| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.010148163182463974, |
| "eval_steps": 10, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00020296326364927948, |
| "eval_loss": 3.347236156463623, |
| "eval_runtime": 61.3527, |
| "eval_samples_per_second": 33.821, |
| "eval_steps_per_second": 16.919, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0010148163182463973, |
| "grad_norm": 1.6440613269805908, |
| "learning_rate": 5e-05, |
| "loss": 3.3295, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0020296326364927946, |
| "grad_norm": 2.3382773399353027, |
| "learning_rate": 0.0001, |
| "loss": 3.1632, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0020296326364927946, |
| "eval_loss": 2.92110538482666, |
| "eval_runtime": 61.5328, |
| "eval_samples_per_second": 33.722, |
| "eval_steps_per_second": 16.869, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.003044448954739192, |
| "grad_norm": 1.8466225862503052, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 2.5546, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.004059265272985589, |
| "grad_norm": 2.247924327850342, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 2.1787, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.004059265272985589, |
| "eval_loss": 1.8443979024887085, |
| "eval_runtime": 61.9335, |
| "eval_samples_per_second": 33.504, |
| "eval_steps_per_second": 16.76, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.005074081591231987, |
| "grad_norm": 2.343292713165283, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 1.599, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.006088897909478384, |
| "grad_norm": 2.303910970687866, |
| "learning_rate": 5e-05, |
| "loss": 1.3913, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.006088897909478384, |
| "eval_loss": 1.363053321838379, |
| "eval_runtime": 61.6365, |
| "eval_samples_per_second": 33.665, |
| "eval_steps_per_second": 16.841, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.007103714227724781, |
| "grad_norm": 2.6633644104003906, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 1.3817, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.008118530545971179, |
| "grad_norm": 2.0624611377716064, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 1.2526, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.008118530545971179, |
| "eval_loss": 1.2399094104766846, |
| "eval_runtime": 61.9297, |
| "eval_samples_per_second": 33.506, |
| "eval_steps_per_second": 16.761, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.009133346864217576, |
| "grad_norm": 2.5647053718566895, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 1.1881, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.010148163182463974, |
| "grad_norm": 1.8386671543121338, |
| "learning_rate": 0.0, |
| "loss": 1.2177, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.010148163182463974, |
| "eval_loss": 1.2173258066177368, |
| "eval_runtime": 61.5869, |
| "eval_samples_per_second": 33.692, |
| "eval_steps_per_second": 16.854, |
| "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": 1278959891251200.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
