| { | |
| "best_metric": 1.1180486679077148, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.03682563063892469, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003682563063892469, | |
| "eval_loss": 2.228027582168579, | |
| "eval_runtime": 105.1707, | |
| "eval_samples_per_second": 10.878, | |
| "eval_steps_per_second": 2.719, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0036825630638924692, | |
| "grad_norm": 3.64420485496521, | |
| "learning_rate": 4.0600000000000004e-05, | |
| "loss": 4.2977, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0073651261277849385, | |
| "grad_norm": 1.8111019134521484, | |
| "learning_rate": 8.120000000000001e-05, | |
| "loss": 3.6581, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011047689191677408, | |
| "grad_norm": 2.067847728729248, | |
| "learning_rate": 0.00012179999999999999, | |
| "loss": 3.1829, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014730252255569877, | |
| "grad_norm": 1.6672817468643188, | |
| "learning_rate": 0.00016240000000000002, | |
| "loss": 2.8307, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.018412815319462345, | |
| "grad_norm": 1.8722939491271973, | |
| "learning_rate": 0.000203, | |
| "loss": 2.597, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.018412815319462345, | |
| "eval_loss": 1.3078378438949585, | |
| "eval_runtime": 104.9597, | |
| "eval_samples_per_second": 10.899, | |
| "eval_steps_per_second": 2.725, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.022095378383354815, | |
| "grad_norm": 1.3702597618103027, | |
| "learning_rate": 0.00020275275110137215, | |
| "loss": 2.5237, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.025777941447247283, | |
| "grad_norm": 1.518210768699646, | |
| "learning_rate": 0.00020201220897726938, | |
| "loss": 2.4878, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.029460504511139754, | |
| "grad_norm": 1.3466520309448242, | |
| "learning_rate": 0.00020078198147448128, | |
| "loss": 2.3046, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.03314306757503222, | |
| "grad_norm": 1.2383614778518677, | |
| "learning_rate": 0.00019906806213773937, | |
| "loss": 2.3387, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.03682563063892469, | |
| "grad_norm": 1.4980638027191162, | |
| "learning_rate": 0.0001968788010097697, | |
| "loss": 2.0506, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03682563063892469, | |
| "eval_loss": 1.1180486679077148, | |
| "eval_runtime": 105.0543, | |
| "eval_samples_per_second": 10.89, | |
| "eval_steps_per_second": 2.722, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.026877886444339e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |