| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.057803468208092484, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011560693641618498, | |
| "eval_loss": 5.359778881072998, | |
| "eval_runtime": 14.3601, | |
| "eval_samples_per_second": 25.418, | |
| "eval_steps_per_second": 12.744, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005780346820809248, | |
| "grad_norm": 7.12149715423584, | |
| "learning_rate": 5e-05, | |
| "loss": 5.0646, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.011560693641618497, | |
| "grad_norm": 7.830906391143799, | |
| "learning_rate": 0.0001, | |
| "loss": 4.5362, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011560693641618497, | |
| "eval_loss": 4.520800590515137, | |
| "eval_runtime": 12.3117, | |
| "eval_samples_per_second": 29.647, | |
| "eval_steps_per_second": 14.864, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.017341040462427744, | |
| "grad_norm": 6.524648666381836, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.8531, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.023121387283236993, | |
| "grad_norm": 5.788236141204834, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.0813, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.023121387283236993, | |
| "eval_loss": 3.173112392425537, | |
| "eval_runtime": 12.4689, | |
| "eval_samples_per_second": 29.273, | |
| "eval_steps_per_second": 14.677, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.028901734104046242, | |
| "grad_norm": 6.4477219581604, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.755, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03468208092485549, | |
| "grad_norm": 6.973568916320801, | |
| "learning_rate": 5e-05, | |
| "loss": 2.6833, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03468208092485549, | |
| "eval_loss": 2.8336453437805176, | |
| "eval_runtime": 12.4217, | |
| "eval_samples_per_second": 29.384, | |
| "eval_steps_per_second": 14.732, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04046242774566474, | |
| "grad_norm": 7.072249412536621, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.6773, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.046242774566473986, | |
| "grad_norm": 6.697601795196533, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.965, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.046242774566473986, | |
| "eval_loss": 2.7534990310668945, | |
| "eval_runtime": 12.5619, | |
| "eval_samples_per_second": 29.056, | |
| "eval_steps_per_second": 14.568, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05202312138728324, | |
| "grad_norm": 7.272146701812744, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.6608, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.057803468208092484, | |
| "grad_norm": 7.5973663330078125, | |
| "learning_rate": 0.0, | |
| "loss": 2.5344, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.057803468208092484, | |
| "eval_loss": 2.740102767944336, | |
| "eval_runtime": 12.2957, | |
| "eval_samples_per_second": 29.685, | |
| "eval_steps_per_second": 14.883, | |
| "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": 451868681306112.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |