| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006035913686434284, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006035913686434284, | |
| "grad_norm": 0.009034841321408749, | |
| "learning_rate": 2e-05, | |
| "loss": 11.9322, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006035913686434284, | |
| "eval_loss": 11.93203353881836, | |
| "eval_runtime": 9.6604, | |
| "eval_samples_per_second": 288.912, | |
| "eval_steps_per_second": 36.127, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012071827372868568, | |
| "grad_norm": 0.009666570462286472, | |
| "learning_rate": 4e-05, | |
| "loss": 11.933, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0018107741059302852, | |
| "grad_norm": 0.008490069769322872, | |
| "learning_rate": 6e-05, | |
| "loss": 11.932, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0018107741059302852, | |
| "eval_loss": 11.932022094726562, | |
| "eval_runtime": 9.7136, | |
| "eval_samples_per_second": 287.329, | |
| "eval_steps_per_second": 35.929, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0024143654745737136, | |
| "grad_norm": 0.010773689486086369, | |
| "learning_rate": 8e-05, | |
| "loss": 11.9312, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003017956843217142, | |
| "grad_norm": 0.009934109635651112, | |
| "learning_rate": 0.0001, | |
| "loss": 11.931, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0036215482118605704, | |
| "grad_norm": 0.010047477670013905, | |
| "learning_rate": 0.00012, | |
| "loss": 11.9307, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0036215482118605704, | |
| "eval_loss": 11.93198299407959, | |
| "eval_runtime": 9.7077, | |
| "eval_samples_per_second": 287.503, | |
| "eval_steps_per_second": 35.951, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004225139580503999, | |
| "grad_norm": 0.008809824474155903, | |
| "learning_rate": 0.00014, | |
| "loss": 11.9323, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004828730949147427, | |
| "grad_norm": 0.00893594790250063, | |
| "learning_rate": 0.00016, | |
| "loss": 11.9324, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005432322317790856, | |
| "grad_norm": 0.011988944374024868, | |
| "learning_rate": 0.00018, | |
| "loss": 11.9309, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005432322317790856, | |
| "eval_loss": 11.931912422180176, | |
| "eval_runtime": 9.7178, | |
| "eval_samples_per_second": 287.206, | |
| "eval_steps_per_second": 35.914, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006035913686434284, | |
| "grad_norm": 0.00849941186606884, | |
| "learning_rate": 0.0002, | |
| "loss": 11.9309, | |
| "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": 59957575680.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |