epoch": 2.92,
"learning_rate": 5.609748685689976e-07,
"loss": 0.5156,
"step": 32000
},
{
"epoch": 2.96,
"learning_rate": 2.576959309569393e-07,
"loss": 0.5304,
"step": 32500
}
],
"max_steps": 32907,
"num_train_epochs": 3,
"total_flos": 6.878245175940096e+16,
"trial_name": null,
"trial_params": null
}