| { | |
| "best_metric": 0.3568706512451172, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.17006802721088435, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006802721088435374, | |
| "grad_norm": 27.985506057739258, | |
| "learning_rate": 5e-05, | |
| "loss": 14.1545, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006802721088435374, | |
| "eval_loss": 15.025331497192383, | |
| "eval_runtime": 28.1339, | |
| "eval_samples_per_second": 35.189, | |
| "eval_steps_per_second": 4.408, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013605442176870748, | |
| "grad_norm": 25.25408172607422, | |
| "learning_rate": 0.0001, | |
| "loss": 13.8137, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02040816326530612, | |
| "grad_norm": 18.87286949157715, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 12.4349, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.027210884353741496, | |
| "grad_norm": 11.770044326782227, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.2198, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.034013605442176874, | |
| "grad_norm": 13.52858829498291, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 9.8085, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04081632653061224, | |
| "grad_norm": 16.554401397705078, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 8.3188, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.047619047619047616, | |
| "grad_norm": 19.92739486694336, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 6.0097, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05442176870748299, | |
| "grad_norm": 26.91805648803711, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.4643, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.061224489795918366, | |
| "grad_norm": 19.16990852355957, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.2118, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06802721088435375, | |
| "grad_norm": 11.783681869506836, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.5312, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07482993197278912, | |
| "grad_norm": 12.638397216796875, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.0482, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.08163265306122448, | |
| "grad_norm": 13.327069282531738, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.3775, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08843537414965986, | |
| "grad_norm": 13.761669158935547, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.9374, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09523809523809523, | |
| "grad_norm": 6.490602016448975, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5507, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.10204081632653061, | |
| "grad_norm": 5.756254196166992, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.6185, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.10884353741496598, | |
| "grad_norm": 11.494712829589844, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.7216, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.11564625850340136, | |
| "grad_norm": 5.566164970397949, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.5369, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.12244897959183673, | |
| "grad_norm": 6.94112491607666, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.4294, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1292517006802721, | |
| "grad_norm": 17.111412048339844, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.954, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1360544217687075, | |
| "grad_norm": 6.664422512054443, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4906, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 8.071250915527344, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.3875, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.14965986394557823, | |
| "grad_norm": 2.643317937850952, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.3396, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1564625850340136, | |
| "grad_norm": 4.199344635009766, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.4363, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "grad_norm": 12.902344703674316, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.7282, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.17006802721088435, | |
| "grad_norm": 14.95378589630127, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.6819, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.17006802721088435, | |
| "eval_loss": 0.3568706512451172, | |
| "eval_runtime": 28.3029, | |
| "eval_samples_per_second": 34.979, | |
| "eval_steps_per_second": 4.381, | |
| "step": 25 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.06796798217814e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |