| { | |
| "best_metric": 0.8644523024559021, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.4140786749482402, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008281573498964804, | |
| "grad_norm": 0.8388795256614685, | |
| "learning_rate": 7e-06, | |
| "loss": 0.804, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008281573498964804, | |
| "eval_loss": 1.1692047119140625, | |
| "eval_runtime": 32.2894, | |
| "eval_samples_per_second": 6.318, | |
| "eval_steps_per_second": 1.579, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.016563146997929608, | |
| "grad_norm": 1.023823618888855, | |
| "learning_rate": 1.4e-05, | |
| "loss": 0.8544, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.024844720496894408, | |
| "grad_norm": 1.0270742177963257, | |
| "learning_rate": 2.1e-05, | |
| "loss": 0.8755, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.033126293995859216, | |
| "grad_norm": 0.9506105780601501, | |
| "learning_rate": 2.8e-05, | |
| "loss": 0.8441, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.041407867494824016, | |
| "grad_norm": 0.7932412028312683, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.7846, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.049689440993788817, | |
| "grad_norm": 0.7128869295120239, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.9147, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.057971014492753624, | |
| "grad_norm": 0.4176234304904938, | |
| "learning_rate": 4.899999999999999e-05, | |
| "loss": 0.7784, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06625258799171843, | |
| "grad_norm": 0.6762263178825378, | |
| "learning_rate": 5.6e-05, | |
| "loss": 0.8248, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07453416149068323, | |
| "grad_norm": 0.8291305899620056, | |
| "learning_rate": 6.3e-05, | |
| "loss": 0.8014, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08281573498964803, | |
| "grad_norm": 0.8136356472969055, | |
| "learning_rate": 7e-05, | |
| "loss": 0.9253, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09109730848861283, | |
| "grad_norm": 0.4319281578063965, | |
| "learning_rate": 6.999521567473641e-05, | |
| "loss": 0.8555, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.09937888198757763, | |
| "grad_norm": 0.36292925477027893, | |
| "learning_rate": 6.998086400693241e-05, | |
| "loss": 0.7425, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.10766045548654245, | |
| "grad_norm": 0.3616969585418701, | |
| "learning_rate": 6.995694892019065e-05, | |
| "loss": 0.9021, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.11594202898550725, | |
| "grad_norm": 0.3888731002807617, | |
| "learning_rate": 6.99234769526571e-05, | |
| "loss": 0.7912, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.12422360248447205, | |
| "grad_norm": 0.3677065968513489, | |
| "learning_rate": 6.988045725523343e-05, | |
| "loss": 0.6922, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.13250517598343686, | |
| "grad_norm": 0.38920730352401733, | |
| "learning_rate": 6.982790158907539e-05, | |
| "loss": 0.8843, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.14078674948240166, | |
| "grad_norm": 0.4462592601776123, | |
| "learning_rate": 6.976582432237733e-05, | |
| "loss": 0.9304, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.14906832298136646, | |
| "grad_norm": 0.40514039993286133, | |
| "learning_rate": 6.969424242644413e-05, | |
| "loss": 0.8461, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.15734989648033126, | |
| "grad_norm": 0.44129592180252075, | |
| "learning_rate": 6.961317547105138e-05, | |
| "loss": 0.8518, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.16563146997929606, | |
| "grad_norm": 0.4335060715675354, | |
| "learning_rate": 6.952264561909527e-05, | |
| "loss": 0.8793, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.17391304347826086, | |
| "grad_norm": 0.543445885181427, | |
| "learning_rate": 6.942267762053337e-05, | |
| "loss": 0.9113, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.18219461697722567, | |
| "grad_norm": 0.5542380809783936, | |
| "learning_rate": 6.931329880561832e-05, | |
| "loss": 0.9433, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 0.516521692276001, | |
| "learning_rate": 6.919453907742597e-05, | |
| "loss": 0.9016, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.19875776397515527, | |
| "grad_norm": 0.5378891825675964, | |
| "learning_rate": 6.90664309036802e-05, | |
| "loss": 0.7877, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2070393374741201, | |
| "grad_norm": 0.577548086643219, | |
| "learning_rate": 6.892900930787656e-05, | |
| "loss": 0.8454, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2153209109730849, | |
| "grad_norm": 0.5783238410949707, | |
| "learning_rate": 6.87823118597072e-05, | |
| "loss": 0.8776, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2236024844720497, | |
| "grad_norm": 0.5544853210449219, | |
| "learning_rate": 6.862637866478969e-05, | |
| "loss": 0.8123, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2318840579710145, | |
| "grad_norm": 0.7183583974838257, | |
| "learning_rate": 6.846125235370252e-05, | |
| "loss": 0.941, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2401656314699793, | |
| "grad_norm": 0.7497084140777588, | |
| "learning_rate": 6.828697807033038e-05, | |
| "loss": 0.9533, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2484472049689441, | |
| "grad_norm": 1.0239611864089966, | |
| "learning_rate": 6.81036034595222e-05, | |
| "loss": 1.0226, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2567287784679089, | |
| "grad_norm": 0.215080127120018, | |
| "learning_rate": 6.791117865406564e-05, | |
| "loss": 0.5555, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2650103519668737, | |
| "grad_norm": 0.32441794872283936, | |
| "learning_rate": 6.770975626098112e-05, | |
| "loss": 0.7501, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2732919254658385, | |
| "grad_norm": 0.309184730052948, | |
| "learning_rate": 6.749939134713974e-05, | |
| "loss": 0.7853, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2815734989648033, | |
| "grad_norm": 0.3206530511379242, | |
| "learning_rate": 6.728014142420846e-05, | |
| "loss": 0.659, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.2898550724637681, | |
| "grad_norm": 0.2530266046524048, | |
| "learning_rate": 6.7052066432927e-05, | |
| "loss": 0.651, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2981366459627329, | |
| "grad_norm": 0.27744585275650024, | |
| "learning_rate": 6.681522872672069e-05, | |
| "loss": 0.6502, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3064182194616977, | |
| "grad_norm": 0.2372923493385315, | |
| "learning_rate": 6.656969305465356e-05, | |
| "loss": 0.7619, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3146997929606625, | |
| "grad_norm": 0.2609351575374603, | |
| "learning_rate": 6.631552654372672e-05, | |
| "loss": 0.6668, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.32298136645962733, | |
| "grad_norm": 0.2953057885169983, | |
| "learning_rate": 6.60527986805264e-05, | |
| "loss": 0.7653, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.33126293995859213, | |
| "grad_norm": 0.32191261649131775, | |
| "learning_rate": 6.578158129222711e-05, | |
| "loss": 0.8575, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.33954451345755693, | |
| "grad_norm": 0.2882176339626312, | |
| "learning_rate": 6.550194852695469e-05, | |
| "loss": 0.7252, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.34782608695652173, | |
| "grad_norm": 0.27066636085510254, | |
| "learning_rate": 6.521397683351509e-05, | |
| "loss": 0.7575, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.35610766045548653, | |
| "grad_norm": 0.3208519518375397, | |
| "learning_rate": 6.491774494049386e-05, | |
| "loss": 0.8635, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.36438923395445133, | |
| "grad_norm": 0.35946550965309143, | |
| "learning_rate": 6.461333383473272e-05, | |
| "loss": 0.8081, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.37267080745341613, | |
| "grad_norm": 0.3770899176597595, | |
| "learning_rate": 6.430082673918849e-05, | |
| "loss": 0.8199, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 0.36672505736351013, | |
| "learning_rate": 6.398030909018069e-05, | |
| "loss": 0.8569, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.38923395445134573, | |
| "grad_norm": 0.3554442226886749, | |
| "learning_rate": 6.365186851403423e-05, | |
| "loss": 0.8098, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.39751552795031053, | |
| "grad_norm": 0.3235284388065338, | |
| "learning_rate": 6.331559480312315e-05, | |
| "loss": 0.791, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4057971014492754, | |
| "grad_norm": 0.3624836206436157, | |
| "learning_rate": 6.297157989132236e-05, | |
| "loss": 0.7369, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4140786749482402, | |
| "grad_norm": 0.3535378873348236, | |
| "learning_rate": 6.261991782887377e-05, | |
| "loss": 0.6616, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4140786749482402, | |
| "eval_loss": 0.8644523024559021, | |
| "eval_runtime": 32.248, | |
| "eval_samples_per_second": 6.326, | |
| "eval_steps_per_second": 1.581, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 4, | |
| "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": 1.696706304367657e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |