| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.6665651407078953e-05, | |
| "eval_steps": 3, | |
| "global_step": 6, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.444275234513159e-06, | |
| "grad_norm": 0.1219407469034195, | |
| "learning_rate": 2e-05, | |
| "loss": 10.8347, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.444275234513159e-06, | |
| "eval_loss": 10.834060668945312, | |
| "eval_runtime": 132.6523, | |
| "eval_samples_per_second": 336.089, | |
| "eval_steps_per_second": 168.048, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.8888550469026318e-05, | |
| "grad_norm": 0.1645568311214447, | |
| "learning_rate": 4e-05, | |
| "loss": 10.8284, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 2.8332825703539477e-05, | |
| "grad_norm": 0.10935860127210617, | |
| "learning_rate": 6e-05, | |
| "loss": 10.8353, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.8332825703539477e-05, | |
| "eval_loss": 10.833942413330078, | |
| "eval_runtime": 131.4171, | |
| "eval_samples_per_second": 339.248, | |
| "eval_steps_per_second": 169.628, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 3.7777100938052636e-05, | |
| "grad_norm": 0.15527969598770142, | |
| "learning_rate": 8e-05, | |
| "loss": 10.8474, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 4.7221376172565795e-05, | |
| "grad_norm": 0.12643839418888092, | |
| "learning_rate": 0.0001, | |
| "loss": 10.8279, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 5.6665651407078953e-05, | |
| "grad_norm": 0.1306692212820053, | |
| "learning_rate": 0.00012, | |
| "loss": 10.8403, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 5.6665651407078953e-05, | |
| "eval_loss": 10.83309268951416, | |
| "eval_runtime": 131.7982, | |
| "eval_samples_per_second": 338.267, | |
| "eval_steps_per_second": 169.137, | |
| "step": 6 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 717758791680.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |