| { | |
| "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 | |
| } | |