| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0008443271767810027, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.443271767810026e-05, | |
| "grad_norm": 3.0607061489718035e-05, | |
| "learning_rate": 2e-05, | |
| "loss": 46.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.443271767810026e-05, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 29.0584, | |
| "eval_samples_per_second": 171.62, | |
| "eval_steps_per_second": 85.827, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016886543535620053, | |
| "grad_norm": 4.8180430894717574e-05, | |
| "learning_rate": 4e-05, | |
| "loss": 46.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002532981530343008, | |
| "grad_norm": 4.388760498841293e-05, | |
| "learning_rate": 6e-05, | |
| "loss": 46.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002532981530343008, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 29.1271, | |
| "eval_samples_per_second": 171.215, | |
| "eval_steps_per_second": 85.625, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00033773087071240106, | |
| "grad_norm": 2.608526665426325e-05, | |
| "learning_rate": 8e-05, | |
| "loss": 46.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00042216358839050134, | |
| "grad_norm": 3.815816671703942e-05, | |
| "learning_rate": 0.0001, | |
| "loss": 46.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005065963060686016, | |
| "grad_norm": 5.386924385675229e-05, | |
| "learning_rate": 0.00012, | |
| "loss": 46.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005065963060686016, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 31.8368, | |
| "eval_samples_per_second": 156.643, | |
| "eval_steps_per_second": 78.337, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005910290237467018, | |
| "grad_norm": 2.5218401788151823e-05, | |
| "learning_rate": 0.00014, | |
| "loss": 46.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006754617414248021, | |
| "grad_norm": 3.802698847721331e-05, | |
| "learning_rate": 0.00016, | |
| "loss": 46.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007598944591029024, | |
| "grad_norm": 3.192108488292433e-05, | |
| "learning_rate": 0.00018, | |
| "loss": 46.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007598944591029024, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 29.5068, | |
| "eval_samples_per_second": 169.012, | |
| "eval_steps_per_second": 84.523, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008443271767810027, | |
| "grad_norm": 4.112796887056902e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 46.0, | |
| "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": 398457569280.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |