| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 400, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.025, |
| "grad_norm": 29.75, |
| "learning_rate": 1.0912572038095237e-05, |
| "loss": 2.6624, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 14.1875, |
| "learning_rate": 2.455328708571428e-05, |
| "loss": 2.0012, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.075, |
| "grad_norm": 8.875, |
| "learning_rate": 3.819400213333333e-05, |
| "loss": 1.4616, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 7.53125, |
| "learning_rate": 5.1834717180952374e-05, |
| "loss": 1.3871, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.125, |
| "grad_norm": 6.59375, |
| "learning_rate": 6.547543222857142e-05, |
| "loss": 1.343, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 6.71875, |
| "learning_rate": 7.911614727619048e-05, |
| "loss": 1.3784, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.175, |
| "grad_norm": 6.6875, |
| "learning_rate": 9.275686232380952e-05, |
| "loss": 1.2931, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 6.53125, |
| "learning_rate": 9.548427313356479e-05, |
| "loss": 1.3394, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.225, |
| "grad_norm": 6.40625, |
| "learning_rate": 9.548129862332663e-05, |
| "loss": 1.3522, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 5.71875, |
| "learning_rate": 9.547603623006331e-05, |
| "loss": 1.3282, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.275, |
| "grad_norm": 5.75, |
| "learning_rate": 9.546848629005064e-05, |
| "loss": 1.3435, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 5.5625, |
| "learning_rate": 9.545864928574254e-05, |
| "loss": 1.3321, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.325, |
| "grad_norm": 5.5, |
| "learning_rate": 9.544652584574018e-05, |
| "loss": 1.3244, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 5.3125, |
| "learning_rate": 9.543211674475186e-05, |
| "loss": 1.2706, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.375, |
| "grad_norm": 5.125, |
| "learning_rate": 9.541542290354346e-05, |
| "loss": 1.3528, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 5.375, |
| "learning_rate": 9.53964453888796e-05, |
| "loss": 1.3099, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.425, |
| "grad_norm": 5.15625, |
| "learning_rate": 9.537518541345552e-05, |
| "loss": 1.3104, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 5.0625, |
| "learning_rate": 9.535164433581954e-05, |
| "loss": 1.3055, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.475, |
| "grad_norm": 5.5, |
| "learning_rate": 9.532582366028624e-05, |
| "loss": 1.3137, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 5.15625, |
| "learning_rate": 9.529772503684043e-05, |
| "loss": 1.2908, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.525, |
| "grad_norm": 4.6875, |
| "learning_rate": 9.52673502610315e-05, |
| "loss": 1.3012, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 4.75, |
| "learning_rate": 9.523470127385899e-05, |
| "loss": 1.3026, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.575, |
| "grad_norm": 4.84375, |
| "learning_rate": 9.519978016164825e-05, |
| "loss": 1.2749, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 4.6875, |
| "learning_rate": 9.516258915591732e-05, |
| "loss": 1.2866, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.625, |
| "grad_norm": 5.09375, |
| "learning_rate": 9.512313063323425e-05, |
| "loss": 1.2496, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 4.78125, |
| "learning_rate": 9.508140711506526e-05, |
| "loss": 1.2829, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.675, |
| "grad_norm": 4.96875, |
| "learning_rate": 9.50374212676136e-05, |
| "loss": 1.2332, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 4.84375, |
| "learning_rate": 9.499117590164916e-05, |
| "loss": 1.2069, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.725, |
| "grad_norm": 5.1875, |
| "learning_rate": 9.494267397232891e-05, |
| "loss": 1.2704, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 4.96875, |
| "learning_rate": 9.489191857900805e-05, |
| "loss": 1.1989, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.775, |
| "grad_norm": 5.25, |
| "learning_rate": 9.483891296504183e-05, |
| "loss": 1.2173, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 4.71875, |
| "learning_rate": 9.478366051757852e-05, |
| "loss": 1.2372, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.825, |
| "grad_norm": 4.5625, |
| "learning_rate": 9.472616476734276e-05, |
| "loss": 1.2163, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.85, |
| "grad_norm": 4.375, |
| "learning_rate": 9.466642938841009e-05, |
| "loss": 1.1987, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.875, |
| "grad_norm": 4.5625, |
| "learning_rate": 9.460445819797204e-05, |
| "loss": 1.1987, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 4.625, |
| "learning_rate": 9.454025515609231e-05, |
| "loss": 1.2309, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.925, |
| "grad_norm": 4.8125, |
| "learning_rate": 9.447382436545368e-05, |
| "loss": 1.1624, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.95, |
| "grad_norm": 4.40625, |
| "learning_rate": 9.44051700710958e-05, |
| "loss": 1.2099, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.975, |
| "grad_norm": 4.3125, |
| "learning_rate": 9.4334296660144e-05, |
| "loss": 1.1686, |
| "step": 195 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 4.625, |
| "learning_rate": 9.426120866152886e-05, |
| "loss": 1.1735, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.098361849784851, |
| "eval_runtime": 0.3671, |
| "eval_samples_per_second": 8.173, |
| "eval_steps_per_second": 8.173, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.025, |
| "grad_norm": 4.0, |
| "learning_rate": 9.41859107456969e-05, |
| "loss": 0.6053, |
| "step": 205 |
| }, |
| { |
| "epoch": 1.05, |
| "grad_norm": 5.03125, |
| "learning_rate": 9.410840772431208e-05, |
| "loss": 0.5627, |
| "step": 210 |
| }, |
| { |
| "epoch": 1.075, |
| "grad_norm": 3.75, |
| "learning_rate": 9.402870454994828e-05, |
| "loss": 0.5576, |
| "step": 215 |
| }, |
| { |
| "epoch": 1.1, |
| "grad_norm": 4.25, |
| "learning_rate": 9.394680631577291e-05, |
| "loss": 0.5748, |
| "step": 220 |
| }, |
| { |
| "epoch": 1.125, |
| "grad_norm": 4.15625, |
| "learning_rate": 9.38627182552214e-05, |
| "loss": 0.5923, |
| "step": 225 |
| }, |
| { |
| "epoch": 1.15, |
| "grad_norm": 4.15625, |
| "learning_rate": 9.377644574166277e-05, |
| "loss": 0.5723, |
| "step": 230 |
| }, |
| { |
| "epoch": 1.175, |
| "grad_norm": 4.03125, |
| "learning_rate": 9.36879942880563e-05, |
| "loss": 0.5853, |
| "step": 235 |
| }, |
| { |
| "epoch": 1.2, |
| "grad_norm": 4.09375, |
| "learning_rate": 9.359736954659916e-05, |
| "loss": 0.5949, |
| "step": 240 |
| }, |
| { |
| "epoch": 1.225, |
| "grad_norm": 4.1875, |
| "learning_rate": 9.350457730836537e-05, |
| "loss": 0.6248, |
| "step": 245 |
| }, |
| { |
| "epoch": 1.25, |
| "grad_norm": 4.0625, |
| "learning_rate": 9.340962350293559e-05, |
| "loss": 0.5959, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.275, |
| "grad_norm": 3.96875, |
| "learning_rate": 9.331251419801827e-05, |
| "loss": 0.6034, |
| "step": 255 |
| }, |
| { |
| "epoch": 1.3, |
| "grad_norm": 3.9375, |
| "learning_rate": 9.321325559906198e-05, |
| "loss": 0.5904, |
| "step": 260 |
| }, |
| { |
| "epoch": 1.325, |
| "grad_norm": 3.875, |
| "learning_rate": 9.311185404885872e-05, |
| "loss": 0.5682, |
| "step": 265 |
| }, |
| { |
| "epoch": 1.35, |
| "grad_norm": 4.4375, |
| "learning_rate": 9.300831602713876e-05, |
| "loss": 0.597, |
| "step": 270 |
| }, |
| { |
| "epoch": 1.375, |
| "grad_norm": 3.953125, |
| "learning_rate": 9.290264815015647e-05, |
| "loss": 0.6471, |
| "step": 275 |
| }, |
| { |
| "epoch": 1.4, |
| "grad_norm": 3.84375, |
| "learning_rate": 9.279485717026758e-05, |
| "loss": 0.5998, |
| "step": 280 |
| }, |
| { |
| "epoch": 1.425, |
| "grad_norm": 4.09375, |
| "learning_rate": 9.26849499754977e-05, |
| "loss": 0.6307, |
| "step": 285 |
| }, |
| { |
| "epoch": 1.45, |
| "grad_norm": 3.921875, |
| "learning_rate": 9.257293358910211e-05, |
| "loss": 0.6069, |
| "step": 290 |
| }, |
| { |
| "epoch": 1.475, |
| "grad_norm": 4.09375, |
| "learning_rate": 9.2458815169117e-05, |
| "loss": 0.6295, |
| "step": 295 |
| }, |
| { |
| "epoch": 1.5, |
| "grad_norm": 4.1875, |
| "learning_rate": 9.234260200790208e-05, |
| "loss": 0.5912, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.525, |
| "grad_norm": 4.09375, |
| "learning_rate": 9.222430153167454e-05, |
| "loss": 0.6214, |
| "step": 305 |
| }, |
| { |
| "epoch": 1.55, |
| "grad_norm": 3.90625, |
| "learning_rate": 9.210392130003452e-05, |
| "loss": 0.6364, |
| "step": 310 |
| }, |
| { |
| "epoch": 1.575, |
| "grad_norm": 4.125, |
| "learning_rate": 9.198146900548206e-05, |
| "loss": 0.6212, |
| "step": 315 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 4.25, |
| "learning_rate": 9.185695247292549e-05, |
| "loss": 0.593, |
| "step": 320 |
| }, |
| { |
| "epoch": 1.625, |
| "grad_norm": 4.1875, |
| "learning_rate": 9.173037965918148e-05, |
| "loss": 0.6031, |
| "step": 325 |
| }, |
| { |
| "epoch": 1.65, |
| "grad_norm": 4.375, |
| "learning_rate": 9.16017586524665e-05, |
| "loss": 0.589, |
| "step": 330 |
| }, |
| { |
| "epoch": 1.675, |
| "grad_norm": 4.125, |
| "learning_rate": 9.147109767188e-05, |
| "loss": 0.5981, |
| "step": 335 |
| }, |
| { |
| "epoch": 1.7, |
| "grad_norm": 3.984375, |
| "learning_rate": 9.133840506687925e-05, |
| "loss": 0.6, |
| "step": 340 |
| }, |
| { |
| "epoch": 1.725, |
| "grad_norm": 3.796875, |
| "learning_rate": 9.120368931674573e-05, |
| "loss": 0.631, |
| "step": 345 |
| }, |
| { |
| "epoch": 1.75, |
| "grad_norm": 3.9375, |
| "learning_rate": 9.106695903004326e-05, |
| "loss": 0.6364, |
| "step": 350 |
| }, |
| { |
| "epoch": 1.775, |
| "grad_norm": 4.09375, |
| "learning_rate": 9.092822294406803e-05, |
| "loss": 0.6163, |
| "step": 355 |
| }, |
| { |
| "epoch": 1.8, |
| "grad_norm": 4.46875, |
| "learning_rate": 9.078748992429015e-05, |
| "loss": 0.6224, |
| "step": 360 |
| }, |
| { |
| "epoch": 1.825, |
| "grad_norm": 4.65625, |
| "learning_rate": 9.064476896378714e-05, |
| "loss": 0.6471, |
| "step": 365 |
| }, |
| { |
| "epoch": 1.85, |
| "grad_norm": 4.125, |
| "learning_rate": 9.050006918266936e-05, |
| "loss": 0.6533, |
| "step": 370 |
| }, |
| { |
| "epoch": 1.875, |
| "grad_norm": 4.09375, |
| "learning_rate": 9.035339982749709e-05, |
| "loss": 0.6316, |
| "step": 375 |
| }, |
| { |
| "epoch": 1.9, |
| "grad_norm": 3.9375, |
| "learning_rate": 9.020477027068971e-05, |
| "loss": 0.6389, |
| "step": 380 |
| }, |
| { |
| "epoch": 1.925, |
| "grad_norm": 4.125, |
| "learning_rate": 9.005419000992689e-05, |
| "loss": 0.6385, |
| "step": 385 |
| }, |
| { |
| "epoch": 1.95, |
| "grad_norm": 4.03125, |
| "learning_rate": 8.990166866754144e-05, |
| "loss": 0.5948, |
| "step": 390 |
| }, |
| { |
| "epoch": 1.975, |
| "grad_norm": 4.0625, |
| "learning_rate": 8.974721598990464e-05, |
| "loss": 0.6169, |
| "step": 395 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 4.15625, |
| "learning_rate": 8.959084184680336e-05, |
| "loss": 0.63, |
| "step": 400 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 1.0628207921981812, |
| "eval_runtime": 0.2691, |
| "eval_samples_per_second": 11.148, |
| "eval_steps_per_second": 11.148, |
| "step": 400 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 2000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.92559424028672e+17, |
| "train_batch_size": 140, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
