| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005684240443370754, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005684240443370755, | |
| "grad_norm": 2.788839101791382, | |
| "learning_rate": 2e-05, | |
| "loss": 3.8105, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005684240443370755, | |
| "eval_loss": 4.394862174987793, | |
| "eval_runtime": 12.1374, | |
| "eval_samples_per_second": 61.051, | |
| "eval_steps_per_second": 30.567, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001136848088674151, | |
| "grad_norm": 3.5119056701660156, | |
| "learning_rate": 4e-05, | |
| "loss": 4.1833, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0017052721330112265, | |
| "grad_norm": 3.555345296859741, | |
| "learning_rate": 6e-05, | |
| "loss": 4.1925, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0017052721330112265, | |
| "eval_loss": 4.37744665145874, | |
| "eval_runtime": 12.1948, | |
| "eval_samples_per_second": 60.764, | |
| "eval_steps_per_second": 30.423, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002273696177348302, | |
| "grad_norm": 3.436891555786133, | |
| "learning_rate": 8e-05, | |
| "loss": 4.8595, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002842120221685377, | |
| "grad_norm": 4.515559196472168, | |
| "learning_rate": 0.0001, | |
| "loss": 4.3636, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003410544266022453, | |
| "grad_norm": 3.168912887573242, | |
| "learning_rate": 0.00012, | |
| "loss": 3.9756, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003410544266022453, | |
| "eval_loss": 4.110952854156494, | |
| "eval_runtime": 12.4679, | |
| "eval_samples_per_second": 59.432, | |
| "eval_steps_per_second": 29.756, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003978968310359528, | |
| "grad_norm": 2.8147921562194824, | |
| "learning_rate": 0.00014, | |
| "loss": 3.5104, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004547392354696604, | |
| "grad_norm": 3.1404922008514404, | |
| "learning_rate": 0.00016, | |
| "loss": 3.704, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005115816399033679, | |
| "grad_norm": 3.2286388874053955, | |
| "learning_rate": 0.00018, | |
| "loss": 3.9134, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005115816399033679, | |
| "eval_loss": 3.5906028747558594, | |
| "eval_runtime": 12.568, | |
| "eval_samples_per_second": 58.959, | |
| "eval_steps_per_second": 29.519, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005684240443370754, | |
| "grad_norm": 3.03719425201416, | |
| "learning_rate": 0.0002, | |
| "loss": 4.0201, | |
| "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": 489477793382400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |