| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.5217391304347827, | |
| "eval_steps": 4, | |
| "global_step": 8, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.34782608695652173, | |
| "grad_norm": 1.4875977039337158, | |
| "learning_rate": 8e-05, | |
| "loss": 2.5412, | |
| "mean_token_accuracy": 0.4997914097956677, | |
| "step": 2, | |
| "timestamp_in_seconds": 1740058274.0585067 | |
| }, | |
| { | |
| "epoch": 0.6956521739130435, | |
| "grad_norm": 1.632702350616455, | |
| "learning_rate": 0.00016, | |
| "loss": 2.9539, | |
| "mean_token_accuracy": 0.42651914517057904, | |
| "step": 4, | |
| "timestamp_in_seconds": 1740058277.1258354 | |
| }, | |
| { | |
| "contract_score": 0.6136034679600317, | |
| "epoch": 0.6956521739130435, | |
| "eval_loss": 2.5099453926086426, | |
| "eval_mean_token_accuracy": 0.5287356321839081, | |
| "eval_runtime": 0.1464, | |
| "eval_samples_per_second": 34.155, | |
| "eval_steps_per_second": 6.831, | |
| "step": 4, | |
| "timestamp_in_seconds": 1740058291.5312915 | |
| }, | |
| { | |
| "epoch": 1.1739130434782608, | |
| "grad_norm": 2.6520564556121826, | |
| "learning_rate": 0.00019, | |
| "loss": 3.6668, | |
| "mean_token_accuracy": 0.4724609108170344, | |
| "step": 6, | |
| "timestamp_in_seconds": 1740058295.0447173 | |
| }, | |
| { | |
| "epoch": 1.5217391304347827, | |
| "grad_norm": 1.0216948986053467, | |
| "learning_rate": 0.00017, | |
| "loss": 2.2706, | |
| "mean_token_accuracy": 0.5100777653686674, | |
| "step": 8, | |
| "timestamp_in_seconds": 1740058298.1438003 | |
| }, | |
| { | |
| "epoch": 1.5217391304347827, | |
| "eval_loss": 2.0535407066345215, | |
| "eval_mean_token_accuracy": 0.5747126436781609, | |
| "eval_runtime": 0.1461, | |
| "eval_samples_per_second": 34.225, | |
| "eval_steps_per_second": 6.845, | |
| "step": 8, | |
| "timestamp_in_seconds": 1740058298.3368814 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 4, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 457437182558208.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |