| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.018733608092918696, | |
| "eval_steps": 7, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007493443237167478, | |
| "eval_loss": 2.3033459186553955, | |
| "eval_runtime": 73.358, | |
| "eval_samples_per_second": 7.661, | |
| "eval_steps_per_second": 3.831, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022480329711502436, | |
| "grad_norm": 2.117216110229492, | |
| "learning_rate": 6e-05, | |
| "loss": 2.0385, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004496065942300487, | |
| "grad_norm": 3.228360652923584, | |
| "learning_rate": 0.00012, | |
| "loss": 2.0083, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005245410266017235, | |
| "eval_loss": 1.7331812381744385, | |
| "eval_runtime": 73.8388, | |
| "eval_samples_per_second": 7.611, | |
| "eval_steps_per_second": 3.806, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0067440989134507304, | |
| "grad_norm": 4.592715263366699, | |
| "learning_rate": 0.00018, | |
| "loss": 1.4491, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008992131884600974, | |
| "grad_norm": 1.454011082649231, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 1.159, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01049082053203447, | |
| "eval_loss": 1.1324224472045898, | |
| "eval_runtime": 73.8035, | |
| "eval_samples_per_second": 7.615, | |
| "eval_steps_per_second": 3.807, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.011240164855751217, | |
| "grad_norm": 2.542600631713867, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.1481, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013488197826901461, | |
| "grad_norm": 2.1977767944335938, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.9791, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.015736230798051705, | |
| "grad_norm": 1.9634613990783691, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 1.0128, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.015736230798051705, | |
| "eval_loss": 0.997219979763031, | |
| "eval_runtime": 73.8265, | |
| "eval_samples_per_second": 7.612, | |
| "eval_steps_per_second": 3.806, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01798426376920195, | |
| "grad_norm": 2.080848455429077, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 0.9633, | |
| "step": 24 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 30, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9273591044505600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |