| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.028421202216853774, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005684240443370755, | |
| "eval_loss": 2.7989397048950195, | |
| "eval_runtime": 17.2024, | |
| "eval_samples_per_second": 43.075, | |
| "eval_steps_per_second": 21.567, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002842120221685377, | |
| "grad_norm": 49.51424789428711, | |
| "learning_rate": 5e-05, | |
| "loss": 10.9741, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005684240443370754, | |
| "grad_norm": 26.1766300201416, | |
| "learning_rate": 0.0001, | |
| "loss": 10.5397, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005684240443370754, | |
| "eval_loss": 2.7859725952148438, | |
| "eval_runtime": 15.1525, | |
| "eval_samples_per_second": 48.903, | |
| "eval_steps_per_second": 24.484, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008526360665056132, | |
| "grad_norm": 79.7308578491211, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 12.8043, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011368480886741509, | |
| "grad_norm": 22.914852142333984, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.0112, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011368480886741509, | |
| "eval_loss": 2.7343838214874268, | |
| "eval_runtime": 15.3255, | |
| "eval_samples_per_second": 48.351, | |
| "eval_steps_per_second": 24.208, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014210601108426887, | |
| "grad_norm": 213.0024871826172, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.3623, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.017052721330112264, | |
| "grad_norm": 43.09209442138672, | |
| "learning_rate": 5e-05, | |
| "loss": 10.0756, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.017052721330112264, | |
| "eval_loss": 2.6987078189849854, | |
| "eval_runtime": 15.2732, | |
| "eval_samples_per_second": 48.516, | |
| "eval_steps_per_second": 24.291, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.019894841551797642, | |
| "grad_norm": 51.78201675415039, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.1476, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.022736961773483017, | |
| "grad_norm": 27.225990295410156, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 9.8778, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.022736961773483017, | |
| "eval_loss": 2.679257869720459, | |
| "eval_runtime": 15.4476, | |
| "eval_samples_per_second": 47.969, | |
| "eval_steps_per_second": 24.017, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.025579081995168396, | |
| "grad_norm": 66.36029815673828, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.9107, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.028421202216853774, | |
| "grad_norm": 37.51848220825195, | |
| "learning_rate": 0.0, | |
| "loss": 11.0199, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.028421202216853774, | |
| "eval_loss": 2.678460121154785, | |
| "eval_runtime": 15.2491, | |
| "eval_samples_per_second": 48.593, | |
| "eval_steps_per_second": 24.329, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 495666396659712.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |