| { | |
| "best_metric": 0.7940676212310791, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.13368983957219252, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00267379679144385, | |
| "grad_norm": 13.120458602905273, | |
| "learning_rate": 1e-05, | |
| "loss": 3.0135, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00267379679144385, | |
| "eval_loss": 2.9659292697906494, | |
| "eval_runtime": 30.2128, | |
| "eval_samples_per_second": 20.852, | |
| "eval_steps_per_second": 2.615, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0053475935828877, | |
| "grad_norm": 11.394423484802246, | |
| "learning_rate": 2e-05, | |
| "loss": 2.7657, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008021390374331552, | |
| "grad_norm": 9.692898750305176, | |
| "learning_rate": 3e-05, | |
| "loss": 2.9229, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0106951871657754, | |
| "grad_norm": 6.488343715667725, | |
| "learning_rate": 4e-05, | |
| "loss": 2.6038, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013368983957219251, | |
| "grad_norm": 4.95293664932251, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0767, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.016042780748663103, | |
| "grad_norm": 5.345605373382568, | |
| "learning_rate": 6e-05, | |
| "loss": 2.0136, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01871657754010695, | |
| "grad_norm": 5.651119709014893, | |
| "learning_rate": 7e-05, | |
| "loss": 1.889, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0213903743315508, | |
| "grad_norm": 5.409059047698975, | |
| "learning_rate": 8e-05, | |
| "loss": 1.8266, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02406417112299465, | |
| "grad_norm": 5.7462944984436035, | |
| "learning_rate": 9e-05, | |
| "loss": 1.5063, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.026737967914438502, | |
| "grad_norm": 5.222486972808838, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5455, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.029411764705882353, | |
| "grad_norm": 3.9986016750335693, | |
| "learning_rate": 9.98458666866564e-05, | |
| "loss": 1.448, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03208556149732621, | |
| "grad_norm": 3.586981773376465, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 1.1441, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.034759358288770054, | |
| "grad_norm": 3.4107515811920166, | |
| "learning_rate": 9.861849601988383e-05, | |
| "loss": 1.2066, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0374331550802139, | |
| "grad_norm": 4.240262031555176, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.0419, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.040106951871657755, | |
| "grad_norm": 3.404278039932251, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.2043, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0427807486631016, | |
| "grad_norm": 2.843229055404663, | |
| "learning_rate": 9.45503262094184e-05, | |
| "loss": 1.0498, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.045454545454545456, | |
| "grad_norm": 3.237807273864746, | |
| "learning_rate": 9.263200821770461e-05, | |
| "loss": 1.0109, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0481283422459893, | |
| "grad_norm": 3.588984251022339, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.0928, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05080213903743316, | |
| "grad_norm": 3.051542282104492, | |
| "learning_rate": 8.802029828000156e-05, | |
| "loss": 0.9856, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.053475935828877004, | |
| "grad_norm": 2.899651527404785, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.9596, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05614973262032086, | |
| "grad_norm": 2.7841622829437256, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 0.9303, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.058823529411764705, | |
| "grad_norm": 2.976398229598999, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.9815, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06149732620320856, | |
| "grad_norm": 3.123530626296997, | |
| "learning_rate": 7.612492823579745e-05, | |
| "loss": 1.0648, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06417112299465241, | |
| "grad_norm": 2.737558126449585, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 0.834, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06684491978609626, | |
| "grad_norm": 3.086487293243408, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.9048, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06684491978609626, | |
| "eval_loss": 0.8926352858543396, | |
| "eval_runtime": 30.4861, | |
| "eval_samples_per_second": 20.665, | |
| "eval_steps_per_second": 2.591, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06951871657754011, | |
| "grad_norm": 2.6327173709869385, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.9139, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.07219251336898395, | |
| "grad_norm": 2.566983222961426, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 0.8632, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0748663101604278, | |
| "grad_norm": 2.66111159324646, | |
| "learning_rate": 5.782172325201155e-05, | |
| "loss": 0.8961, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07754010695187166, | |
| "grad_norm": 2.4014999866485596, | |
| "learning_rate": 5.392295478639225e-05, | |
| "loss": 0.8594, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.08021390374331551, | |
| "grad_norm": 2.5496883392333984, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9502, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08288770053475936, | |
| "grad_norm": 2.623340368270874, | |
| "learning_rate": 4.607704521360776e-05, | |
| "loss": 0.8187, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0855614973262032, | |
| "grad_norm": 2.894226551055908, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 0.8912, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08823529411764706, | |
| "grad_norm": 2.7737977504730225, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 0.851, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.09090909090909091, | |
| "grad_norm": 3.402663469314575, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.8979, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.09358288770053476, | |
| "grad_norm": 2.527940511703491, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.8144, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0962566844919786, | |
| "grad_norm": 2.616532564163208, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.8559, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09893048128342247, | |
| "grad_norm": 2.637568473815918, | |
| "learning_rate": 2.3875071764202563e-05, | |
| "loss": 0.8393, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.10160427807486631, | |
| "grad_norm": 2.4025931358337402, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.821, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.10427807486631016, | |
| "grad_norm": 2.9822089672088623, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 1.0798, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.10695187165775401, | |
| "grad_norm": 2.652627468109131, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.845, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10962566844919786, | |
| "grad_norm": 2.6627089977264404, | |
| "learning_rate": 1.1979701719998453e-05, | |
| "loss": 0.9285, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.11229946524064172, | |
| "grad_norm": 2.631807327270508, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.8711, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.11497326203208556, | |
| "grad_norm": 2.398806571960449, | |
| "learning_rate": 7.367991782295391e-06, | |
| "loss": 0.8058, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 2.3895256519317627, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 0.8576, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.12032085561497326, | |
| "grad_norm": 2.452927827835083, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.8259, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.12299465240641712, | |
| "grad_norm": 2.3350183963775635, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.7746, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.12566844919786097, | |
| "grad_norm": 2.2762725353240967, | |
| "learning_rate": 1.3815039801161721e-06, | |
| "loss": 0.7767, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.12834224598930483, | |
| "grad_norm": 2.786212682723999, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 0.9144, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.13101604278074866, | |
| "grad_norm": 2.353525161743164, | |
| "learning_rate": 1.5413331334360182e-07, | |
| "loss": 0.7969, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.13368983957219252, | |
| "grad_norm": 2.672391176223755, | |
| "learning_rate": 0.0, | |
| "loss": 0.7842, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13368983957219252, | |
| "eval_loss": 0.7940676212310791, | |
| "eval_runtime": 30.486, | |
| "eval_samples_per_second": 20.665, | |
| "eval_steps_per_second": 2.591, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.0821993309863936e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |