| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0016909744240118367, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001690974424011837, | |
| "grad_norm": 7.831810474395752, | |
| "learning_rate": 2e-05, | |
| "loss": 6.6256, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001690974424011837, | |
| "eval_loss": 6.817934036254883, | |
| "eval_runtime": 86.9, | |
| "eval_samples_per_second": 28.654, | |
| "eval_steps_per_second": 14.327, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003381948848023674, | |
| "grad_norm": 8.248199462890625, | |
| "learning_rate": 4e-05, | |
| "loss": 6.6485, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000507292327203551, | |
| "grad_norm": 8.04307746887207, | |
| "learning_rate": 6e-05, | |
| "loss": 6.9443, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000507292327203551, | |
| "eval_loss": 6.721807479858398, | |
| "eval_runtime": 85.1933, | |
| "eval_samples_per_second": 29.228, | |
| "eval_steps_per_second": 14.614, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006763897696047348, | |
| "grad_norm": 8.164813041687012, | |
| "learning_rate": 8e-05, | |
| "loss": 6.3247, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008454872120059184, | |
| "grad_norm": 8.150789260864258, | |
| "learning_rate": 0.0001, | |
| "loss": 6.4343, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001014584654407102, | |
| "grad_norm": 7.140324592590332, | |
| "learning_rate": 0.00012, | |
| "loss": 5.5998, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001014584654407102, | |
| "eval_loss": 5.347555637359619, | |
| "eval_runtime": 85.3388, | |
| "eval_samples_per_second": 29.178, | |
| "eval_steps_per_second": 14.589, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011836820968082857, | |
| "grad_norm": 6.379798889160156, | |
| "learning_rate": 0.00014, | |
| "loss": 5.621, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013527795392094695, | |
| "grad_norm": 5.837831020355225, | |
| "learning_rate": 0.00016, | |
| "loss": 4.7013, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0015218769816106531, | |
| "grad_norm": 5.567393779754639, | |
| "learning_rate": 0.00018, | |
| "loss": 4.3138, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0015218769816106531, | |
| "eval_loss": 3.6386404037475586, | |
| "eval_runtime": 85.3417, | |
| "eval_samples_per_second": 29.177, | |
| "eval_steps_per_second": 14.588, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016909744240118367, | |
| "grad_norm": 5.417690753936768, | |
| "learning_rate": 0.0002, | |
| "loss": 3.5436, | |
| "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": 1199811613163520.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |