| { | |
| "best_metric": 0.6373523473739624, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.0711490572749911, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001422981145499822, | |
| "grad_norm": 0.8191930651664734, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 2.8579, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001422981145499822, | |
| "eval_loss": 2.6855461597442627, | |
| "eval_runtime": 2.0671, | |
| "eval_samples_per_second": 24.188, | |
| "eval_steps_per_second": 3.386, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002845962290999644, | |
| "grad_norm": 0.9729381799697876, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 3.0766, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004268943436499467, | |
| "grad_norm": 0.8968315124511719, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 2.5414, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005691924581999288, | |
| "grad_norm": 0.882707417011261, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 2.5339, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007114905727499111, | |
| "grad_norm": 0.916093647480011, | |
| "learning_rate": 0.00015, | |
| "loss": 2.5088, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008537886872998933, | |
| "grad_norm": 0.9488129615783691, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 2.385, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009960868018498754, | |
| "grad_norm": 1.007516860961914, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 2.2796, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.011383849163998577, | |
| "grad_norm": 1.0053644180297852, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 2.0712, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012806830309498399, | |
| "grad_norm": 0.915839433670044, | |
| "learning_rate": 0.00027, | |
| "loss": 1.998, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.014229811454998222, | |
| "grad_norm": 0.7682165503501892, | |
| "learning_rate": 0.0003, | |
| "loss": 1.8872, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.015652792600498042, | |
| "grad_norm": 0.8641461133956909, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 1.7376, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.017075773745997867, | |
| "grad_norm": 0.8075277805328369, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 1.632, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.018498754891497687, | |
| "grad_norm": 0.762394905090332, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 1.347, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.019921736036997508, | |
| "grad_norm": 0.7908850312232971, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 1.1928, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.021344717182497332, | |
| "grad_norm": 0.8413186073303223, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 1.0229, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.022767698327997153, | |
| "grad_norm": 0.8821457028388977, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 1.019, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.024190679473496977, | |
| "grad_norm": 0.9173251986503601, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 1.0191, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.025613660618996798, | |
| "grad_norm": 0.7435721755027771, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 0.9497, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02703664176449662, | |
| "grad_norm": 0.7625381350517273, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 0.8573, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.028459622909996443, | |
| "grad_norm": 0.8063183426856995, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 0.9115, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.029882604055496264, | |
| "grad_norm": 0.6584380269050598, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 0.7548, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.031305585200996085, | |
| "grad_norm": 0.6741005182266235, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 0.8572, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03272856634649591, | |
| "grad_norm": 0.6349349617958069, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 0.7942, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03415154749199573, | |
| "grad_norm": 0.5690104961395264, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 0.7952, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03557452863749555, | |
| "grad_norm": 0.5119650363922119, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 0.8102, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03557452863749555, | |
| "eval_loss": 0.8686224222183228, | |
| "eval_runtime": 1.5871, | |
| "eval_samples_per_second": 31.505, | |
| "eval_steps_per_second": 4.411, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.036997509782995375, | |
| "grad_norm": 0.6452613472938538, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 0.9172, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0384204909284952, | |
| "grad_norm": 0.5750677585601807, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 0.8096, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.039843472073995016, | |
| "grad_norm": 0.493135005235672, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 0.6532, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.04126645321949484, | |
| "grad_norm": 0.566339373588562, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.7725, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.042689434364994665, | |
| "grad_norm": 0.4760490655899048, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 0.8217, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04411241551049449, | |
| "grad_norm": 0.4571889340877533, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 0.746, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.045535396655994306, | |
| "grad_norm": 0.4935093820095062, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 0.7695, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04695837780149413, | |
| "grad_norm": 0.4788101315498352, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 0.7196, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.048381358946993955, | |
| "grad_norm": 0.4659596383571625, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 0.6524, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04980434009249377, | |
| "grad_norm": 0.4702892005443573, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 0.7084, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.051227321237993596, | |
| "grad_norm": 0.43953150510787964, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 0.6571, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.05265030238349342, | |
| "grad_norm": 0.48017436265945435, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 0.6499, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.05407328352899324, | |
| "grad_norm": 0.4220162034034729, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 0.6256, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.05549626467449306, | |
| "grad_norm": 0.45973941683769226, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 0.6496, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.056919245819992886, | |
| "grad_norm": 0.49031051993370056, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 0.7017, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05834222696549271, | |
| "grad_norm": 0.50996333360672, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 0.646, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05976520811099253, | |
| "grad_norm": 0.49370792508125305, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 0.6681, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.06118818925649235, | |
| "grad_norm": 0.6224830746650696, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 0.7153, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.06261117040199217, | |
| "grad_norm": 0.47643178701400757, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 0.7022, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.064034151547492, | |
| "grad_norm": 0.5734248757362366, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 0.7246, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06545713269299182, | |
| "grad_norm": 0.6396843194961548, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 0.6551, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06688011383849164, | |
| "grad_norm": 0.7682932019233704, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 0.7881, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06830309498399147, | |
| "grad_norm": 0.5934016704559326, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.6506, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06972607612949129, | |
| "grad_norm": 1.0871713161468506, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 0.8281, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0711490572749911, | |
| "grad_norm": 0.8507772088050842, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 0.8056, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0711490572749911, | |
| "eval_loss": 0.6373523473739624, | |
| "eval_runtime": 1.5884, | |
| "eval_samples_per_second": 31.477, | |
| "eval_steps_per_second": 4.407, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0991728418881536e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |