| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.021194673072167863, | |
| "eval_steps": 13, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00014129782048111908, | |
| "eval_loss": NaN, | |
| "eval_runtime": 235.7619, | |
| "eval_samples_per_second": 50.559, | |
| "eval_steps_per_second": 6.32, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004238934614433572, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008477869228867144, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0012716803843300717, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016955738457734289, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.994965332706573e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.001836871666254548, | |
| "eval_loss": NaN, | |
| "eval_runtime": 235.922, | |
| "eval_samples_per_second": 50.525, | |
| "eval_steps_per_second": 6.316, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002119467307216786, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.968561049466214e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0025433607686601435, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.919647942993148e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.002967254230103501, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.848447601883435e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0033911476915468577, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003673743332509096, | |
| "eval_loss": NaN, | |
| "eval_runtime": 235.9223, | |
| "eval_samples_per_second": 50.525, | |
| "eval_steps_per_second": 6.316, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.003815041152990215, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.640574942595196e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004238934614433572, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00466282807587693, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.348705665778478e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.005086721537320287, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.172866268606513e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.005510614998763644, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.978122744408906e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.005510614998763644, | |
| "eval_loss": NaN, | |
| "eval_runtime": 235.965, | |
| "eval_samples_per_second": 50.516, | |
| "eval_steps_per_second": 6.314, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.005934508460207002, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.765357330018056e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.006358401921650359, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.006782295383093715, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.289693629698564e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.007206188844537073, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.0289502192041e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.007347486665018192, | |
| "eval_loss": NaN, | |
| "eval_runtime": 235.958, | |
| "eval_samples_per_second": 50.517, | |
| "eval_steps_per_second": 6.315, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.00763008230598043, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.754484907260513e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.008053975767423787, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.467541090321735e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.008477869228867145, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.169418695587791e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.008901762690310502, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.861468292009727e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.00918435833127274, | |
| "eval_loss": NaN, | |
| "eval_runtime": 235.8169, | |
| "eval_samples_per_second": 50.548, | |
| "eval_steps_per_second": 6.318, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.00932565615175386, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.009749549613197217, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.22170203068947e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.010173443074640574, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.8927844739931834e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.010597336536083931, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.559822380516539e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.011021229997527289, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.2243241517525754e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.011021229997527289, | |
| "eval_loss": NaN, | |
| "eval_runtime": 235.731, | |
| "eval_samples_per_second": 50.566, | |
| "eval_steps_per_second": 6.321, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.011445123458970646, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.887809678520976e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.011869016920414003, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.551803455482833e-05, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.01229291038185736, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.012716803843300718, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.887395330218429e-05, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.012858101663781835, | |
| "eval_loss": NaN, | |
| "eval_runtime": 235.7733, | |
| "eval_samples_per_second": 50.557, | |
| "eval_steps_per_second": 6.32, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.013140697304744074, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.562003362839914e-05, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.01356459076618743, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.243125879593286e-05, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.013988484227630788, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.932207475167398e-05, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.014412377689074145, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.630656687635007e-05, | |
| "loss": 0.0, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.014694973330036384, | |
| "eval_loss": NaN, | |
| "eval_runtime": 235.7296, | |
| "eval_samples_per_second": 50.566, | |
| "eval_steps_per_second": 6.321, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.014836271150517503, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3398396174233178e-05, | |
| "loss": 0.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.01526016461196086, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.015684058073404217, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7956219300748793e-05, | |
| "loss": 0.0, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.016107951534847575, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.544686755065677e-05, | |
| "loss": 0.0, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.016531844996290932, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3094050125632972e-05, | |
| "loss": 0.0, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.016531844996290932, | |
| "eval_loss": NaN, | |
| "eval_runtime": 235.7863, | |
| "eval_samples_per_second": 50.554, | |
| "eval_steps_per_second": 6.319, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.01695573845773429, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.090842587659851e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.017379631919177647, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.899896227604509e-06, | |
| "loss": 0.0, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.017803525380621004, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.077560319906695e-06, | |
| "loss": 0.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.01822741884206436, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 0.0, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.01836871666254548, | |
| "eval_loss": NaN, | |
| "eval_runtime": 235.7866, | |
| "eval_samples_per_second": 50.554, | |
| "eval_steps_per_second": 6.319, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.01865131230350772, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.023611372427471e-06, | |
| "loss": 0.0, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.019075205764951076, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8058334845816213e-06, | |
| "loss": 0.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.019499099226394433, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8018569652073381e-06, | |
| "loss": 0.0, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.01992299268783779, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.016230078838226e-06, | |
| "loss": 0.0, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.02020558832880003, | |
| "eval_loss": NaN, | |
| "eval_runtime": 235.8437, | |
| "eval_samples_per_second": 50.542, | |
| "eval_steps_per_second": 6.318, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.020346886149281148, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.52511911603265e-07, | |
| "loss": 0.0, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.020770779610724505, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.132562476771959e-07, | |
| "loss": 0.0, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.021194673072167863, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 150, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.19972177870848e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |