| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.003532216760368528, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00011774055867895093, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 33.4561, | |
| "eval_samples_per_second": 106.916, | |
| "eval_steps_per_second": 53.473, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00035322167603685277, | |
| "grad_norm": 0.00012053907266817987, | |
| "learning_rate": 3e-05, | |
| "loss": 46.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007064433520737055, | |
| "grad_norm": 8.882124529918656e-05, | |
| "learning_rate": 6e-05, | |
| "loss": 46.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009419244694316074, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 33.3479, | |
| "eval_samples_per_second": 107.263, | |
| "eval_steps_per_second": 53.647, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0010596650281105584, | |
| "grad_norm": 0.00017460780509281904, | |
| "learning_rate": 9e-05, | |
| "loss": 46.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001412886704147411, | |
| "grad_norm": 0.00011067960440414026, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 46.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.001766108380184264, | |
| "grad_norm": 0.0001415925653418526, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 46.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0018838489388632149, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 33.3057, | |
| "eval_samples_per_second": 107.399, | |
| "eval_steps_per_second": 53.714, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0021193300562211167, | |
| "grad_norm": 0.00010048472177004442, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 46.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0024725517322579695, | |
| "grad_norm": 0.00010087699047289789, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 46.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.002825773408294822, | |
| "grad_norm": 0.00010204371210420504, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 46.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.002825773408294822, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 33.2973, | |
| "eval_samples_per_second": 107.426, | |
| "eval_steps_per_second": 53.728, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0031789950843316753, | |
| "grad_norm": 0.0001002256540232338, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 46.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.003532216760368528, | |
| "grad_norm": 9.665413381299004e-05, | |
| "learning_rate": 0.0, | |
| "loss": 46.0, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1196882657280.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |