| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0042653017701002344, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00042653017701002344, | |
| "grad_norm": 0.7401810884475708, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7824, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00042653017701002344, | |
| "eval_loss": 0.4496455192565918, | |
| "eval_runtime": 50.9515, | |
| "eval_samples_per_second": 19.391, | |
| "eval_steps_per_second": 9.695, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008530603540200469, | |
| "grad_norm": 0.6387481093406677, | |
| "learning_rate": 4e-05, | |
| "loss": 1.5662, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0012795905310300703, | |
| "grad_norm": 0.6438620686531067, | |
| "learning_rate": 6e-05, | |
| "loss": 1.5031, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0012795905310300703, | |
| "eval_loss": 0.4480697810649872, | |
| "eval_runtime": 51.0431, | |
| "eval_samples_per_second": 19.356, | |
| "eval_steps_per_second": 9.678, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0017061207080400938, | |
| "grad_norm": 0.7213350534439087, | |
| "learning_rate": 8e-05, | |
| "loss": 1.6767, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0021326508850501172, | |
| "grad_norm": 0.7695198059082031, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7562, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0025591810620601407, | |
| "grad_norm": 0.9236007928848267, | |
| "learning_rate": 0.00012, | |
| "loss": 1.9805, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0025591810620601407, | |
| "eval_loss": 0.4349501132965088, | |
| "eval_runtime": 51.0295, | |
| "eval_samples_per_second": 19.361, | |
| "eval_steps_per_second": 9.681, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002985711239070164, | |
| "grad_norm": 0.7685030102729797, | |
| "learning_rate": 0.00014, | |
| "loss": 1.9835, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0034122414160801876, | |
| "grad_norm": 0.780146062374115, | |
| "learning_rate": 0.00016, | |
| "loss": 1.7891, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003838771593090211, | |
| "grad_norm": 0.7326439619064331, | |
| "learning_rate": 0.00018, | |
| "loss": 1.7685, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003838771593090211, | |
| "eval_loss": 0.3959052264690399, | |
| "eval_runtime": 51.0716, | |
| "eval_samples_per_second": 19.345, | |
| "eval_steps_per_second": 9.673, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0042653017701002344, | |
| "grad_norm": 0.6148147583007812, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2899, | |
| "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": 1835906755461120.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |