| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0010534743584341157, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.1069487168682315e-05, | |
| "eval_loss": 3.2631447315216064, | |
| "eval_runtime": 573.1084, | |
| "eval_samples_per_second": 34.871, | |
| "eval_steps_per_second": 17.436, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00010534743584341157, | |
| "grad_norm": 0.18382155895233154, | |
| "learning_rate": 5e-05, | |
| "loss": 3.2617, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00021069487168682313, | |
| "grad_norm": 0.23125022649765015, | |
| "learning_rate": 0.0001, | |
| "loss": 3.2338, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00021069487168682313, | |
| "eval_loss": 3.2458643913269043, | |
| "eval_runtime": 569.477, | |
| "eval_samples_per_second": 35.094, | |
| "eval_steps_per_second": 17.548, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0003160423075302347, | |
| "grad_norm": 0.49949705600738525, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.1384, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00042138974337364626, | |
| "grad_norm": 0.5684022903442383, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.0211, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00042138974337364626, | |
| "eval_loss": 3.1317827701568604, | |
| "eval_runtime": 567.3693, | |
| "eval_samples_per_second": 35.224, | |
| "eval_steps_per_second": 17.613, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0005267371792170579, | |
| "grad_norm": 0.6344699263572693, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.2487, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0006320846150604694, | |
| "grad_norm": 0.5269583463668823, | |
| "learning_rate": 5e-05, | |
| "loss": 3.103, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0006320846150604694, | |
| "eval_loss": 3.084909677505493, | |
| "eval_runtime": 569.2849, | |
| "eval_samples_per_second": 35.105, | |
| "eval_steps_per_second": 17.554, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.000737432050903881, | |
| "grad_norm": 1.1395690441131592, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.0862, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0008427794867472925, | |
| "grad_norm": 0.6051152944564819, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.9749, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0008427794867472925, | |
| "eval_loss": 3.0690979957580566, | |
| "eval_runtime": 569.8301, | |
| "eval_samples_per_second": 35.072, | |
| "eval_steps_per_second": 17.537, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0009481269225907041, | |
| "grad_norm": 0.6785821318626404, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.9934, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0010534743584341157, | |
| "grad_norm": 0.7350694537162781, | |
| "learning_rate": 0.0, | |
| "loss": 3.1248, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0010534743584341157, | |
| "eval_loss": 3.0668978691101074, | |
| "eval_runtime": 568.6446, | |
| "eval_samples_per_second": 35.145, | |
| "eval_steps_per_second": 17.573, | |
| "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": 1801107479199744.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |