| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.011587485515643106, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002317497103128621, | |
| "grad_norm": 3.2033631801605225, | |
| "learning_rate": 1e-05, | |
| "loss": 7.6899, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002317497103128621, | |
| "eval_loss": 7.833714485168457, | |
| "eval_runtime": 60.9519, | |
| "eval_samples_per_second": 11.927, | |
| "eval_steps_per_second": 5.972, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004634994206257242, | |
| "grad_norm": 3.071789503097534, | |
| "learning_rate": 2e-05, | |
| "loss": 7.7967, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004634994206257242, | |
| "eval_loss": 7.827545166015625, | |
| "eval_runtime": 5.4651, | |
| "eval_samples_per_second": 133.027, | |
| "eval_steps_per_second": 66.605, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006952491309385863, | |
| "grad_norm": 2.7997231483459473, | |
| "learning_rate": 3e-05, | |
| "loss": 7.6475, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009269988412514484, | |
| "grad_norm": 2.8682124614715576, | |
| "learning_rate": 4e-05, | |
| "loss": 7.8465, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.009269988412514484, | |
| "eval_loss": 7.81229305267334, | |
| "eval_runtime": 5.5295, | |
| "eval_samples_per_second": 131.477, | |
| "eval_steps_per_second": 65.829, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011587485515643106, | |
| "grad_norm": 3.212735176086426, | |
| "learning_rate": 5e-05, | |
| "loss": 7.7115, | |
| "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": 2048704512000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |