| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.03568242640499554, |
| "eval_steps": 10, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0007136485280999108, |
| "eval_loss": 4.1770219802856445, |
| "eval_runtime": 39.0571, |
| "eval_samples_per_second": 15.106, |
| "eval_steps_per_second": 7.553, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.003568242640499554, |
| "grad_norm": 2.147374153137207, |
| "learning_rate": 5e-05, |
| "loss": 4.1219, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.007136485280999108, |
| "grad_norm": 2.610384225845337, |
| "learning_rate": 0.0001, |
| "loss": 3.7342, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.007136485280999108, |
| "eval_loss": 3.428222179412842, |
| "eval_runtime": 39.3068, |
| "eval_samples_per_second": 15.01, |
| "eval_steps_per_second": 7.505, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.010704727921498661, |
| "grad_norm": 2.355562210083008, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 2.7551, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.014272970561998216, |
| "grad_norm": 2.9461042881011963, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 1.8547, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.014272970561998216, |
| "eval_loss": 1.55669105052948, |
| "eval_runtime": 39.3365, |
| "eval_samples_per_second": 14.999, |
| "eval_steps_per_second": 7.499, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.01784121320249777, |
| "grad_norm": 2.520334005355835, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 1.5225, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.021409455842997322, |
| "grad_norm": 2.5305795669555664, |
| "learning_rate": 5e-05, |
| "loss": 1.3177, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.021409455842997322, |
| "eval_loss": 1.2350683212280273, |
| "eval_runtime": 39.4794, |
| "eval_samples_per_second": 14.944, |
| "eval_steps_per_second": 7.472, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.024977698483496878, |
| "grad_norm": 2.365730047225952, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 1.1974, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.028545941123996433, |
| "grad_norm": 1.927002191543579, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 1.1119, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.028545941123996433, |
| "eval_loss": 1.1479406356811523, |
| "eval_runtime": 39.5706, |
| "eval_samples_per_second": 14.91, |
| "eval_steps_per_second": 7.455, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.032114183764495985, |
| "grad_norm": 2.129756450653076, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 1.1849, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.03568242640499554, |
| "grad_norm": 2.1976375579833984, |
| "learning_rate": 0.0, |
| "loss": 1.1207, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.03568242640499554, |
| "eval_loss": 1.1337636709213257, |
| "eval_runtime": 39.4315, |
| "eval_samples_per_second": 14.963, |
| "eval_steps_per_second": 7.481, |
| "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": 9247821240729600.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
