| { | |
| "best_metric": 0.250135213136673, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.4294149221685454, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008588298443370907, | |
| "grad_norm": 7.55905294418335, | |
| "learning_rate": 5e-05, | |
| "loss": 9.1199, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008588298443370907, | |
| "eval_loss": 9.081170082092285, | |
| "eval_runtime": 2.5395, | |
| "eval_samples_per_second": 19.689, | |
| "eval_steps_per_second": 5.119, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017176596886741814, | |
| "grad_norm": 7.514353275299072, | |
| "learning_rate": 0.0001, | |
| "loss": 8.8054, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02576489533011272, | |
| "grad_norm": 7.8171467781066895, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 8.7824, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03435319377348363, | |
| "grad_norm": 7.417876243591309, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 6.9901, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04294149221685454, | |
| "grad_norm": 6.940496444702148, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 5.0434, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05152979066022544, | |
| "grad_norm": 5.353168487548828, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 4.0804, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06011808910359635, | |
| "grad_norm": 4.561730861663818, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 3.0291, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06870638754696726, | |
| "grad_norm": 4.618034362792969, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.4864, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07729468599033816, | |
| "grad_norm": 3.445601463317871, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.7061, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08588298443370908, | |
| "grad_norm": 2.718672752380371, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.0334, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09447128287707998, | |
| "grad_norm": 2.2221052646636963, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.87, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10305958132045089, | |
| "grad_norm": 2.8456015586853027, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.8587, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11164787976382179, | |
| "grad_norm": 3.1550638675689697, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.7196, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1202361782071927, | |
| "grad_norm": 2.76228928565979, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.4587, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1288244766505636, | |
| "grad_norm": 2.384809732437134, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.3835, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1374127750939345, | |
| "grad_norm": 2.198056936264038, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.3717, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.14600107353730543, | |
| "grad_norm": 3.1217353343963623, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.3326, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.15458937198067632, | |
| "grad_norm": 1.242319941520691, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.2944, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.16317767042404724, | |
| "grad_norm": 4.2636613845825195, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.3544, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.17176596886741816, | |
| "grad_norm": 2.7467615604400635, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.3021, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18035426731078905, | |
| "grad_norm": 1.0115433931350708, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.3188, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.18894256575415996, | |
| "grad_norm": 1.282575249671936, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.3169, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 0.8947703242301941, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.3382, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.20611916264090177, | |
| "grad_norm": 0.7449538111686707, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.3761, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2147074610842727, | |
| "grad_norm": 1.1275854110717773, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.3411, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2147074610842727, | |
| "eval_loss": 0.3024834394454956, | |
| "eval_runtime": 1.9145, | |
| "eval_samples_per_second": 26.116, | |
| "eval_steps_per_second": 6.79, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22329575952764358, | |
| "grad_norm": 1.5792282819747925, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.3402, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2318840579710145, | |
| "grad_norm": 1.05101478099823, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.3257, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2404723564143854, | |
| "grad_norm": 1.035786747932434, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.3294, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2490606548577563, | |
| "grad_norm": 1.0826724767684937, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.3104, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2576489533011272, | |
| "grad_norm": 0.639144778251648, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.3057, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.26623725174449814, | |
| "grad_norm": 0.630906343460083, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.278, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.274825550187869, | |
| "grad_norm": 1.115294337272644, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.2595, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2834138486312399, | |
| "grad_norm": 0.47555750608444214, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.2681, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.29200214707461086, | |
| "grad_norm": 0.9514725804328918, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.3414, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.30059044551798175, | |
| "grad_norm": 0.8921436071395874, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.2927, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.30917874396135264, | |
| "grad_norm": 1.4115748405456543, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.3358, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3177670424047236, | |
| "grad_norm": 1.133245587348938, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.3453, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3263553408480945, | |
| "grad_norm": 1.1106758117675781, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.318, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.33494363929146537, | |
| "grad_norm": 1.7452747821807861, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.3193, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3435319377348363, | |
| "grad_norm": 1.925551176071167, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.3473, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3521202361782072, | |
| "grad_norm": 0.773165762424469, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.2916, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3607085346215781, | |
| "grad_norm": 0.8585931062698364, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.3026, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.369296833064949, | |
| "grad_norm": 0.44937247037887573, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.2761, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3778851315083199, | |
| "grad_norm": 0.7727624773979187, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.3183, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3864734299516908, | |
| "grad_norm": 0.6559286713600159, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.285, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "grad_norm": 0.5505415201187134, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.2792, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.40365002683843265, | |
| "grad_norm": 0.9058887958526611, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.2909, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.41223832528180354, | |
| "grad_norm": 0.9981274008750916, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.3462, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.42082662372517443, | |
| "grad_norm": 1.426024079322815, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.385, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4294149221685454, | |
| "grad_norm": 0.8514761328697205, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3346, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4294149221685454, | |
| "eval_loss": 0.250135213136673, | |
| "eval_runtime": 1.9284, | |
| "eval_samples_per_second": 25.928, | |
| "eval_steps_per_second": 6.741, | |
| "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": 5.32019209568256e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |