| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002055287226389888, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002055287226389888, | |
| "grad_norm": 18.38691520690918, | |
| "learning_rate": 2e-05, | |
| "loss": 20.7071, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002055287226389888, | |
| "eval_loss": 5.155397891998291, | |
| "eval_runtime": 61.0259, | |
| "eval_samples_per_second": 33.576, | |
| "eval_steps_per_second": 16.796, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004110574452779776, | |
| "grad_norm": 18.949068069458008, | |
| "learning_rate": 4e-05, | |
| "loss": 20.2608, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006165861679169664, | |
| "grad_norm": 19.084632873535156, | |
| "learning_rate": 6e-05, | |
| "loss": 20.6069, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006165861679169664, | |
| "eval_loss": 5.114022254943848, | |
| "eval_runtime": 59.8915, | |
| "eval_samples_per_second": 34.212, | |
| "eval_steps_per_second": 17.114, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008221148905559552, | |
| "grad_norm": 19.072351455688477, | |
| "learning_rate": 8e-05, | |
| "loss": 19.5259, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001027643613194944, | |
| "grad_norm": 19.643707275390625, | |
| "learning_rate": 0.0001, | |
| "loss": 22.0196, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0012331723358339328, | |
| "grad_norm": 22.42145347595215, | |
| "learning_rate": 0.00012, | |
| "loss": 20.3694, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0012331723358339328, | |
| "eval_loss": 4.786177158355713, | |
| "eval_runtime": 60.0719, | |
| "eval_samples_per_second": 34.109, | |
| "eval_steps_per_second": 17.063, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0014387010584729215, | |
| "grad_norm": 19.99371910095215, | |
| "learning_rate": 0.00014, | |
| "loss": 19.0668, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0016442297811119105, | |
| "grad_norm": 18.28893280029297, | |
| "learning_rate": 0.00016, | |
| "loss": 16.4857, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0018497585037508992, | |
| "grad_norm": 23.7630672454834, | |
| "learning_rate": 0.00018, | |
| "loss": 19.2521, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0018497585037508992, | |
| "eval_loss": 3.8478376865386963, | |
| "eval_runtime": 60.0903, | |
| "eval_samples_per_second": 34.099, | |
| "eval_steps_per_second": 17.058, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002055287226389888, | |
| "grad_norm": 21.88700294494629, | |
| "learning_rate": 0.0002, | |
| "loss": 16.219, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1305898647552000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |