| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.976, | |
| "eval_steps": 500, | |
| "global_step": 186, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.19458943605422974, | |
| "learning_rate": 4.9910902453260824e-05, | |
| "loss": 0.8099, | |
| "num_input_tokens_seen": 114944, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.23063905537128448, | |
| "learning_rate": 4.964424488287009e-05, | |
| "loss": 0.958, | |
| "num_input_tokens_seen": 227728, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.22587424516677856, | |
| "learning_rate": 4.920192797165511e-05, | |
| "loss": 0.715, | |
| "num_input_tokens_seen": 326640, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.17264235019683838, | |
| "learning_rate": 4.858710446774951e-05, | |
| "loss": 0.7585, | |
| "num_input_tokens_seen": 437280, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.19875957071781158, | |
| "learning_rate": 4.780415671242334e-05, | |
| "loss": 0.7342, | |
| "num_input_tokens_seen": 530192, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.36600446701049805, | |
| "learning_rate": 4.685866540361456e-05, | |
| "loss": 0.6904, | |
| "num_input_tokens_seen": 634960, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.20120520889759064, | |
| "learning_rate": 4.5757369817809415e-05, | |
| "loss": 0.8254, | |
| "num_input_tokens_seen": 740704, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.22245633602142334, | |
| "learning_rate": 4.45081197738023e-05, | |
| "loss": 0.7551, | |
| "num_input_tokens_seen": 841600, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.27814680337905884, | |
| "learning_rate": 4.3119819680728e-05, | |
| "loss": 0.7747, | |
| "num_input_tokens_seen": 947648, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.27052441239356995, | |
| "learning_rate": 4.160236506918098e-05, | |
| "loss": 0.7027, | |
| "num_input_tokens_seen": 1047520, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.38937926292419434, | |
| "learning_rate": 3.9966572057815373e-05, | |
| "loss": 0.7581, | |
| "num_input_tokens_seen": 1148080, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.37379005551338196, | |
| "learning_rate": 3.822410025817406e-05, | |
| "loss": 0.7221, | |
| "num_input_tokens_seen": 1252880, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 0.34213003516197205, | |
| "learning_rate": 3.638736966726585e-05, | |
| "loss": 0.8214, | |
| "num_input_tokens_seen": 1364304, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.33407434821128845, | |
| "learning_rate": 3.44694721402644e-05, | |
| "loss": 0.6304, | |
| "num_input_tokens_seen": 1466240, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.33909159898757935, | |
| "learning_rate": 3.2484078074333954e-05, | |
| "loss": 0.6434, | |
| "num_input_tokens_seen": 1558752, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.4054814577102661, | |
| "learning_rate": 3.0445338968721287e-05, | |
| "loss": 0.6796, | |
| "num_input_tokens_seen": 1668480, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.3599999999999999, | |
| "grad_norm": 0.2723485231399536, | |
| "learning_rate": 2.836778655564653e-05, | |
| "loss": 0.6651, | |
| "num_input_tokens_seen": 1773264, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.3467393219470978, | |
| "learning_rate": 2.6266229220967818e-05, | |
| "loss": 0.7844, | |
| "num_input_tokens_seen": 1885920, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 0.4250239431858063, | |
| "learning_rate": 2.4155646452913296e-05, | |
| "loss": 0.8139, | |
| "num_input_tokens_seen": 1996656, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.30656036734580994, | |
| "learning_rate": 2.2051082071228854e-05, | |
| "loss": 0.6717, | |
| "num_input_tokens_seen": 2102896, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.6800000000000002, | |
| "grad_norm": 0.49129152297973633, | |
| "learning_rate": 1.9967536997783494e-05, | |
| "loss": 0.7524, | |
| "num_input_tokens_seen": 2214272, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 0.3904927670955658, | |
| "learning_rate": 1.79198623329424e-05, | |
| "loss": 0.631, | |
| "num_input_tokens_seen": 2316448, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.8399999999999999, | |
| "grad_norm": 0.2829418182373047, | |
| "learning_rate": 1.5922653499838137e-05, | |
| "loss": 0.7462, | |
| "num_input_tokens_seen": 2425248, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.29749077558517456, | |
| "learning_rate": 1.399014621105914e-05, | |
| "loss": 0.6148, | |
| "num_input_tokens_seen": 2537680, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.38928714394569397, | |
| "learning_rate": 1.2136114999284288e-05, | |
| "loss": 0.7145, | |
| "num_input_tokens_seen": 2642080, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": 0.3223271369934082, | |
| "learning_rate": 1.0373775035117305e-05, | |
| "loss": 0.6798, | |
| "num_input_tokens_seen": 2750752, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "grad_norm": 0.29905465245246887, | |
| "learning_rate": 8.715687931944449e-06, | |
| "loss": 0.6754, | |
| "num_input_tokens_seen": 2852096, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "grad_norm": 0.3506278991699219, | |
| "learning_rate": 7.173672209219495e-06, | |
| "loss": 0.6708, | |
| "num_input_tokens_seen": 2951888, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "grad_norm": 0.3896699547767639, | |
| "learning_rate": 5.758719052376693e-06, | |
| "loss": 0.6386, | |
| "num_input_tokens_seen": 3049616, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 0.5055662989616394, | |
| "learning_rate": 4.480913969818098e-06, | |
| "loss": 0.6995, | |
| "num_input_tokens_seen": 3150784, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "grad_norm": 0.30896279215812683, | |
| "learning_rate": 3.3493649053890326e-06, | |
| "loss": 0.6691, | |
| "num_input_tokens_seen": 3262992, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 0.30288368463516235, | |
| "learning_rate": 2.372137318741968e-06, | |
| "loss": 0.6024, | |
| "num_input_tokens_seen": 3371440, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "grad_norm": 0.3581477999687195, | |
| "learning_rate": 1.5561966963229924e-06, | |
| "loss": 0.6484, | |
| "num_input_tokens_seen": 3473680, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 2.7199999999999998, | |
| "grad_norm": 0.43826210498809814, | |
| "learning_rate": 9.073589027514789e-07, | |
| "loss": 0.7137, | |
| "num_input_tokens_seen": 3574736, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "grad_norm": 0.22761593759059906, | |
| "learning_rate": 4.302487264785521e-07, | |
| "loss": 0.777, | |
| "num_input_tokens_seen": 3697920, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "grad_norm": 0.3505564033985138, | |
| "learning_rate": 1.2826691520262114e-07, | |
| "loss": 0.6529, | |
| "num_input_tokens_seen": 3803552, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "grad_norm": 0.48998603224754333, | |
| "learning_rate": 3.565936007254855e-09, | |
| "loss": 0.6996, | |
| "num_input_tokens_seen": 3907456, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 2.976, | |
| "num_input_tokens_seen": 3930992, | |
| "step": 186, | |
| "total_flos": 3.112338516554547e+16, | |
| "train_loss": 0.7158093615885703, | |
| "train_runtime": 1518.3826, | |
| "train_samples_per_second": 3.952, | |
| "train_steps_per_second": 0.122 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 186, | |
| "num_input_tokens_seen": 3930992, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.112338516554547e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |