| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.20012336371736, | |
| "eval_steps": 365, | |
| "global_step": 365, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005482831882667398, | |
| "grad_norm": 1.8271640439809084e-13, | |
| "learning_rate": 9.999257569732963e-06, | |
| "loss": 0.0547, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010965663765334796, | |
| "grad_norm": 1.8681511551469146e-14, | |
| "learning_rate": 9.997030499412933e-06, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.016448495648002194, | |
| "grad_norm": 1.2511433729323063e-11, | |
| "learning_rate": 9.993319450417669e-06, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.021931327530669592, | |
| "grad_norm": 3.090452546650191e-11, | |
| "learning_rate": 9.988125524825216e-06, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02741415941333699, | |
| "grad_norm": 1.458404726736688e-14, | |
| "learning_rate": 9.981450265086598e-06, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03289699129600439, | |
| "grad_norm": 3.242672515051115e-14, | |
| "learning_rate": 9.973295653567764e-06, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.038379823178671786, | |
| "grad_norm": 2.718872761479918e-14, | |
| "learning_rate": 9.963664111960875e-06, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.043862655061339184, | |
| "grad_norm": 9.169036085943105e-10, | |
| "learning_rate": 9.952558500565135e-06, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.04934548694400658, | |
| "grad_norm": 6.057082835297933e-09, | |
| "learning_rate": 9.939982117437356e-06, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.05482831882667398, | |
| "grad_norm": 2.746146947174566e-06, | |
| "learning_rate": 9.925938697412536e-06, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.06031115070934138, | |
| "grad_norm": 2.1543860384554137e-07, | |
| "learning_rate": 9.910432410994701e-06, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.06579398259200878, | |
| "grad_norm": 1.2734583378914976e-06, | |
| "learning_rate": 9.893467863118402e-06, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.07127681447467617, | |
| "grad_norm": 3.238647128256389e-09, | |
| "learning_rate": 9.87505009178116e-06, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.07675964635734357, | |
| "grad_norm": 1.8630474585279444e-07, | |
| "learning_rate": 9.855184566547333e-06, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.08224247824001096, | |
| "grad_norm": 1.8918351329944016e-09, | |
| "learning_rate": 9.833877186923803e-06, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.08772531012267837, | |
| "grad_norm": 1.6541060188224321e-10, | |
| "learning_rate": 9.811134280607988e-06, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.09320814200534576, | |
| "grad_norm": 0.0067967576906085014, | |
| "learning_rate": 9.786962601608689e-06, | |
| "loss": 0.0015, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.09869097388801316, | |
| "grad_norm": 7.394525164272636e-05, | |
| "learning_rate": 9.761369328240347e-06, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.10417380577068056, | |
| "grad_norm": 2.62540652329335e-07, | |
| "learning_rate": 9.734362060991274e-06, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.10965663765334796, | |
| "grad_norm": 4.609726822479843e-09, | |
| "learning_rate": 9.70594882026652e-06, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.11513946953601535, | |
| "grad_norm": 8.970529319363152e-10, | |
| "learning_rate": 9.676138044006051e-06, | |
| "loss": 0.0, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.12062230141868276, | |
| "grad_norm": 7.758627629250725e-10, | |
| "learning_rate": 9.644938585178894e-06, | |
| "loss": 0.0, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.12610513330135015, | |
| "grad_norm": 3.484149357912969e-10, | |
| "learning_rate": 9.61235970915407e-06, | |
| "loss": 0.0, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.13158796518401755, | |
| "grad_norm": 3.5987784974267356e-10, | |
| "learning_rate": 9.57841109094903e-06, | |
| "loss": 0.0, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.13707079706668493, | |
| "grad_norm": 2.9926486289078014e-10, | |
| "learning_rate": 9.543102812356446e-06, | |
| "loss": 0.0, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.14255362894935233, | |
| "grad_norm": 2.17573001282112e-10, | |
| "learning_rate": 9.506445358950199e-06, | |
| "loss": 0.0, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.14803646083201974, | |
| "grad_norm": 1.5743054082584251e-10, | |
| "learning_rate": 9.468449616971458e-06, | |
| "loss": 0.0, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.15351929271468714, | |
| "grad_norm": 3.0337881185005244e-07, | |
| "learning_rate": 9.429126870095766e-06, | |
| "loss": 0.0, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.15900212459735452, | |
| "grad_norm": 2.075781768695606e-10, | |
| "learning_rate": 9.388488796082113e-06, | |
| "loss": 0.0, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.16448495648002193, | |
| "grad_norm": 2.6534453922977264e-07, | |
| "learning_rate": 9.346547463304953e-06, | |
| "loss": 0.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.16996778836268933, | |
| "grad_norm": 2.213984316767892e-06, | |
| "learning_rate": 9.303315327170244e-06, | |
| "loss": 0.0, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.17545062024535674, | |
| "grad_norm": 1.0965933022744068e-10, | |
| "learning_rate": 9.258805226416536e-06, | |
| "loss": 0.0, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.1809334521280241, | |
| "grad_norm": 9.682482593476038e-11, | |
| "learning_rate": 9.213030379302223e-06, | |
| "loss": 0.0, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.18641628401069152, | |
| "grad_norm": 1.8911376631347565e-10, | |
| "learning_rate": 9.166004379680094e-06, | |
| "loss": 0.0, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.19189911589335892, | |
| "grad_norm": 2.287967731939844e-10, | |
| "learning_rate": 9.11774119296033e-06, | |
| "loss": 0.0, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.19738194777602633, | |
| "grad_norm": 1.6538861946635564e-10, | |
| "learning_rate": 9.068255151963174e-06, | |
| "loss": 0.0, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.20012336371736, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 8.152250430271124e-09, | |
| "eval_runtime": 172.1258, | |
| "eval_samples_per_second": 37.455, | |
| "eval_steps_per_second": 4.683, | |
| "step": 365 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1823, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 365, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |