| { | |
| "best_metric": 0.7782544493675232, | |
| "best_model_checkpoint": "D:\\illuminus_bot\\models\\checkpoint-150", | |
| "epoch": 3.0, | |
| "eval_steps": 10, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 2.298717737197876, | |
| "eval_runtime": 3.0303, | |
| "eval_samples_per_second": 9.9, | |
| "eval_steps_per_second": 1.32, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.898303747177124, | |
| "eval_runtime": 1.7196, | |
| "eval_samples_per_second": 17.446, | |
| "eval_steps_per_second": 2.326, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.2992270290851593, | |
| "learning_rate": 0.00019075754196709572, | |
| "loss": 2.342, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.4412014484405518, | |
| "eval_runtime": 2.3282, | |
| "eval_samples_per_second": 12.886, | |
| "eval_steps_per_second": 1.718, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.1243364810943604, | |
| "eval_runtime": 1.6919, | |
| "eval_samples_per_second": 17.732, | |
| "eval_steps_per_second": 2.364, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.4127086102962494, | |
| "learning_rate": 0.00015611870653623825, | |
| "loss": 1.2512, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.0006705522537231, | |
| "eval_runtime": 1.6939, | |
| "eval_samples_per_second": 17.71, | |
| "eval_steps_per_second": 2.361, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 0.9261489510536194, | |
| "eval_runtime": 1.6971, | |
| "eval_samples_per_second": 17.677, | |
| "eval_steps_per_second": 2.357, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_loss": 0.875005841255188, | |
| "eval_runtime": 1.7176, | |
| "eval_samples_per_second": 17.467, | |
| "eval_steps_per_second": 2.329, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.37045156955718994, | |
| "learning_rate": 0.00010541389085854176, | |
| "loss": 0.9112, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 0.8470792770385742, | |
| "eval_runtime": 1.7055, | |
| "eval_samples_per_second": 17.591, | |
| "eval_steps_per_second": 2.345, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 0.8251746296882629, | |
| "eval_runtime": 1.709, | |
| "eval_samples_per_second": 17.554, | |
| "eval_steps_per_second": 2.341, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.3344666361808777, | |
| "learning_rate": 5.3159155930021e-05, | |
| "loss": 0.8194, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.8055851459503174, | |
| "eval_runtime": 1.7151, | |
| "eval_samples_per_second": 17.492, | |
| "eval_steps_per_second": 2.332, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_loss": 0.7922044396400452, | |
| "eval_runtime": 2.5303, | |
| "eval_samples_per_second": 11.856, | |
| "eval_steps_per_second": 1.581, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 0.7848032712936401, | |
| "eval_runtime": 1.7215, | |
| "eval_samples_per_second": 17.426, | |
| "eval_steps_per_second": 2.324, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 0.3872661292552948, | |
| "learning_rate": 1.4314282383241096e-05, | |
| "loss": 0.76, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "eval_loss": 0.7804359793663025, | |
| "eval_runtime": 1.7004, | |
| "eval_samples_per_second": 17.643, | |
| "eval_steps_per_second": 2.352, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 0.7785606980323792, | |
| "eval_runtime": 1.6951, | |
| "eval_samples_per_second": 17.699, | |
| "eval_steps_per_second": 2.36, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.3779631555080414, | |
| "learning_rate": 0.0, | |
| "loss": 0.7537, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.7782544493675232, | |
| "eval_runtime": 1.7693, | |
| "eval_samples_per_second": 16.956, | |
| "eval_steps_per_second": 2.261, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 150, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 0, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7772716744704000.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |