| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.001554001554001554, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001554001554001554, | |
| "grad_norm": 2.598501443862915, | |
| "learning_rate": 2e-05, | |
| "loss": 5.5903, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001554001554001554, | |
| "eval_loss": 5.979092121124268, | |
| "eval_runtime": 119.1828, | |
| "eval_samples_per_second": 22.738, | |
| "eval_steps_per_second": 11.369, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003108003108003108, | |
| "grad_norm": 1.9009497165679932, | |
| "learning_rate": 4e-05, | |
| "loss": 4.2089, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0004662004662004662, | |
| "grad_norm": 2.9781405925750732, | |
| "learning_rate": 6e-05, | |
| "loss": 5.9268, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004662004662004662, | |
| "eval_loss": 5.970939636230469, | |
| "eval_runtime": 117.8699, | |
| "eval_samples_per_second": 22.991, | |
| "eval_steps_per_second": 11.496, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006216006216006216, | |
| "grad_norm": 2.6014654636383057, | |
| "learning_rate": 8e-05, | |
| "loss": 6.3323, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.000777000777000777, | |
| "grad_norm": 2.1102042198181152, | |
| "learning_rate": 0.0001, | |
| "loss": 4.3612, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009324009324009324, | |
| "grad_norm": 3.557586431503296, | |
| "learning_rate": 0.00012, | |
| "loss": 5.8431, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009324009324009324, | |
| "eval_loss": 5.798998832702637, | |
| "eval_runtime": 117.8935, | |
| "eval_samples_per_second": 22.987, | |
| "eval_steps_per_second": 11.493, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010878010878010878, | |
| "grad_norm": 2.7650983333587646, | |
| "learning_rate": 0.00014, | |
| "loss": 4.7111, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0012432012432012432, | |
| "grad_norm": 3.379702091217041, | |
| "learning_rate": 0.00016, | |
| "loss": 5.5954, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0013986013986013986, | |
| "grad_norm": 3.5403878688812256, | |
| "learning_rate": 0.00018, | |
| "loss": 4.7313, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0013986013986013986, | |
| "eval_loss": 5.086339950561523, | |
| "eval_runtime": 117.9242, | |
| "eval_samples_per_second": 22.981, | |
| "eval_steps_per_second": 11.49, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001554001554001554, | |
| "grad_norm": 3.722743034362793, | |
| "learning_rate": 0.0002, | |
| "loss": 4.751, | |
| "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": 2728107266015232.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |