| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02577873254564984, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008592910848549946, | |
| "eval_loss": 1.8667653799057007, | |
| "eval_runtime": 45.578, | |
| "eval_samples_per_second": 10.751, | |
| "eval_steps_per_second": 5.375, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0025778732545649837, | |
| "grad_norm": 0.36189717054367065, | |
| "learning_rate": 6e-05, | |
| "loss": 1.9011, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0051557465091299675, | |
| "grad_norm": 0.39917466044425964, | |
| "learning_rate": 0.00012, | |
| "loss": 1.8653, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006874328678839957, | |
| "eval_loss": 1.7837806940078735, | |
| "eval_runtime": 45.119, | |
| "eval_samples_per_second": 10.86, | |
| "eval_steps_per_second": 5.43, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007733619763694952, | |
| "grad_norm": 0.3139704763889313, | |
| "learning_rate": 0.00018, | |
| "loss": 1.7275, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010311493018259935, | |
| "grad_norm": 0.44123542308807373, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.8639, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01288936627282492, | |
| "grad_norm": 0.2540883421897888, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.7744, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013748657357679914, | |
| "eval_loss": 1.7006312608718872, | |
| "eval_runtime": 45.3441, | |
| "eval_samples_per_second": 10.806, | |
| "eval_steps_per_second": 5.403, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.015467239527389903, | |
| "grad_norm": 0.2754911780357361, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.6289, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01804511278195489, | |
| "grad_norm": 0.25182831287384033, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.6613, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02062298603651987, | |
| "grad_norm": 0.2403896301984787, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.6021, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02062298603651987, | |
| "eval_loss": 1.673106074333191, | |
| "eval_runtime": 45.3591, | |
| "eval_samples_per_second": 10.803, | |
| "eval_steps_per_second": 5.401, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.023200859291084855, | |
| "grad_norm": 0.29642242193222046, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.6458, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02577873254564984, | |
| "grad_norm": 0.24471496045589447, | |
| "learning_rate": 0.0, | |
| "loss": 1.6717, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "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": 1.1272153982828544e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |