| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.022050716648291068, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011025358324145535, | |
| "grad_norm": 0.9616879224777222, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7729, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011025358324145535, | |
| "eval_loss": NaN, | |
| "eval_runtime": 54.0175, | |
| "eval_samples_per_second": 7.072, | |
| "eval_steps_per_second": 3.536, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002205071664829107, | |
| "grad_norm": 0.9806817173957825, | |
| "learning_rate": 4e-05, | |
| "loss": 1.7726, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0033076074972436605, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 1.5169, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004410143329658214, | |
| "grad_norm": 0.9089802503585815, | |
| "learning_rate": 8e-05, | |
| "loss": 1.7227, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005512679162072767, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3213, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005512679162072767, | |
| "eval_loss": NaN, | |
| "eval_runtime": 52.4748, | |
| "eval_samples_per_second": 7.28, | |
| "eval_steps_per_second": 3.64, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006615214994487321, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 1.0191, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007717750826901874, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 1.6653, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008820286659316428, | |
| "grad_norm": 1.0089209079742432, | |
| "learning_rate": 0.00016, | |
| "loss": 1.565, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009922822491730982, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.8436, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011025358324145534, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4544, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011025358324145534, | |
| "eval_loss": NaN, | |
| "eval_runtime": 53.6986, | |
| "eval_samples_per_second": 7.114, | |
| "eval_steps_per_second": 3.557, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012127894156560088, | |
| "grad_norm": 1.2060033082962036, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 1.7359, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.013230429988974642, | |
| "grad_norm": 1.1315321922302246, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 1.5669, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.014332965821389196, | |
| "grad_norm": 1.1741143465042114, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.606, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.015435501653803748, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 2.3572, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.016538037486218304, | |
| "grad_norm": 0.6324079036712646, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.4557, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.016538037486218304, | |
| "eval_loss": NaN, | |
| "eval_runtime": 53.6318, | |
| "eval_samples_per_second": 7.123, | |
| "eval_steps_per_second": 3.561, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017640573318632856, | |
| "grad_norm": 0.648357093334198, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.5305, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.018743109151047408, | |
| "grad_norm": 0.5638170838356018, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.386, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.019845644983461964, | |
| "grad_norm": 0.7388977408409119, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.3905, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.020948180815876516, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 2.1132, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.022050716648291068, | |
| "grad_norm": 0.5183130502700806, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.3396, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.022050716648291068, | |
| "eval_loss": NaN, | |
| "eval_runtime": 53.1373, | |
| "eval_samples_per_second": 7.189, | |
| "eval_steps_per_second": 3.594, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 2 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2782892182732800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |