| { | |
| "best_metric": 2.396644353866577, | |
| "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": 0.8639248609542847, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4264, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009786531286317206, | |
| "eval_loss": 2.862811326980591, | |
| "eval_runtime": 3.8273, | |
| "eval_samples_per_second": 13.064, | |
| "eval_steps_per_second": 3.397, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0019573062572634413, | |
| "grad_norm": 0.9601908922195435, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5591, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002935959385895162, | |
| "grad_norm": 0.9256122708320618, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.6103, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0039146125145268825, | |
| "grad_norm": 0.6171367764472961, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.4584, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004893265643158603, | |
| "grad_norm": 0.5734070539474487, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.5139, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005871918771790324, | |
| "grad_norm": 0.8724387288093567, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.4751, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006850571900422044, | |
| "grad_norm": 0.6571186780929565, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.4628, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007829225029053765, | |
| "grad_norm": 0.49470987915992737, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.4433, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008807878157685486, | |
| "grad_norm": 0.48135384917259216, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.4587, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009786531286317205, | |
| "grad_norm": 0.5197238326072693, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.4447, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010765184414948926, | |
| "grad_norm": 0.5565487146377563, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.3875, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.011743837543580648, | |
| "grad_norm": 0.6979668140411377, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.3434, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.012722490672212369, | |
| "grad_norm": 0.5456087589263916, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.1983, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.013701143800844088, | |
| "grad_norm": 0.6193813681602478, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.3342, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.014679796929475809, | |
| "grad_norm": 0.46197935938835144, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.2981, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01565845005810753, | |
| "grad_norm": 0.3292851150035858, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 2.2367, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01663710318673925, | |
| "grad_norm": 0.2769424617290497, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 2.3678, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.017615756315370972, | |
| "grad_norm": 0.2884497344493866, | |
| "learning_rate": 7.75e-05, | |
| "loss": 2.3846, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01859440944400269, | |
| "grad_norm": 0.3412442207336426, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 2.3055, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01957306257263441, | |
| "grad_norm": 0.355741947889328, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 2.327, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.020551715701266134, | |
| "grad_norm": 0.3909011781215668, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 2.3584, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.021530368829897853, | |
| "grad_norm": 0.43203940987586975, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 2.3477, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.022509021958529572, | |
| "grad_norm": 0.4551961123943329, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 2.3487, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.023487675087161295, | |
| "grad_norm": 0.4476655125617981, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 2.3101, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.024466328215793014, | |
| "grad_norm": 0.569807231426239, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 2.4272, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.024466328215793014, | |
| "eval_loss": 2.410325527191162, | |
| "eval_runtime": 3.4749, | |
| "eval_samples_per_second": 14.389, | |
| "eval_steps_per_second": 3.741, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.025444981344424737, | |
| "grad_norm": 0.19889217615127563, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.1861, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.026423634473056457, | |
| "grad_norm": 0.24287927150726318, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 2.2757, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.027402287601688176, | |
| "grad_norm": 0.2795593738555908, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 2.3154, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0283809407303199, | |
| "grad_norm": 0.307158499956131, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 2.3342, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.029359593858951618, | |
| "grad_norm": 0.3302345871925354, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 2.2589, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.030338246987583337, | |
| "grad_norm": 0.31997916102409363, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 2.291, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03131690011621506, | |
| "grad_norm": 0.34045863151550293, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 2.2796, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.03229555324484678, | |
| "grad_norm": 0.3185667395591736, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 2.33, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0332742063734785, | |
| "grad_norm": 0.3068499267101288, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 2.3097, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03425285950211022, | |
| "grad_norm": 0.3778265118598938, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 2.3589, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.035231512630741944, | |
| "grad_norm": 0.3738100826740265, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 2.2939, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.036210165759373664, | |
| "grad_norm": 0.42966437339782715, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 2.3238, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.03718881888800538, | |
| "grad_norm": 0.18900859355926514, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 2.156, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0381674720166371, | |
| "grad_norm": 0.18164923787117004, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 2.2335, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03914612514526882, | |
| "grad_norm": 0.2060445249080658, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 2.2695, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04012477827390054, | |
| "grad_norm": 0.2239447981119156, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 2.2437, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.04110343140253227, | |
| "grad_norm": 0.23141714930534363, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 2.2309, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.04208208453116399, | |
| "grad_norm": 0.2500653862953186, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 2.3043, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.043060737659795706, | |
| "grad_norm": 0.25972434878349304, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 2.2783, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.044039390788427425, | |
| "grad_norm": 0.2742820084095001, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 2.2897, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.045018043917059145, | |
| "grad_norm": 0.2878837585449219, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 2.2736, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.04599669704569087, | |
| "grad_norm": 0.32029470801353455, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 2.3139, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.04697535017432259, | |
| "grad_norm": 0.37453824281692505, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 2.3575, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.04795400330295431, | |
| "grad_norm": 0.38911765813827515, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 2.2911, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.04893265643158603, | |
| "grad_norm": 0.4732091724872589, | |
| "learning_rate": 1e-05, | |
| "loss": 2.2883, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04893265643158603, | |
| "eval_loss": 2.396644353866577, | |
| "eval_runtime": 3.4758, | |
| "eval_samples_per_second": 14.385, | |
| "eval_steps_per_second": 3.74, | |
| "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 | |
| } | |