anantoj's picture
commit files to HF hub
2d34e7b
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"global_step": 44157,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"learning_rate": 1.9774441198450984e-05,
"loss": 2.4542,
"step": 500
},
{
"epoch": 0.07,
"learning_rate": 1.9547976538261206e-05,
"loss": 2.4106,
"step": 1000
},
{
"epoch": 0.1,
"learning_rate": 1.9321511878071427e-05,
"loss": 2.4207,
"step": 1500
},
{
"epoch": 0.14,
"learning_rate": 1.909595307652241e-05,
"loss": 2.3664,
"step": 2000
},
{
"epoch": 0.17,
"learning_rate": 1.8869488416332635e-05,
"loss": 2.3553,
"step": 2500
},
{
"epoch": 0.2,
"learning_rate": 1.8643023756142857e-05,
"loss": 2.3541,
"step": 3000
},
{
"epoch": 0.24,
"learning_rate": 1.841655909595308e-05,
"loss": 2.3494,
"step": 3500
},
{
"epoch": 0.27,
"learning_rate": 1.81900944357633e-05,
"loss": 2.3592,
"step": 4000
},
{
"epoch": 0.31,
"learning_rate": 1.7963629775573522e-05,
"loss": 2.3452,
"step": 4500
},
{
"epoch": 0.34,
"learning_rate": 1.7737165115383744e-05,
"loss": 2.32,
"step": 5000
},
{
"epoch": 0.37,
"learning_rate": 1.7510700455193966e-05,
"loss": 2.2992,
"step": 5500
},
{
"epoch": 0.41,
"learning_rate": 1.728423579500419e-05,
"loss": 2.3109,
"step": 6000
},
{
"epoch": 0.44,
"learning_rate": 1.7057771134814413e-05,
"loss": 2.3008,
"step": 6500
},
{
"epoch": 0.48,
"learning_rate": 1.6831306474624635e-05,
"loss": 2.3091,
"step": 7000
},
{
"epoch": 0.51,
"learning_rate": 1.6604841814434857e-05,
"loss": 2.3252,
"step": 7500
},
{
"epoch": 0.54,
"learning_rate": 1.6378377154245082e-05,
"loss": 2.2909,
"step": 8000
},
{
"epoch": 0.58,
"learning_rate": 1.6151912494055304e-05,
"loss": 2.3015,
"step": 8500
},
{
"epoch": 0.61,
"learning_rate": 1.5925900763185907e-05,
"loss": 2.2997,
"step": 9000
},
{
"epoch": 0.65,
"learning_rate": 1.569943610299613e-05,
"loss": 2.283,
"step": 9500
},
{
"epoch": 0.68,
"learning_rate": 1.547297144280635e-05,
"loss": 2.2826,
"step": 10000
},
{
"epoch": 0.71,
"learning_rate": 1.5246506782616575e-05,
"loss": 2.2771,
"step": 10500
},
{
"epoch": 0.75,
"learning_rate": 1.5020042122426796e-05,
"loss": 2.2991,
"step": 11000
},
{
"epoch": 0.78,
"learning_rate": 1.4794030391557398e-05,
"loss": 2.3035,
"step": 11500
},
{
"epoch": 0.82,
"learning_rate": 1.456756573136762e-05,
"loss": 2.2715,
"step": 12000
},
{
"epoch": 0.85,
"learning_rate": 1.4341101071177844e-05,
"loss": 2.2736,
"step": 12500
},
{
"epoch": 0.88,
"learning_rate": 1.4114636410988067e-05,
"loss": 2.2883,
"step": 13000
},
{
"epoch": 0.92,
"learning_rate": 1.388862468011867e-05,
"loss": 2.2545,
"step": 13500
},
{
"epoch": 0.95,
"learning_rate": 1.3662160019928891e-05,
"loss": 2.2956,
"step": 14000
},
{
"epoch": 0.99,
"learning_rate": 1.3435695359739113e-05,
"loss": 2.2575,
"step": 14500
},
{
"epoch": 1.0,
"eval_loss": 2.1173367500305176,
"eval_runtime": 371.7904,
"eval_samples_per_second": 158.353,
"eval_steps_per_second": 9.898,
"step": 14719
},
{
"epoch": 1.02,
"learning_rate": 1.3209230699549337e-05,
"loss": 2.2485,
"step": 15000
},
{
"epoch": 1.05,
"learning_rate": 1.298276603935956e-05,
"loss": 2.2548,
"step": 15500
},
{
"epoch": 1.09,
"learning_rate": 1.2756301379169782e-05,
"loss": 2.242,
"step": 16000
},
{
"epoch": 1.12,
"learning_rate": 1.2529836718980004e-05,
"loss": 2.2797,
"step": 16500
},
{
"epoch": 1.15,
"learning_rate": 1.2303824988110606e-05,
"loss": 2.264,
"step": 17000
},
{
"epoch": 1.19,
"learning_rate": 1.207781325724121e-05,
"loss": 2.2747,
"step": 17500
},
{
"epoch": 1.22,
"learning_rate": 1.1851348597051431e-05,
"loss": 2.2776,
"step": 18000
},
{
"epoch": 1.26,
"learning_rate": 1.1624883936861653e-05,
"loss": 2.2696,
"step": 18500
},
{
"epoch": 1.29,
"learning_rate": 1.1398419276671877e-05,
"loss": 2.2436,
"step": 19000
},
{
"epoch": 1.32,
"learning_rate": 1.1171954616482099e-05,
"loss": 2.2563,
"step": 19500
},
{
"epoch": 1.36,
"learning_rate": 1.094548995629232e-05,
"loss": 2.266,
"step": 20000
},
{
"epoch": 1.39,
"learning_rate": 1.0719478225422924e-05,
"loss": 2.2696,
"step": 20500
},
{
"epoch": 1.43,
"learning_rate": 1.0493013565233146e-05,
"loss": 2.2423,
"step": 21000
},
{
"epoch": 1.46,
"learning_rate": 1.026654890504337e-05,
"loss": 2.2411,
"step": 21500
},
{
"epoch": 1.49,
"learning_rate": 1.0040084244853591e-05,
"loss": 2.2564,
"step": 22000
},
{
"epoch": 1.53,
"learning_rate": 9.813619584663813e-06,
"loss": 2.2632,
"step": 22500
},
{
"epoch": 1.56,
"learning_rate": 9.587154924474037e-06,
"loss": 2.2656,
"step": 23000
},
{
"epoch": 1.6,
"learning_rate": 9.360690264284259e-06,
"loss": 2.2667,
"step": 23500
},
{
"epoch": 1.63,
"learning_rate": 9.134225604094482e-06,
"loss": 2.2622,
"step": 24000
},
{
"epoch": 1.66,
"learning_rate": 8.907760943904704e-06,
"loss": 2.2398,
"step": 24500
},
{
"epoch": 1.7,
"learning_rate": 8.681296283714928e-06,
"loss": 2.2477,
"step": 25000
},
{
"epoch": 1.73,
"learning_rate": 8.45528455284553e-06,
"loss": 2.2248,
"step": 25500
},
{
"epoch": 1.77,
"learning_rate": 8.228819892655751e-06,
"loss": 2.2286,
"step": 26000
},
{
"epoch": 1.8,
"learning_rate": 8.002355232465975e-06,
"loss": 2.2268,
"step": 26500
},
{
"epoch": 1.83,
"learning_rate": 7.775890572276197e-06,
"loss": 2.239,
"step": 27000
},
{
"epoch": 1.87,
"learning_rate": 7.5498788414067996e-06,
"loss": 2.2238,
"step": 27500
},
{
"epoch": 1.9,
"learning_rate": 7.323414181217021e-06,
"loss": 2.2225,
"step": 28000
},
{
"epoch": 1.94,
"learning_rate": 7.096949521027244e-06,
"loss": 2.2272,
"step": 28500
},
{
"epoch": 1.97,
"learning_rate": 6.870484860837466e-06,
"loss": 2.2663,
"step": 29000
},
{
"epoch": 2.0,
"eval_loss": 2.092595100402832,
"eval_runtime": 372.6322,
"eval_samples_per_second": 157.995,
"eval_steps_per_second": 9.876,
"step": 29438
},
{
"epoch": 2.0,
"learning_rate": 6.644473129968069e-06,
"loss": 2.2417,
"step": 29500
},
{
"epoch": 2.04,
"learning_rate": 6.4180084697782915e-06,
"loss": 2.2355,
"step": 30000
},
{
"epoch": 2.07,
"learning_rate": 6.191543809588514e-06,
"loss": 2.2285,
"step": 30500
},
{
"epoch": 2.11,
"learning_rate": 5.965079149398737e-06,
"loss": 2.2392,
"step": 31000
},
{
"epoch": 2.14,
"learning_rate": 5.738614489208959e-06,
"loss": 2.23,
"step": 31500
},
{
"epoch": 2.17,
"learning_rate": 5.512149829019182e-06,
"loss": 2.2399,
"step": 32000
},
{
"epoch": 2.21,
"learning_rate": 5.286138098149784e-06,
"loss": 2.2363,
"step": 32500
},
{
"epoch": 2.24,
"learning_rate": 5.059673437960007e-06,
"loss": 2.2392,
"step": 33000
},
{
"epoch": 2.28,
"learning_rate": 4.833208777770229e-06,
"loss": 2.2302,
"step": 33500
},
{
"epoch": 2.31,
"learning_rate": 4.6067441175804515e-06,
"loss": 2.2257,
"step": 34000
},
{
"epoch": 2.34,
"learning_rate": 4.380732386711054e-06,
"loss": 2.2527,
"step": 34500
},
{
"epoch": 2.38,
"learning_rate": 4.154267726521277e-06,
"loss": 2.2505,
"step": 35000
},
{
"epoch": 2.41,
"learning_rate": 3.927803066331499e-06,
"loss": 2.2063,
"step": 35500
},
{
"epoch": 2.45,
"learning_rate": 3.701338406141722e-06,
"loss": 2.2317,
"step": 36000
},
{
"epoch": 2.48,
"learning_rate": 3.4748737459519442e-06,
"loss": 2.2432,
"step": 36500
},
{
"epoch": 2.51,
"learning_rate": 3.248409085762167e-06,
"loss": 2.2414,
"step": 37000
},
{
"epoch": 2.55,
"learning_rate": 3.0219444255723896e-06,
"loss": 2.2523,
"step": 37500
},
{
"epoch": 2.58,
"learning_rate": 2.795479765382612e-06,
"loss": 2.2264,
"step": 38000
},
{
"epoch": 2.62,
"learning_rate": 2.5690151051928346e-06,
"loss": 2.229,
"step": 38500
},
{
"epoch": 2.65,
"learning_rate": 2.343003374323437e-06,
"loss": 2.2231,
"step": 39000
},
{
"epoch": 2.68,
"learning_rate": 2.1165387141336597e-06,
"loss": 2.2375,
"step": 39500
},
{
"epoch": 2.72,
"learning_rate": 1.8900740539438822e-06,
"loss": 2.235,
"step": 40000
},
{
"epoch": 2.75,
"learning_rate": 1.6636093937541049e-06,
"loss": 2.2294,
"step": 40500
},
{
"epoch": 2.79,
"learning_rate": 1.4371447335643274e-06,
"loss": 2.2244,
"step": 41000
},
{
"epoch": 2.82,
"learning_rate": 1.2106800733745499e-06,
"loss": 2.2468,
"step": 41500
},
{
"epoch": 2.85,
"learning_rate": 9.842154131847726e-07,
"loss": 2.2278,
"step": 42000
},
{
"epoch": 2.89,
"learning_rate": 7.577507529949953e-07,
"loss": 2.222,
"step": 42500
},
{
"epoch": 2.92,
"learning_rate": 5.317390221255973e-07,
"loss": 2.2208,
"step": 43000
},
{
"epoch": 2.96,
"learning_rate": 3.057272912561995e-07,
"loss": 2.211,
"step": 43500
},
{
"epoch": 2.99,
"learning_rate": 7.926263106642208e-08,
"loss": 2.2092,
"step": 44000
},
{
"epoch": 3.0,
"eval_loss": 2.086573362350464,
"eval_runtime": 371.7326,
"eval_samples_per_second": 158.377,
"eval_steps_per_second": 9.9,
"step": 44157
}
],
"max_steps": 44157,
"num_train_epochs": 3,
"total_flos": 6.916093810478285e+16,
"trial_name": null,
"trial_params": null
}