| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0008680781617576847, |
| "eval_steps": 10, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.7361563235153692e-05, |
| "eval_loss": 3.2406625747680664, |
| "eval_runtime": 1579.9553, |
| "eval_samples_per_second": 15.35, |
| "eval_steps_per_second": 7.675, |
| "step": 1 |
| }, |
| { |
| "epoch": 8.680781617576846e-05, |
| "grad_norm": 56.969181060791016, |
| "learning_rate": 5e-05, |
| "loss": 12.0664, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.00017361563235153692, |
| "grad_norm": 48.02027130126953, |
| "learning_rate": 0.0001, |
| "loss": 8.5399, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.00017361563235153692, |
| "eval_loss": 1.7465617656707764, |
| "eval_runtime": 1583.1765, |
| "eval_samples_per_second": 15.319, |
| "eval_steps_per_second": 7.659, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0002604234485273054, |
| "grad_norm": 24.002090454101562, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 6.8368, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.00034723126470307384, |
| "grad_norm": 22.417949676513672, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 6.5063, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.00034723126470307384, |
| "eval_loss": 1.3497487306594849, |
| "eval_runtime": 1582.5355, |
| "eval_samples_per_second": 15.325, |
| "eval_steps_per_second": 7.662, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.00043403908087884236, |
| "grad_norm": 26.679052352905273, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 5.296, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.0005208468970546108, |
| "grad_norm": 23.542726516723633, |
| "learning_rate": 5e-05, |
| "loss": 5.1197, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.0005208468970546108, |
| "eval_loss": 1.267897367477417, |
| "eval_runtime": 1579.6304, |
| "eval_samples_per_second": 15.353, |
| "eval_steps_per_second": 7.676, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.0006076547132303793, |
| "grad_norm": 19.179880142211914, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 4.7048, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.0006944625294061477, |
| "grad_norm": 19.000234603881836, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 5.4107, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.0006944625294061477, |
| "eval_loss": 1.2511236667633057, |
| "eval_runtime": 1584.0605, |
| "eval_samples_per_second": 15.31, |
| "eval_steps_per_second": 7.655, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.0007812703455819162, |
| "grad_norm": 22.011131286621094, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 5.3537, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.0008680781617576847, |
| "grad_norm": 17.464994430541992, |
| "learning_rate": 0.0, |
| "loss": 4.3659, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.0008680781617576847, |
| "eval_loss": 1.2439897060394287, |
| "eval_runtime": 1587.0763, |
| "eval_samples_per_second": 15.281, |
| "eval_steps_per_second": 7.64, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 50, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 13, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 8763509991014400.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
