| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0013531341970839958, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00027062683941679914, | |
| "grad_norm": 0.6253830194473267, | |
| "learning_rate": 1e-05, | |
| "loss": 1.0784, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00027062683941679914, | |
| "eval_loss": 1.2135142087936401, | |
| "eval_runtime": 343.3771, | |
| "eval_samples_per_second": 18.126, | |
| "eval_steps_per_second": 9.063, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005412536788335983, | |
| "grad_norm": 0.5701841711997986, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1425, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005412536788335983, | |
| "eval_loss": 1.2049360275268555, | |
| "eval_runtime": 364.8344, | |
| "eval_samples_per_second": 17.06, | |
| "eval_steps_per_second": 8.53, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008118805182503975, | |
| "grad_norm": 0.570219099521637, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1019, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010825073576671966, | |
| "grad_norm": 0.6055260896682739, | |
| "learning_rate": 4e-05, | |
| "loss": 1.1515, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0010825073576671966, | |
| "eval_loss": 1.1862051486968994, | |
| "eval_runtime": 303.7185, | |
| "eval_samples_per_second": 20.493, | |
| "eval_steps_per_second": 10.246, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0013531341970839958, | |
| "grad_norm": 0.5400911569595337, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0075, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5064392253112320.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |