| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0007082403767838804, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.082403767838805e-05, | |
| "grad_norm": 0.5956665277481079, | |
| "learning_rate": 2e-05, | |
| "loss": 1.4888, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.082403767838805e-05, | |
| "eval_loss": 1.285233497619629, | |
| "eval_runtime": 244.9702, | |
| "eval_samples_per_second": 24.272, | |
| "eval_steps_per_second": 12.136, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001416480753567761, | |
| "grad_norm": 0.3512568175792694, | |
| "learning_rate": 4e-05, | |
| "loss": 1.0845, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00021247211303516414, | |
| "grad_norm": 0.2720630168914795, | |
| "learning_rate": 6e-05, | |
| "loss": 1.1689, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00021247211303516414, | |
| "eval_loss": 1.2835770845413208, | |
| "eval_runtime": 243.9274, | |
| "eval_samples_per_second": 24.376, | |
| "eval_steps_per_second": 12.188, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002832961507135522, | |
| "grad_norm": 0.5889267921447754, | |
| "learning_rate": 8e-05, | |
| "loss": 1.1645, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0003541201883919402, | |
| "grad_norm": 0.8530604839324951, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3131, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00042494422607032827, | |
| "grad_norm": 0.24282629787921906, | |
| "learning_rate": 0.00012, | |
| "loss": 1.1017, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00042494422607032827, | |
| "eval_loss": 1.2677675485610962, | |
| "eval_runtime": 246.6787, | |
| "eval_samples_per_second": 24.104, | |
| "eval_steps_per_second": 12.052, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0004957682637487163, | |
| "grad_norm": 0.4078926146030426, | |
| "learning_rate": 0.00014, | |
| "loss": 1.0795, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005665923014271044, | |
| "grad_norm": 0.4543113112449646, | |
| "learning_rate": 0.00016, | |
| "loss": 1.0601, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006374163391054924, | |
| "grad_norm": 0.3541891872882843, | |
| "learning_rate": 0.00018, | |
| "loss": 1.068, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006374163391054924, | |
| "eval_loss": 1.2101588249206543, | |
| "eval_runtime": 249.3616, | |
| "eval_samples_per_second": 23.845, | |
| "eval_steps_per_second": 11.922, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007082403767838804, | |
| "grad_norm": 0.7510812878608704, | |
| "learning_rate": 0.0002, | |
| "loss": 1.232, | |
| "step": 10 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2265756519628800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |