| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0878348704435661, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001756697408871322, | |
| "eval_loss": 11.082844734191895, | |
| "eval_runtime": 2.2192, | |
| "eval_samples_per_second": 108.149, | |
| "eval_steps_per_second": 54.075, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00878348704435661, | |
| "grad_norm": 0.4254762828350067, | |
| "learning_rate": 5e-05, | |
| "loss": 44.3315, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01756697408871322, | |
| "grad_norm": 0.4281250834465027, | |
| "learning_rate": 0.0001, | |
| "loss": 44.3285, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01756697408871322, | |
| "eval_loss": 11.08116626739502, | |
| "eval_runtime": 1.4271, | |
| "eval_samples_per_second": 168.168, | |
| "eval_steps_per_second": 84.084, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.026350461133069828, | |
| "grad_norm": 0.4372434914112091, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 44.3201, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03513394817742644, | |
| "grad_norm": 0.4354489743709564, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 44.3119, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03513394817742644, | |
| "eval_loss": 11.077805519104004, | |
| "eval_runtime": 1.4987, | |
| "eval_samples_per_second": 160.137, | |
| "eval_steps_per_second": 80.068, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04391743522178305, | |
| "grad_norm": 0.45061734318733215, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 44.3135, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.052700922266139656, | |
| "grad_norm": 0.4921723008155823, | |
| "learning_rate": 5e-05, | |
| "loss": 44.2984, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.052700922266139656, | |
| "eval_loss": 11.075677871704102, | |
| "eval_runtime": 1.5009, | |
| "eval_samples_per_second": 159.903, | |
| "eval_steps_per_second": 79.951, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.061484409310496264, | |
| "grad_norm": 0.43915820121765137, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 44.3019, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07026789635485288, | |
| "grad_norm": 0.48046568036079407, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 44.2978, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07026789635485288, | |
| "eval_loss": 11.074297904968262, | |
| "eval_runtime": 1.4162, | |
| "eval_samples_per_second": 169.463, | |
| "eval_steps_per_second": 84.731, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07905138339920949, | |
| "grad_norm": 0.47706079483032227, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 44.2985, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0878348704435661, | |
| "grad_norm": 0.4358697533607483, | |
| "learning_rate": 0.0, | |
| "loss": 44.296, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0878348704435661, | |
| "eval_loss": 11.074076652526855, | |
| "eval_runtime": 1.383, | |
| "eval_samples_per_second": 173.539, | |
| "eval_steps_per_second": 86.769, | |
| "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": 43892736000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |