| { | |
| "best_metric": 2.397162914276123, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.04893265643158603, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009786531286317206, | |
| "grad_norm": 0.9052294492721558, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4264, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009786531286317206, | |
| "eval_loss": 2.863002061843872, | |
| "eval_runtime": 2.6894, | |
| "eval_samples_per_second": 18.591, | |
| "eval_steps_per_second": 4.834, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0019573062572634413, | |
| "grad_norm": 1.0080630779266357, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5587, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002935959385895162, | |
| "grad_norm": 0.9608753323554993, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.6122, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0039146125145268825, | |
| "grad_norm": 0.6398207545280457, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.4608, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004893265643158603, | |
| "grad_norm": 0.5527761578559875, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.5155, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005871918771790324, | |
| "grad_norm": 0.893443763256073, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.4791, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006850571900422044, | |
| "grad_norm": 0.6713712215423584, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.4671, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007829225029053765, | |
| "grad_norm": 0.49785712361335754, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.4463, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008807878157685486, | |
| "grad_norm": 0.4845285713672638, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.4611, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009786531286317205, | |
| "grad_norm": 0.5214321613311768, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.4473, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010765184414948926, | |
| "grad_norm": 0.53846275806427, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.3884, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.011743837543580648, | |
| "grad_norm": 0.6865140795707703, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.3446, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.012722490672212369, | |
| "grad_norm": 0.5346219539642334, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.198, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.013701143800844088, | |
| "grad_norm": 0.6182193756103516, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.3342, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.014679796929475809, | |
| "grad_norm": 0.46032652258872986, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.298, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01565845005810753, | |
| "grad_norm": 0.3307320475578308, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 2.2378, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01663710318673925, | |
| "grad_norm": 0.26941177248954773, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 2.3683, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.017615756315370972, | |
| "grad_norm": 0.2807510793209076, | |
| "learning_rate": 7.75e-05, | |
| "loss": 2.3843, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01859440944400269, | |
| "grad_norm": 0.33372122049331665, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 2.3049, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01957306257263441, | |
| "grad_norm": 0.3496776521205902, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 2.3267, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.020551715701266134, | |
| "grad_norm": 0.38420557975769043, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 2.3582, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.021530368829897853, | |
| "grad_norm": 0.4269815683364868, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 2.3467, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.022509021958529572, | |
| "grad_norm": 0.45104503631591797, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 2.3472, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.023487675087161295, | |
| "grad_norm": 0.44177213311195374, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 2.3087, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.024466328215793014, | |
| "grad_norm": 0.565604567527771, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 2.4263, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.024466328215793014, | |
| "eval_loss": 2.4111673831939697, | |
| "eval_runtime": 2.0329, | |
| "eval_samples_per_second": 24.595, | |
| "eval_steps_per_second": 6.395, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.025444981344424737, | |
| "grad_norm": 0.1908201426267624, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.186, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.026423634473056457, | |
| "grad_norm": 0.23226866126060486, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 2.2756, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.027402287601688176, | |
| "grad_norm": 0.2683747410774231, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 2.3146, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0283809407303199, | |
| "grad_norm": 0.295396089553833, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 2.3337, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.029359593858951618, | |
| "grad_norm": 0.3223787546157837, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 2.2585, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.030338246987583337, | |
| "grad_norm": 0.3190826177597046, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 2.2912, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03131690011621506, | |
| "grad_norm": 0.33541804552078247, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 2.2797, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.03229555324484678, | |
| "grad_norm": 0.31905463337898254, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 2.3301, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0332742063734785, | |
| "grad_norm": 0.3051736354827881, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 2.3091, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03425285950211022, | |
| "grad_norm": 0.3700856566429138, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 2.3587, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.035231512630741944, | |
| "grad_norm": 0.3710134029388428, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 2.2941, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.036210165759373664, | |
| "grad_norm": 0.42295482754707336, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 2.3233, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.03718881888800538, | |
| "grad_norm": 0.18501313030719757, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 2.1554, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0381674720166371, | |
| "grad_norm": 0.1772017776966095, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 2.2334, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03914612514526882, | |
| "grad_norm": 0.19991019368171692, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 2.269, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04012477827390054, | |
| "grad_norm": 0.23480480909347534, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 2.2437, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.04110343140253227, | |
| "grad_norm": 0.22680670022964478, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 2.2303, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.04208208453116399, | |
| "grad_norm": 0.24856442213058472, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 2.3045, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.043060737659795706, | |
| "grad_norm": 0.25991547107696533, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 2.2777, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.044039390788427425, | |
| "grad_norm": 0.2713627219200134, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 2.2902, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.045018043917059145, | |
| "grad_norm": 0.28513380885124207, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 2.2732, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.04599669704569087, | |
| "grad_norm": 0.31669914722442627, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 2.3142, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.04697535017432259, | |
| "grad_norm": 0.37770146131515503, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 2.3571, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.04795400330295431, | |
| "grad_norm": 0.3908044695854187, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 2.2915, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.04893265643158603, | |
| "grad_norm": 0.4706682562828064, | |
| "learning_rate": 1e-05, | |
| "loss": 2.2868, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04893265643158603, | |
| "eval_loss": 2.397162914276123, | |
| "eval_runtime": 2.0287, | |
| "eval_samples_per_second": 24.647, | |
| "eval_steps_per_second": 6.408, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.969948642440643e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |