| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02851033499643621, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002851033499643621, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002851033499643621, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.7858, | |
| "eval_samples_per_second": 30.925, | |
| "eval_steps_per_second": 15.463, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005702066999287242, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008553100498930863, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008553100498930863, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.2353, | |
| "eval_samples_per_second": 34.945, | |
| "eval_steps_per_second": 17.472, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.011404133998574484, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.014255167498218105, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.017106200997861726, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017106200997861726, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.2694, | |
| "eval_samples_per_second": 34.665, | |
| "eval_steps_per_second": 17.333, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.019957234497505347, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.022808267997148968, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02565930149679259, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02565930149679259, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.2839, | |
| "eval_samples_per_second": 34.548, | |
| "eval_steps_per_second": 17.274, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02851033499643621, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "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": 1753442880061440.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |