| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.061514195583596214, | |
| "eval_steps": 10, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0015772870662460567, | |
| "eval_loss": 11.935985565185547, | |
| "eval_runtime": 33.1237, | |
| "eval_samples_per_second": 8.061, | |
| "eval_steps_per_second": 4.045, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007886435331230283, | |
| "grad_norm": 0.20729076862335205, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9381, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015772870662460567, | |
| "grad_norm": 0.16789914667606354, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9335, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.015772870662460567, | |
| "eval_loss": 11.933769226074219, | |
| "eval_runtime": 34.0875, | |
| "eval_samples_per_second": 7.833, | |
| "eval_steps_per_second": 3.931, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02365930599369085, | |
| "grad_norm": 0.1739414930343628, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.9289, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.031545741324921134, | |
| "grad_norm": 0.1966327428817749, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.9279, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.031545741324921134, | |
| "eval_loss": 11.928752899169922, | |
| "eval_runtime": 23.245, | |
| "eval_samples_per_second": 11.486, | |
| "eval_steps_per_second": 5.765, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03943217665615142, | |
| "grad_norm": 0.19630083441734314, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.9268, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0473186119873817, | |
| "grad_norm": 0.18544097244739532, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9257, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0473186119873817, | |
| "eval_loss": 11.924522399902344, | |
| "eval_runtime": 26.5922, | |
| "eval_samples_per_second": 10.041, | |
| "eval_steps_per_second": 5.039, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.055205047318611984, | |
| "grad_norm": 0.21347272396087646, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.9219, | |
| "step": 35 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9292828114944.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |