| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "entropy": 0.40918557345867157, | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 0.21945789456367493, | |
| "learning_rate": 0.0003, | |
| "loss": 0.7418, | |
| "mean_token_accuracy": 0.8251394703984261, | |
| "num_tokens": 253105.0, | |
| "step": 1 | |
| }, | |
| { | |
| "entropy": 0.4437573179602623, | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 0.12486214935779572, | |
| "learning_rate": 0.000225, | |
| "loss": 0.6689, | |
| "mean_token_accuracy": 0.8339769467711449, | |
| "num_tokens": 507231.0, | |
| "step": 2 | |
| }, | |
| { | |
| "entropy": 0.5273671075701714, | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": 0.06876438111066818, | |
| "learning_rate": 0.00015, | |
| "loss": 0.6568, | |
| "mean_token_accuracy": 0.8280958458781242, | |
| "num_tokens": 750116.0, | |
| "step": 3 | |
| }, | |
| { | |
| "entropy": 0.5205405354499817, | |
| "epoch": 1.0, | |
| "grad_norm": 0.050599515438079834, | |
| "learning_rate": 7.5e-05, | |
| "loss": 0.5893, | |
| "mean_token_accuracy": 0.8457660377025604, | |
| "num_tokens": 813660.0, | |
| "step": 4 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 4, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.838366729828352e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |