| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.869565217391304, | |
| "eval_steps": 500, | |
| "global_step": 15, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.34782608695652173, | |
| "grad_norm": 2.2193984985351562, | |
| "learning_rate": 8e-05, | |
| "loss": 2.602, | |
| "mean_token_accuracy": 0.48853018043069, | |
| "step": 2, | |
| "timestamp_in_seconds": 1739737841.8907907 | |
| }, | |
| { | |
| "epoch": 0.6956521739130435, | |
| "grad_norm": 2.590531587600708, | |
| "learning_rate": 0.00016, | |
| "loss": 2.1615, | |
| "mean_token_accuracy": 0.5326818635271061, | |
| "step": 4, | |
| "timestamp_in_seconds": 1739737846.0858383 | |
| }, | |
| { | |
| "contract_score": 0.34910623408499225, | |
| "epoch": 0.8695652173913043, | |
| "eval_loss": 2.3978517055511475, | |
| "eval_mean_token_accuracy": 0.500905218748722, | |
| "eval_runtime": 0.2461, | |
| "eval_samples_per_second": 20.321, | |
| "eval_steps_per_second": 4.064, | |
| "step": 5, | |
| "timestamp_in_seconds": 1739737861.5970306 | |
| }, | |
| { | |
| "epoch": 1.1739130434782608, | |
| "grad_norm": 1.9542165994644165, | |
| "learning_rate": 0.00019555555555555556, | |
| "loss": 2.9919, | |
| "mean_token_accuracy": 0.5233166398059312, | |
| "step": 6, | |
| "timestamp_in_seconds": 1739737863.68004 | |
| }, | |
| { | |
| "epoch": 1.5217391304347827, | |
| "grad_norm": 0.9734348654747009, | |
| "learning_rate": 0.0001866666666666667, | |
| "loss": 1.6638, | |
| "mean_token_accuracy": 0.5688752612519408, | |
| "step": 8, | |
| "timestamp_in_seconds": 1739737867.885973 | |
| }, | |
| { | |
| "epoch": 1.8695652173913042, | |
| "grad_norm": 0.9799295663833618, | |
| "learning_rate": 0.00017777777777777779, | |
| "loss": 1.699, | |
| "mean_token_accuracy": 0.5963812146418476, | |
| "step": 10, | |
| "timestamp_in_seconds": 1739737872.0998006 | |
| }, | |
| { | |
| "contract_score": 0.46223260788690473, | |
| "epoch": 1.8695652173913042, | |
| "eval_loss": 2.370565176010132, | |
| "eval_mean_token_accuracy": 0.5109471680152309, | |
| "eval_runtime": 0.2465, | |
| "eval_samples_per_second": 20.286, | |
| "eval_steps_per_second": 4.057, | |
| "step": 10, | |
| "timestamp_in_seconds": 1739737885.94682 | |
| }, | |
| { | |
| "epoch": 2.3478260869565215, | |
| "grad_norm": 0.9762361645698547, | |
| "learning_rate": 0.00016888888888888889, | |
| "loss": 2.1365, | |
| "mean_token_accuracy": 0.6419918473272441, | |
| "step": 12, | |
| "timestamp_in_seconds": 1739737890.190909 | |
| }, | |
| { | |
| "epoch": 2.6956521739130435, | |
| "grad_norm": 1.0904510021209717, | |
| "learning_rate": 0.00016, | |
| "loss": 1.4277, | |
| "mean_token_accuracy": 0.6154424721840729, | |
| "step": 14, | |
| "timestamp_in_seconds": 1739737894.3377419 | |
| }, | |
| { | |
| "epoch": 2.869565217391304, | |
| "eval_loss": 2.4834651947021484, | |
| "eval_mean_token_accuracy": 0.5880390118821684, | |
| "eval_runtime": 0.2447, | |
| "eval_samples_per_second": 20.433, | |
| "eval_steps_per_second": 4.087, | |
| "step": 15 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2390259035480064.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |