| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04796738218011752, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009593476436023504, | |
| "eval_loss": 2.3225936889648438, | |
| "eval_runtime": 311.6538, | |
| "eval_samples_per_second": 5.634, | |
| "eval_steps_per_second": 2.817, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009593476436023504, | |
| "eval_loss": 2.3082287311553955, | |
| "eval_runtime": 312.7969, | |
| "eval_samples_per_second": 5.614, | |
| "eval_steps_per_second": 2.807, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.019186952872047008, | |
| "eval_loss": 2.1574323177337646, | |
| "eval_runtime": 310.4943, | |
| "eval_samples_per_second": 5.655, | |
| "eval_steps_per_second": 2.828, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.028780429308070513, | |
| "eval_loss": 1.9162683486938477, | |
| "eval_runtime": 310.4456, | |
| "eval_samples_per_second": 5.656, | |
| "eval_steps_per_second": 2.828, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.038373905744094015, | |
| "grad_norm": 18.934436798095703, | |
| "learning_rate": 2.9289321881345257e-06, | |
| "loss": 33.3571, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.038373905744094015, | |
| "eval_loss": 1.7879064083099365, | |
| "eval_runtime": 310.5118, | |
| "eval_samples_per_second": 5.655, | |
| "eval_steps_per_second": 2.828, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04796738218011752, | |
| "eval_loss": 1.7664101123809814, | |
| "eval_runtime": 308.078, | |
| "eval_samples_per_second": 5.7, | |
| "eval_steps_per_second": 2.85, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 40, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.3324486107136e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |