| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0032144005143040825, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003214400514304082, | |
| "grad_norm": 2.2238895893096924, | |
| "learning_rate": 2e-05, | |
| "loss": 8.2829, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003214400514304082, | |
| "eval_loss": 2.0177955627441406, | |
| "eval_runtime": 60.9768, | |
| "eval_samples_per_second": 21.484, | |
| "eval_steps_per_second": 10.742, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006428801028608164, | |
| "grad_norm": 2.1225650310516357, | |
| "learning_rate": 4e-05, | |
| "loss": 7.2637, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0009643201542912247, | |
| "grad_norm": 1.856429100036621, | |
| "learning_rate": 6e-05, | |
| "loss": 7.9549, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009643201542912247, | |
| "eval_loss": 2.014383554458618, | |
| "eval_runtime": 59.7107, | |
| "eval_samples_per_second": 21.939, | |
| "eval_steps_per_second": 10.97, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0012857602057216328, | |
| "grad_norm": 2.1928322315216064, | |
| "learning_rate": 8e-05, | |
| "loss": 8.4298, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0016072002571520412, | |
| "grad_norm": 2.4467806816101074, | |
| "learning_rate": 0.0001, | |
| "loss": 9.1291, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0019286403085824494, | |
| "grad_norm": 1.8387688398361206, | |
| "learning_rate": 0.00012, | |
| "loss": 7.5879, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0019286403085824494, | |
| "eval_loss": 1.9823801517486572, | |
| "eval_runtime": 59.7435, | |
| "eval_samples_per_second": 21.927, | |
| "eval_steps_per_second": 10.964, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0022500803600128574, | |
| "grad_norm": 1.947957158088684, | |
| "learning_rate": 0.00014, | |
| "loss": 7.3814, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0025715204114432656, | |
| "grad_norm": 3.4860267639160156, | |
| "learning_rate": 0.00016, | |
| "loss": 8.7578, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0028929604628736743, | |
| "grad_norm": 2.8685097694396973, | |
| "learning_rate": 0.00018, | |
| "loss": 6.9682, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0028929604628736743, | |
| "eval_loss": 1.8758397102355957, | |
| "eval_runtime": 59.7212, | |
| "eval_samples_per_second": 21.935, | |
| "eval_steps_per_second": 10.968, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0032144005143040825, | |
| "grad_norm": 3.1170525550842285, | |
| "learning_rate": 0.0002, | |
| "loss": 7.966, | |
| "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": 4065247635701760.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |