16-clusters-balanced-4 / trainer_state.json
MHGanainy's picture
MHGanainy/16-clusters-balanced-4
714f0a4 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 4888,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.020458265139116204,
"grad_norm": 0.1146482527256012,
"learning_rate": 6.666666666666667e-06,
"loss": 2.4366,
"step": 100
},
{
"epoch": 0.04091653027823241,
"grad_norm": 0.19526588916778564,
"learning_rate": 1.3333333333333333e-05,
"loss": 2.4074,
"step": 200
},
{
"epoch": 0.06137479541734861,
"grad_norm": 0.2903444170951843,
"learning_rate": 2e-05,
"loss": 2.3776,
"step": 300
},
{
"epoch": 0.08183306055646482,
"grad_norm": 0.38961780071258545,
"learning_rate": 1.9976565632583726e-05,
"loss": 2.3633,
"step": 400
},
{
"epoch": 0.10229132569558101,
"grad_norm": 0.39514774084091187,
"learning_rate": 1.990637236425014e-05,
"loss": 2.3275,
"step": 500
},
{
"epoch": 0.12274959083469722,
"grad_norm": 0.4908258020877838,
"learning_rate": 1.9789749181967304e-05,
"loss": 2.2917,
"step": 600
},
{
"epoch": 0.1432078559738134,
"grad_norm": 0.45681577920913696,
"learning_rate": 1.9627242683835782e-05,
"loss": 2.2691,
"step": 700
},
{
"epoch": 0.16366612111292964,
"grad_norm": 0.514772891998291,
"learning_rate": 1.9419614517252536e-05,
"loss": 2.2543,
"step": 800
},
{
"epoch": 0.18412438625204583,
"grad_norm": 0.5909072160720825,
"learning_rate": 1.916783780916589e-05,
"loss": 2.2484,
"step": 900
},
{
"epoch": 0.20458265139116202,
"grad_norm": 0.5185887217521667,
"learning_rate": 1.8873092605152686e-05,
"loss": 2.2393,
"step": 1000
},
{
"epoch": 0.22504091653027825,
"grad_norm": 0.6383090615272522,
"learning_rate": 1.8536760338693926e-05,
"loss": 2.2473,
"step": 1100
},
{
"epoch": 0.24549918166939444,
"grad_norm": 0.5739400386810303,
"learning_rate": 1.816041735657083e-05,
"loss": 2.2004,
"step": 1200
},
{
"epoch": 0.26595744680851063,
"grad_norm": 0.6199432611465454,
"learning_rate": 1.7745827530726937e-05,
"loss": 2.2167,
"step": 1300
},
{
"epoch": 0.2864157119476268,
"grad_norm": 0.6655313372612,
"learning_rate": 1.7294933991223413e-05,
"loss": 2.1977,
"step": 1400
},
{
"epoch": 0.306873977086743,
"grad_norm": 0.6417890787124634,
"learning_rate": 1.6809850019034324e-05,
"loss": 2.1943,
"step": 1500
},
{
"epoch": 0.32733224222585927,
"grad_norm": 0.6394040584564209,
"learning_rate": 1.6292849141366084e-05,
"loss": 2.2409,
"step": 1600
},
{
"epoch": 0.34779050736497547,
"grad_norm": 0.6412447690963745,
"learning_rate": 1.574635447592305e-05,
"loss": 2.2241,
"step": 1700
},
{
"epoch": 0.36824877250409166,
"grad_norm": 0.7298178672790527,
"learning_rate": 1.5172927374061427e-05,
"loss": 2.1782,
"step": 1800
},
{
"epoch": 0.38870703764320785,
"grad_norm": 0.7089855074882507,
"learning_rate": 1.4575255416059513e-05,
"loss": 2.2225,
"step": 1900
},
{
"epoch": 0.40916530278232405,
"grad_norm": 0.6368885636329651,
"learning_rate": 1.3956139814768949e-05,
"loss": 2.1694,
"step": 2000
},
{
"epoch": 0.42962356792144024,
"grad_norm": 0.6372247338294983,
"learning_rate": 1.3318482286684498e-05,
"loss": 2.1647,
"step": 2100
},
{
"epoch": 0.4500818330605565,
"grad_norm": 0.8332213759422302,
"learning_rate": 1.2665271451965933e-05,
"loss": 2.1871,
"step": 2200
},
{
"epoch": 0.4705400981996727,
"grad_norm": 0.6431373357772827,
"learning_rate": 1.1999568827153472e-05,
"loss": 2.1635,
"step": 2300
},
{
"epoch": 0.4909983633387889,
"grad_norm": 0.7330695986747742,
"learning_rate": 1.1324494476227082e-05,
"loss": 2.1713,
"step": 2400
},
{
"epoch": 0.5114566284779051,
"grad_norm": 0.8543004393577576,
"learning_rate": 1.0643212387261345e-05,
"loss": 2.1591,
"step": 2500
},
{
"epoch": 0.5319148936170213,
"grad_norm": 0.819828987121582,
"learning_rate": 9.958915643213654e-06,
"loss": 2.1482,
"step": 2600
},
{
"epoch": 0.5523731587561375,
"grad_norm": 0.7319233417510986,
"learning_rate": 9.274811456348358e-06,
"loss": 2.1939,
"step": 2700
},
{
"epoch": 0.5728314238952537,
"grad_norm": 0.7505283355712891,
"learning_rate": 8.594106136438665e-06,
"loss": 2.1661,
"step": 2800
},
{
"epoch": 0.5932896890343698,
"grad_norm": 0.8119780421257019,
"learning_rate": 7.919990063198368e-06,
"loss": 2.1571,
"step": 2900
},
{
"epoch": 0.613747954173486,
"grad_norm": 0.8243106603622437,
"learning_rate": 7.255622733375776e-06,
"loss": 2.1802,
"step": 3000
},
{
"epoch": 0.6342062193126022,
"grad_norm": 0.7845710515975952,
"learning_rate": 6.604117952592168e-06,
"loss": 2.1798,
"step": 3100
},
{
"epoch": 0.6546644844517185,
"grad_norm": 0.7707119584083557,
"learning_rate": 5.968529241328822e-06,
"loss": 2.1381,
"step": 3200
},
{
"epoch": 0.6751227495908347,
"grad_norm": 0.7787159085273743,
"learning_rate": 5.351835523462808e-06,
"loss": 2.156,
"step": 3300
},
{
"epoch": 0.6955810147299509,
"grad_norm": 0.6944179534912109,
"learning_rate": 4.756927164427685e-06,
"loss": 2.163,
"step": 3400
},
{
"epoch": 0.7160392798690671,
"grad_norm": 0.8797001838684082,
"learning_rate": 4.18659242443638e-06,
"loss": 2.1375,
"step": 3500
},
{
"epoch": 0.7364975450081833,
"grad_norm": 0.7624711990356445,
"learning_rate": 3.6435043902583344e-06,
"loss": 2.1825,
"step": 3600
},
{
"epoch": 0.7569558101472995,
"grad_norm": 0.7933531999588013,
"learning_rate": 3.1302084468000206e-06,
"loss": 2.1442,
"step": 3700
},
{
"epoch": 0.7774140752864157,
"grad_norm": 0.9495463967323303,
"learning_rate": 2.6491103472078828e-06,
"loss": 2.1191,
"step": 3800
},
{
"epoch": 0.7978723404255319,
"grad_norm": 1.328906774520874,
"learning_rate": 2.202464937407752e-06,
"loss": 2.1698,
"step": 3900
},
{
"epoch": 0.8183306055646481,
"grad_norm": 0.9682719111442566,
"learning_rate": 1.7923655879272395e-06,
"loss": 2.1254,
"step": 4000
},
{
"epoch": 0.8387888707037643,
"grad_norm": 0.7559231519699097,
"learning_rate": 1.4207343825329167e-06,
"loss": 2.1739,
"step": 4100
},
{
"epoch": 0.8592471358428805,
"grad_norm": 0.8757209777832031,
"learning_rate": 1.089313109666904e-06,
"loss": 2.1108,
"step": 4200
},
{
"epoch": 0.8797054009819967,
"grad_norm": 0.911118745803833,
"learning_rate": 7.996550989047813e-07,
"loss": 2.1683,
"step": 4300
},
{
"epoch": 0.900163666121113,
"grad_norm": 0.9142606854438782,
"learning_rate": 5.531179406964016e-07,
"loss": 2.1318,
"step": 4400
},
{
"epoch": 0.9206219312602292,
"grad_norm": 0.9097318649291992,
"learning_rate": 3.5085712351121016e-07,
"loss": 2.1436,
"step": 4500
},
{
"epoch": 0.9410801963993454,
"grad_norm": 0.7701767086982727,
"learning_rate": 1.9382061820997112e-07,
"loss": 2.1591,
"step": 4600
},
{
"epoch": 0.9615384615384616,
"grad_norm": 0.7752079367637634,
"learning_rate": 8.274443502528817e-08,
"loss": 2.1662,
"step": 4700
},
{
"epoch": 0.9819967266775778,
"grad_norm": 0.7332737445831299,
"learning_rate": 1.814917397474636e-08,
"loss": 2.1488,
"step": 4800
},
{
"epoch": 1.0,
"step": 4888,
"total_flos": 8.882163499008e+16,
"train_loss": 2.2017843461856126,
"train_runtime": 1517.6787,
"train_samples_per_second": 6.441,
"train_steps_per_second": 3.221
}
],
"logging_steps": 100,
"max_steps": 4888,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 8.882163499008e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}