| { | |
| "best_metric": 10.337969779968262, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.01379690949227373, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002759381898454746, | |
| "grad_norm": 0.7854787707328796, | |
| "learning_rate": 2e-05, | |
| "loss": 41.5156, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002759381898454746, | |
| "eval_loss": 10.377832412719727, | |
| "eval_runtime": 10.0369, | |
| "eval_samples_per_second": 608.159, | |
| "eval_steps_per_second": 76.02, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005518763796909492, | |
| "grad_norm": 0.7835937142372131, | |
| "learning_rate": 4e-05, | |
| "loss": 41.5171, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008278145695364238, | |
| "grad_norm": 0.6889204978942871, | |
| "learning_rate": 6e-05, | |
| "loss": 41.5131, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011037527593818985, | |
| "grad_norm": 0.7042638659477234, | |
| "learning_rate": 8e-05, | |
| "loss": 41.5141, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0013796909492273732, | |
| "grad_norm": 0.6951324939727783, | |
| "learning_rate": 0.0001, | |
| "loss": 41.5098, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016556291390728477, | |
| "grad_norm": 0.6777766942977905, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 41.505, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0019315673289183224, | |
| "grad_norm": 0.8211271166801453, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 41.4827, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002207505518763797, | |
| "grad_norm": 0.8304107189178467, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 41.4976, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0024834437086092716, | |
| "grad_norm": 0.8473355174064636, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 41.4832, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0027593818984547464, | |
| "grad_norm": 0.8748414516448975, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 41.4754, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0030353200883002206, | |
| "grad_norm": 0.7247818112373352, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 41.493, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0033112582781456954, | |
| "grad_norm": 0.8492615818977356, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 41.4772, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00358719646799117, | |
| "grad_norm": 0.9790228605270386, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 41.4824, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003863134657836645, | |
| "grad_norm": 0.9517574310302734, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 41.4685, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0041390728476821195, | |
| "grad_norm": 1.0385410785675049, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 41.4702, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004415011037527594, | |
| "grad_norm": 1.0945062637329102, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 41.4524, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004690949227373068, | |
| "grad_norm": 1.1814308166503906, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 41.4478, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004966887417218543, | |
| "grad_norm": 1.359357476234436, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 41.4397, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0052428256070640175, | |
| "grad_norm": 1.34695565700531, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 41.433, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.005518763796909493, | |
| "grad_norm": 1.2304890155792236, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 41.4341, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005794701986754967, | |
| "grad_norm": 1.1841272115707397, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 41.4414, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006070640176600441, | |
| "grad_norm": 1.362281322479248, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 41.4325, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0063465783664459164, | |
| "grad_norm": 1.3806591033935547, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 41.429, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006622516556291391, | |
| "grad_norm": 1.485974907875061, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 41.4122, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006898454746136865, | |
| "grad_norm": 1.4396660327911377, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 41.4154, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006898454746136865, | |
| "eval_loss": 10.35084342956543, | |
| "eval_runtime": 10.0816, | |
| "eval_samples_per_second": 605.461, | |
| "eval_steps_per_second": 75.683, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00717439293598234, | |
| "grad_norm": 1.611414909362793, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 41.407, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0074503311258278145, | |
| "grad_norm": 1.6409019231796265, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 41.3963, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00772626931567329, | |
| "grad_norm": 1.5699679851531982, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 41.3951, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.008002207505518763, | |
| "grad_norm": 1.6396316289901733, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 41.3885, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.008278145695364239, | |
| "grad_norm": 1.6167317628860474, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 41.3895, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008554083885209713, | |
| "grad_norm": 1.7325376272201538, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 41.3668, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.008830022075055188, | |
| "grad_norm": 1.465965986251831, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 41.372, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.009105960264900662, | |
| "grad_norm": 1.48931884765625, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 41.3638, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.009381898454746136, | |
| "grad_norm": 1.526735782623291, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 41.3626, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.009657836644591612, | |
| "grad_norm": 1.6789668798446655, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 41.3546, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.009933774834437087, | |
| "grad_norm": 1.4913084506988525, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 41.347, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01020971302428256, | |
| "grad_norm": 1.4911720752716064, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 41.3674, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.010485651214128035, | |
| "grad_norm": 1.5095301866531372, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 41.3685, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.01076158940397351, | |
| "grad_norm": 1.401106357574463, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 41.374, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.011037527593818985, | |
| "grad_norm": 1.4282902479171753, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 41.3633, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01131346578366446, | |
| "grad_norm": 1.5233620405197144, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 41.3372, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.011589403973509934, | |
| "grad_norm": 1.521764874458313, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 41.3368, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.011865342163355408, | |
| "grad_norm": 1.5868169069290161, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 41.3614, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.012141280353200883, | |
| "grad_norm": 1.4296141862869263, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 41.3517, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.012417218543046357, | |
| "grad_norm": 1.431632161140442, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 41.3548, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.012693156732891833, | |
| "grad_norm": 1.5977118015289307, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 41.3662, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.012969094922737307, | |
| "grad_norm": 1.4877045154571533, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 41.3298, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.013245033112582781, | |
| "grad_norm": 1.7337113618850708, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 41.3669, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.013520971302428256, | |
| "grad_norm": 1.775262475013733, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 41.3547, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.01379690949227373, | |
| "grad_norm": 2.36063289642334, | |
| "learning_rate": 0.0, | |
| "loss": 41.3447, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01379690949227373, | |
| "eval_loss": 10.337969779968262, | |
| "eval_runtime": 10.0528, | |
| "eval_samples_per_second": 607.196, | |
| "eval_steps_per_second": 75.9, | |
| "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": 5, | |
| "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": 8726623027200.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |