| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 25, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 1.7322526846695911, |
| "learning_rate": 3.979642883761866e-05, |
| "loss": 0.7335, |
| "loss_nan_ranks": 0, |
| "loss_rank_avg": 0.1319078654050827, |
| "step": 5, |
| "valid_targets_mean": 3753.4, |
| "valid_targets_min": 949 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.6096692490454981, |
| "learning_rate": 3.309721467890571e-05, |
| "loss": 0.6164, |
| "loss_nan_ranks": 0, |
| "loss_rank_avg": 0.13100628554821014, |
| "step": 10, |
| "valid_targets_mean": 3684.0, |
| "valid_targets_min": 569 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.4279329965930942, |
| "learning_rate": 2e-05, |
| "loss": 0.5735, |
| "loss_nan_ranks": 0, |
| "loss_rank_avg": 0.1547342836856842, |
| "step": 15, |
| "valid_targets_mean": 4793.8, |
| "valid_targets_min": 1376 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.3280390446220114, |
| "learning_rate": 6.902785321094301e-06, |
| "loss": 0.548, |
| "loss_nan_ranks": 0, |
| "loss_rank_avg": 0.14000384509563446, |
| "step": 20, |
| "valid_targets_mean": 4282.3, |
| "valid_targets_min": 853 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.3127396964330603, |
| "learning_rate": 2.0357116238134633e-07, |
| "loss": 0.5415, |
| "loss_nan_ranks": 0, |
| "loss_rank_avg": 0.13704220950603485, |
| "step": 25, |
| "valid_targets_mean": 4015.5, |
| "valid_targets_min": 740 |
| }, |
| { |
| "epoch": 5.0, |
| "loss_nan_ranks": 0, |
| "loss_rank_avg": 0.13704220950603485, |
| "step": 25, |
| "total_flos": 4.222945955781018e+16, |
| "train_loss": 0.6025812339782715, |
| "train_runtime": 546.5421, |
| "train_samples_per_second": 2.891, |
| "train_steps_per_second": 0.046, |
| "valid_targets_mean": 4015.5, |
| "valid_targets_min": 740 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 25, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": false, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.222945955781018e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
