| { | |
| "best_metric": 3.8318495750427246, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.03263574429894342, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006527148859788684, | |
| "grad_norm": 0.8191147446632385, | |
| "learning_rate": 1e-05, | |
| "loss": 4.5952, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006527148859788684, | |
| "eval_loss": 4.644200325012207, | |
| "eval_runtime": 162.2369, | |
| "eval_samples_per_second": 63.623, | |
| "eval_steps_per_second": 7.957, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013054297719577368, | |
| "grad_norm": 0.8031899333000183, | |
| "learning_rate": 2e-05, | |
| "loss": 4.6289, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001958144657936605, | |
| "grad_norm": 0.8169269561767578, | |
| "learning_rate": 3e-05, | |
| "loss": 4.6883, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0026108595439154735, | |
| "grad_norm": 0.7823262810707092, | |
| "learning_rate": 4e-05, | |
| "loss": 4.547, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003263574429894342, | |
| "grad_norm": 0.8156715035438538, | |
| "learning_rate": 5e-05, | |
| "loss": 4.5746, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00391628931587321, | |
| "grad_norm": 0.7746463418006897, | |
| "learning_rate": 6e-05, | |
| "loss": 4.485, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004569004201852078, | |
| "grad_norm": 0.6617835760116577, | |
| "learning_rate": 7e-05, | |
| "loss": 4.4756, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005221719087830947, | |
| "grad_norm": 0.5175589323043823, | |
| "learning_rate": 8e-05, | |
| "loss": 4.4369, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005874433973809815, | |
| "grad_norm": 0.3726535439491272, | |
| "learning_rate": 9e-05, | |
| "loss": 4.3528, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006527148859788684, | |
| "grad_norm": 0.575859785079956, | |
| "learning_rate": 0.0001, | |
| "loss": 4.3215, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007179863745767552, | |
| "grad_norm": 0.7978506088256836, | |
| "learning_rate": 9.98458666866564e-05, | |
| "loss": 4.3095, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00783257863174642, | |
| "grad_norm": 0.8266698718070984, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 4.3506, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00848529351772529, | |
| "grad_norm": 0.6456958055496216, | |
| "learning_rate": 9.861849601988383e-05, | |
| "loss": 4.2903, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009138008403704156, | |
| "grad_norm": 0.4962930679321289, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 4.2426, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.009790723289683025, | |
| "grad_norm": 0.4060556888580322, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.1318, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010443438175661894, | |
| "grad_norm": 0.3522457182407379, | |
| "learning_rate": 9.45503262094184e-05, | |
| "loss": 4.1726, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011096153061640763, | |
| "grad_norm": 0.36963698267936707, | |
| "learning_rate": 9.263200821770461e-05, | |
| "loss": 4.1933, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01174886794761963, | |
| "grad_norm": 0.3324430286884308, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 4.0834, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.012401582833598499, | |
| "grad_norm": 0.33209967613220215, | |
| "learning_rate": 8.802029828000156e-05, | |
| "loss": 4.1266, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.013054297719577368, | |
| "grad_norm": 0.3280082046985626, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.0839, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013707012605556235, | |
| "grad_norm": 0.32346111536026, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 4.0942, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.014359727491535103, | |
| "grad_norm": 0.3204044997692108, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 4.0493, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.015012442377513972, | |
| "grad_norm": 0.31801706552505493, | |
| "learning_rate": 7.612492823579745e-05, | |
| "loss": 4.0828, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01566515726349284, | |
| "grad_norm": 0.305008202791214, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 4.0288, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01631787214947171, | |
| "grad_norm": 0.2867254316806793, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.0314, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01631787214947171, | |
| "eval_loss": 4.0032172203063965, | |
| "eval_runtime": 162.334, | |
| "eval_samples_per_second": 63.585, | |
| "eval_steps_per_second": 7.953, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01697058703545058, | |
| "grad_norm": 0.275655061006546, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 4.0362, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.017623301921429444, | |
| "grad_norm": 0.2766662538051605, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 3.9851, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.018276016807408313, | |
| "grad_norm": 0.28725364804267883, | |
| "learning_rate": 5.782172325201155e-05, | |
| "loss": 3.963, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.01892873169338718, | |
| "grad_norm": 0.29449453949928284, | |
| "learning_rate": 5.392295478639225e-05, | |
| "loss": 3.8857, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01958144657936605, | |
| "grad_norm": 0.2972124218940735, | |
| "learning_rate": 5e-05, | |
| "loss": 3.9618, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02023416146534492, | |
| "grad_norm": 0.28751111030578613, | |
| "learning_rate": 4.607704521360776e-05, | |
| "loss": 3.9089, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.020886876351323788, | |
| "grad_norm": 0.2986813485622406, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 3.9097, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.021539591237302657, | |
| "grad_norm": 0.29656606912612915, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 3.8916, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.022192306123281526, | |
| "grad_norm": 0.2817177176475525, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 3.8711, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.02284502100926039, | |
| "grad_norm": 0.26632481813430786, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.8853, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02349773589523926, | |
| "grad_norm": 0.25886937975883484, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 3.876, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.02415045078121813, | |
| "grad_norm": 0.2591487765312195, | |
| "learning_rate": 2.3875071764202563e-05, | |
| "loss": 3.8295, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.024803165667196998, | |
| "grad_norm": 0.2501070201396942, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 3.8698, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.025455880553175866, | |
| "grad_norm": 0.2335180789232254, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 3.8729, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.026108595439154735, | |
| "grad_norm": 0.23493771255016327, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.8857, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.026761310325133604, | |
| "grad_norm": 0.23735849559307098, | |
| "learning_rate": 1.1979701719998453e-05, | |
| "loss": 3.8839, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.02741402521111247, | |
| "grad_norm": 0.2246159315109253, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 3.8638, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.028066740097091338, | |
| "grad_norm": 0.2345479428768158, | |
| "learning_rate": 7.367991782295391e-06, | |
| "loss": 3.8221, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.028719454983070207, | |
| "grad_norm": 0.22978436946868896, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 3.8427, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.029372169869049076, | |
| "grad_norm": 0.23703986406326294, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.8245, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.030024884755027945, | |
| "grad_norm": 0.22607843577861786, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 3.8449, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.030677599641006813, | |
| "grad_norm": 0.23095040023326874, | |
| "learning_rate": 1.3815039801161721e-06, | |
| "loss": 3.8575, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.03133031452698568, | |
| "grad_norm": 0.234283447265625, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 3.7832, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03198302941296455, | |
| "grad_norm": 0.23588110506534576, | |
| "learning_rate": 1.5413331334360182e-07, | |
| "loss": 3.816, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03263574429894342, | |
| "grad_norm": 0.22595348954200745, | |
| "learning_rate": 0.0, | |
| "loss": 3.8225, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03263574429894342, | |
| "eval_loss": 3.8318495750427246, | |
| "eval_runtime": 162.2542, | |
| "eval_samples_per_second": 63.616, | |
| "eval_steps_per_second": 7.957, | |
| "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": 1.2246627254481715e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |