| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.008194855451855224, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009105394946505805, | |
| "grad_norm": 15.459493637084961, | |
| "learning_rate": 2e-05, | |
| "loss": 6.699, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009105394946505805, | |
| "eval_loss": 6.645326614379883, | |
| "eval_runtime": 16.2723, | |
| "eval_samples_per_second": 28.453, | |
| "eval_steps_per_second": 14.257, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001821078989301161, | |
| "grad_norm": 19.65015411376953, | |
| "learning_rate": 4e-05, | |
| "loss": 6.5514, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0027316184839517414, | |
| "grad_norm": 15.934015274047852, | |
| "learning_rate": 6e-05, | |
| "loss": 6.7668, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0027316184839517414, | |
| "eval_loss": 6.436738967895508, | |
| "eval_runtime": 16.2764, | |
| "eval_samples_per_second": 28.446, | |
| "eval_steps_per_second": 14.254, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003642157978602322, | |
| "grad_norm": 14.389528274536133, | |
| "learning_rate": 8e-05, | |
| "loss": 6.318, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004552697473252903, | |
| "grad_norm": 16.335371017456055, | |
| "learning_rate": 0.0001, | |
| "loss": 5.8031, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005463236967903483, | |
| "grad_norm": 17.598861694335938, | |
| "learning_rate": 0.00012, | |
| "loss": 4.4722, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005463236967903483, | |
| "eval_loss": 4.52072811126709, | |
| "eval_runtime": 16.2973, | |
| "eval_samples_per_second": 28.41, | |
| "eval_steps_per_second": 14.235, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006373776462554063, | |
| "grad_norm": 13.830560684204102, | |
| "learning_rate": 0.00014, | |
| "loss": 3.322, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007284315957204644, | |
| "grad_norm": 8.69044303894043, | |
| "learning_rate": 0.00016, | |
| "loss": 3.1473, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008194855451855224, | |
| "grad_norm": 11.504103660583496, | |
| "learning_rate": 0.00018, | |
| "loss": 3.5931, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008194855451855224, | |
| "eval_loss": 3.023555278778076, | |
| "eval_runtime": 16.2783, | |
| "eval_samples_per_second": 28.443, | |
| "eval_steps_per_second": 14.252, | |
| "step": 9 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1719982274641920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |