| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06548788474132286, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013097576948264572, | |
| "eval_loss": NaN, | |
| "eval_runtime": 56.8542, | |
| "eval_samples_per_second": 5.664, | |
| "eval_steps_per_second": 2.832, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006548788474132285, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01309757694826457, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01309757694826457, | |
| "eval_loss": NaN, | |
| "eval_runtime": 55.2813, | |
| "eval_samples_per_second": 5.825, | |
| "eval_steps_per_second": 2.912, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.019646365422396856, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02619515389652914, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02619515389652914, | |
| "eval_loss": NaN, | |
| "eval_runtime": 57.8537, | |
| "eval_samples_per_second": 5.566, | |
| "eval_steps_per_second": 2.783, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03274394237066143, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03929273084479371, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03929273084479371, | |
| "eval_loss": NaN, | |
| "eval_runtime": 60.4125, | |
| "eval_samples_per_second": 5.33, | |
| "eval_steps_per_second": 2.665, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.045841519318926, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05239030779305828, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05239030779305828, | |
| "eval_loss": NaN, | |
| "eval_runtime": 66.5241, | |
| "eval_samples_per_second": 4.84, | |
| "eval_steps_per_second": 2.42, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05893909626719057, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06548788474132286, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06548788474132286, | |
| "eval_loss": NaN, | |
| "eval_runtime": 43.1808, | |
| "eval_samples_per_second": 7.457, | |
| "eval_steps_per_second": 3.729, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8767214400307200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |