| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0006483717763765744, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00012967435527531487, | |
| "grad_norm": 1.1431047916412354, | |
| "learning_rate": 1e-05, | |
| "loss": 1.7935, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00012967435527531487, | |
| "eval_loss": 1.8209973573684692, | |
| "eval_runtime": 521.3515, | |
| "eval_samples_per_second": 24.912, | |
| "eval_steps_per_second": 12.456, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00025934871055062974, | |
| "grad_norm": 1.130334496498108, | |
| "learning_rate": 2e-05, | |
| "loss": 1.6793, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00025934871055062974, | |
| "eval_loss": 1.8031895160675049, | |
| "eval_runtime": 450.2468, | |
| "eval_samples_per_second": 28.846, | |
| "eval_steps_per_second": 14.423, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0003890230658259446, | |
| "grad_norm": 1.1945505142211914, | |
| "learning_rate": 3e-05, | |
| "loss": 1.9287, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005186974211012595, | |
| "grad_norm": 1.2244787216186523, | |
| "learning_rate": 4e-05, | |
| "loss": 1.6216, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0005186974211012595, | |
| "eval_loss": 1.7570958137512207, | |
| "eval_runtime": 505.6656, | |
| "eval_samples_per_second": 25.685, | |
| "eval_steps_per_second": 12.842, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0006483717763765744, | |
| "grad_norm": 1.231426477432251, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6159, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5398833250959360.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |