| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0351173391862232, | |
| "eval_steps": 13, | |
| "global_step": 13, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0027013337835556307, | |
| "grad_norm": 0.18103669583797455, | |
| "learning_rate": 1e-05, | |
| "loss": 1.4768, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0027013337835556307, | |
| "eval_loss": 1.515325665473938, | |
| "eval_runtime": 102.7627, | |
| "eval_samples_per_second": 6.072, | |
| "eval_steps_per_second": 3.036, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0054026675671112615, | |
| "grad_norm": 0.19400662183761597, | |
| "learning_rate": 2e-05, | |
| "loss": 1.4582, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008104001350666891, | |
| "grad_norm": 0.14791804552078247, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2738, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010805335134222523, | |
| "grad_norm": 0.14204905927181244, | |
| "learning_rate": 4e-05, | |
| "loss": 1.3744, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013506668917778153, | |
| "grad_norm": 0.13965387642383575, | |
| "learning_rate": 5e-05, | |
| "loss": 1.168, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.016208002701333782, | |
| "grad_norm": 0.1606331765651703, | |
| "learning_rate": 6e-05, | |
| "loss": 1.2615, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.018909336484889416, | |
| "grad_norm": 0.16424395143985748, | |
| "learning_rate": 7e-05, | |
| "loss": 1.2599, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.021610670268445046, | |
| "grad_norm": 0.22166331112384796, | |
| "learning_rate": 8e-05, | |
| "loss": 1.4082, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.024312004052000676, | |
| "grad_norm": 0.19696258008480072, | |
| "learning_rate": 9e-05, | |
| "loss": 1.3881, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.027013337835556307, | |
| "grad_norm": 0.23053531348705292, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3014, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.029714671619111937, | |
| "grad_norm": 0.22696362435817719, | |
| "learning_rate": 9.98458666866564e-05, | |
| "loss": 1.3396, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.032416005402667564, | |
| "grad_norm": 0.19953660666942596, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 1.164, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0351173391862232, | |
| "grad_norm": 0.21297410130500793, | |
| "learning_rate": 9.861849601988383e-05, | |
| "loss": 1.3591, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0351173391862232, | |
| "eval_loss": 1.3835619688034058, | |
| "eval_runtime": 21.4452, | |
| "eval_samples_per_second": 29.097, | |
| "eval_steps_per_second": 14.549, | |
| "step": 13 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.4855972292919296e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |