| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0033685156074556477, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00011228385358185493, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 36.9861, | |
| "eval_samples_per_second": 101.389, | |
| "eval_steps_per_second": 50.695, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00033685156074556477, | |
| "grad_norm": 1.857743518485222e-05, | |
| "learning_rate": 3e-05, | |
| "loss": 46.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006737031214911295, | |
| "grad_norm": 1.1584648746065795e-05, | |
| "learning_rate": 6e-05, | |
| "loss": 46.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0008982708286548395, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 36.8996, | |
| "eval_samples_per_second": 101.627, | |
| "eval_steps_per_second": 50.813, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0010105546822366943, | |
| "grad_norm": 1.5065967090777121e-05, | |
| "learning_rate": 9e-05, | |
| "loss": 46.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001347406242982259, | |
| "grad_norm": 1.5385758160846308e-05, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 46.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0016842578037278239, | |
| "grad_norm": 9.523390872345772e-06, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 46.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.001796541657309679, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 37.1694, | |
| "eval_samples_per_second": 100.889, | |
| "eval_steps_per_second": 50.445, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0020211093644733886, | |
| "grad_norm": 1.3232111996330786e-05, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 46.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0023579609252189536, | |
| "grad_norm": 1.4776323041587602e-05, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 46.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.002694812485964518, | |
| "grad_norm": 1.4560354429704603e-05, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 46.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.002694812485964518, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 37.1229, | |
| "eval_samples_per_second": 101.016, | |
| "eval_steps_per_second": 50.508, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003031664046710083, | |
| "grad_norm": 2.0876279450021684e-05, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 46.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0033685156074556477, | |
| "grad_norm": 1.5224530216073617e-05, | |
| "learning_rate": 0.0, | |
| "loss": 46.0, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1206856679424.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |