| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.041036717062635, | |
| "eval_steps": 25, | |
| "global_step": 44, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06911447084233262, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06911447084233262, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.9974, | |
| "eval_samples_per_second": 25.033, | |
| "eval_steps_per_second": 6.508, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.13822894168466524, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.20734341252699784, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.987417087315311e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.27645788336933047, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.949738718013078e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.34557235421166305, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.887175604818206e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.4146868250539957, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.800077626037634e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.4838012958963283, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.688931868898919e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5529157667386609, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.554359905560886e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6220302375809935, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.6911447084233261, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.218074484421978e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7602591792656588, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.018241671106134e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.8293736501079914, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.798733423234218e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8984881209503239, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.560777319969136e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.9676025917926566, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.305704108364301e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.0367170626349893, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.034940261286298e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.1058315334773219, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.1749460043196545, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.452476826029011e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.244060475161987, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.14403460964878e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.3131749460043196, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.82639828484907e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.3822894168466522, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.501344202803414e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.451403887688985, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.170690197792785e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.5205183585313176, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.83628542113891e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.5896328293736501, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.6587473002159827, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.163714578861091e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.7278617710583153, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.829309802207215e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.7278617710583153, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0022, | |
| "eval_samples_per_second": 24.973, | |
| "eval_steps_per_second": 6.493, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.7969762419006479, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.498655797196586e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.8660907127429804, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.173601715150931e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.935205183585313, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8559653903512224e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.0043196544276456, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.547523173970989e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.0734341252699786, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.142548596112311, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9650597387137014e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.2116630669546438, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6942958916356998e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.2807775377969763, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4392226800308622e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.349892008639309, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2012665767657826e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.4190064794816415, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.981758328893866e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.488120950323974, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.781925515578024e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.5572354211663066, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.626349892008639, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4456400944391146e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.695464362850972, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3110681311010814e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.7645788336933044, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1999223739623667e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.833693304535637, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1128243951817937e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.90280777537797, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0502612819869217e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.971922246220302, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0125829126846895e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 3.041036717062635, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 44, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 9.32391991419863e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |