| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.9907120743034055, |
| "eval_steps": 100, |
| "global_step": 242, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0412796697626419, |
| "grad_norm": 0.5423572411981227, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 1.9532, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0825593395252838, |
| "grad_norm": 0.3952174476286853, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 1.8852, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.1238390092879257, |
| "grad_norm": 0.39153877344371674, |
| "learning_rate": 1.2e-05, |
| "loss": 1.7935, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.1651186790505676, |
| "grad_norm": 0.27826347316491185, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 1.5697, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.20639834881320948, |
| "grad_norm": 0.27509780034807013, |
| "learning_rate": 2e-05, |
| "loss": 1.3934, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.2476780185758514, |
| "grad_norm": 0.31439323035169303, |
| "learning_rate": 1.997381210172319e-05, |
| "loss": 1.284, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.2889576883384933, |
| "grad_norm": 0.1926553270852725, |
| "learning_rate": 1.989538556809598e-05, |
| "loss": 1.1481, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.3302373581011352, |
| "grad_norm": 0.16412584493261162, |
| "learning_rate": 1.9765131164335345e-05, |
| "loss": 1.1067, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.3715170278637771, |
| "grad_norm": 0.14201820701986695, |
| "learning_rate": 1.958373110825644e-05, |
| "loss": 1.0804, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.41279669762641896, |
| "grad_norm": 0.13251231709921993, |
| "learning_rate": 1.9352135497102464e-05, |
| "loss": 1.074, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.4540763673890609, |
| "grad_norm": 0.15466409379526366, |
| "learning_rate": 1.907155733133467e-05, |
| "loss": 1.0715, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.4953560371517028, |
| "grad_norm": 0.14973122929035207, |
| "learning_rate": 1.8743466161445823e-05, |
| "loss": 1.0653, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.5366357069143447, |
| "grad_norm": 0.14709203237203478, |
| "learning_rate": 1.8369580391072435e-05, |
| "loss": 1.0496, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.5779153766769866, |
| "grad_norm": 0.12510498686662688, |
| "learning_rate": 1.7951858276718845e-05, |
| "loss": 1.0392, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.6191950464396285, |
| "grad_norm": 0.14382258751082552, |
| "learning_rate": 1.7492487671232784e-05, |
| "loss": 1.0278, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.6604747162022704, |
| "grad_norm": 0.13327205460615688, |
| "learning_rate": 1.6993874564751824e-05, |
| "loss": 1.0243, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.7017543859649122, |
| "grad_norm": 0.12863671293917475, |
| "learning_rate": 1.6458630483138354e-05, |
| "loss": 1.0325, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.7430340557275542, |
| "grad_norm": 0.1391969379512732, |
| "learning_rate": 1.58895588099049e-05, |
| "loss": 1.0146, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.7843137254901961, |
| "grad_norm": 0.12799160286774816, |
| "learning_rate": 1.5289640103269626e-05, |
| "loss": 1.0312, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.8255933952528379, |
| "grad_norm": 0.1255522837974007, |
| "learning_rate": 1.4662016485245274e-05, |
| "loss": 1.0285, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.8255933952528379, |
| "eval_loss": 1.045740008354187, |
| "eval_runtime": 1.5063, |
| "eval_samples_per_second": 15.933, |
| "eval_steps_per_second": 1.992, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.8668730650154799, |
| "grad_norm": 0.13220466757417867, |
| "learning_rate": 1.400997518452484e-05, |
| "loss": 1.0197, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.9081527347781218, |
| "grad_norm": 0.12455077448359639, |
| "learning_rate": 1.3336931319359428e-05, |
| "loss": 0.9905, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.9494324045407637, |
| "grad_norm": 0.13056751429758742, |
| "learning_rate": 1.2646410010604397e-05, |
| "loss": 1.0204, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.9907120743034056, |
| "grad_norm": 0.12235542685054333, |
| "learning_rate": 1.1942027918618076e-05, |
| "loss": 1.0135, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.0247678018575852, |
| "grad_norm": 0.15537117537160547, |
| "learning_rate": 1.1227474300715056e-05, |
| "loss": 0.9998, |
| "step": 125 |
| }, |
| { |
| "epoch": 1.066047471620227, |
| "grad_norm": 0.135345591232645, |
| "learning_rate": 1.0506491688387128e-05, |
| "loss": 0.9884, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.107327141382869, |
| "grad_norm": 0.12431806316772155, |
| "learning_rate": 9.782856285496494e-06, |
| "loss": 0.9699, |
| "step": 135 |
| }, |
| { |
| "epoch": 1.1486068111455108, |
| "grad_norm": 0.13879009526242994, |
| "learning_rate": 9.060358190107235e-06, |
| "loss": 0.9526, |
| "step": 140 |
| }, |
| { |
| "epoch": 1.1898864809081529, |
| "grad_norm": 0.12717946885931922, |
| "learning_rate": 8.342781543544799e-06, |
| "loss": 0.9655, |
| "step": 145 |
| }, |
| { |
| "epoch": 1.2311661506707947, |
| "grad_norm": 0.12892351453778872, |
| "learning_rate": 7.633884710654383e-06, |
| "loss": 0.9771, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.2724458204334366, |
| "grad_norm": 0.12611153356544771, |
| "learning_rate": 6.937380595065686e-06, |
| "loss": 0.9431, |
| "step": 155 |
| }, |
| { |
| "epoch": 1.3137254901960784, |
| "grad_norm": 0.12541315034043007, |
| "learning_rate": 6.2569171925643915e-06, |
| "loss": 0.9388, |
| "step": 160 |
| }, |
| { |
| "epoch": 1.3550051599587203, |
| "grad_norm": 0.11909992847099143, |
| "learning_rate": 5.5960584844236565e-06, |
| "loss": 0.9503, |
| "step": 165 |
| }, |
| { |
| "epoch": 1.3962848297213624, |
| "grad_norm": 0.12075323476100178, |
| "learning_rate": 4.958265770768315e-06, |
| "loss": 0.9574, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.437564499484004, |
| "grad_norm": 0.12177362606151067, |
| "learning_rate": 4.34687954173974e-06, |
| "loss": 0.956, |
| "step": 175 |
| }, |
| { |
| "epoch": 1.478844169246646, |
| "grad_norm": 0.1230932967148576, |
| "learning_rate": 3.7651019814126656e-06, |
| "loss": 0.9343, |
| "step": 180 |
| }, |
| { |
| "epoch": 1.520123839009288, |
| "grad_norm": 0.11921943724872856, |
| "learning_rate": 3.215980196101002e-06, |
| "loss": 0.9573, |
| "step": 185 |
| }, |
| { |
| "epoch": 1.5614035087719298, |
| "grad_norm": 0.11176701701622194, |
| "learning_rate": 2.7023902548958193e-06, |
| "loss": 0.9492, |
| "step": 190 |
| }, |
| { |
| "epoch": 1.6026831785345719, |
| "grad_norm": 0.11546689796712385, |
| "learning_rate": 2.2270221260243675e-06, |
| "loss": 0.9309, |
| "step": 195 |
| }, |
| { |
| "epoch": 1.6439628482972135, |
| "grad_norm": 0.11779816575572202, |
| "learning_rate": 1.7923655879272395e-06, |
| "loss": 0.9383, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.6439628482972135, |
| "eval_loss": 1.0228246450424194, |
| "eval_runtime": 1.4581, |
| "eval_samples_per_second": 16.46, |
| "eval_steps_per_second": 2.057, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.6852425180598556, |
| "grad_norm": 0.11119335035958992, |
| "learning_rate": 1.4006971888454324e-06, |
| "loss": 0.9379, |
| "step": 205 |
| }, |
| { |
| "epoch": 1.7265221878224974, |
| "grad_norm": 0.11484496155186044, |
| "learning_rate": 1.0540683232176307e-06, |
| "loss": 0.9537, |
| "step": 210 |
| }, |
| { |
| "epoch": 1.7678018575851393, |
| "grad_norm": 0.11415468044875361, |
| "learning_rate": 7.542944873384106e-07, |
| "loss": 0.9527, |
| "step": 215 |
| }, |
| { |
| "epoch": 1.8090815273477814, |
| "grad_norm": 0.11205413468590845, |
| "learning_rate": 5.029457705517793e-07, |
| "loss": 0.938, |
| "step": 220 |
| }, |
| { |
| "epoch": 1.850361197110423, |
| "grad_norm": 0.1135948106196872, |
| "learning_rate": 3.0133863178318237e-07, |
| "loss": 0.9664, |
| "step": 225 |
| }, |
| { |
| "epoch": 1.891640866873065, |
| "grad_norm": 0.11128328680253924, |
| "learning_rate": 1.5052900448100815e-07, |
| "loss": 0.9418, |
| "step": 230 |
| }, |
| { |
| "epoch": 1.932920536635707, |
| "grad_norm": 0.11332409865653205, |
| "learning_rate": 5.1306766081048456e-08, |
| "loss": 0.9604, |
| "step": 235 |
| }, |
| { |
| "epoch": 1.9742002063983488, |
| "grad_norm": 0.11189144523888174, |
| "learning_rate": 4.1916009605058594e-09, |
| "loss": 0.9453, |
| "step": 240 |
| }, |
| { |
| "epoch": 1.9907120743034055, |
| "step": 242, |
| "total_flos": 5.939028700430336e+16, |
| "train_loss": 1.0744690299034119, |
| "train_runtime": 1891.5529, |
| "train_samples_per_second": 4.098, |
| "train_steps_per_second": 0.128 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 242, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": false, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 5.939028700430336e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
