| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013836574679068337, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004612191559689446, | |
| "eval_loss": 2.5192465782165527, | |
| "eval_runtime": 70.9137, | |
| "eval_samples_per_second": 19.319, | |
| "eval_steps_per_second": 9.66, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013836574679068337, | |
| "grad_norm": 1.2828813791275024, | |
| "learning_rate": 0.00012, | |
| "loss": 2.3526, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0027673149358136673, | |
| "grad_norm": 0.6379570364952087, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 2.2248, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0036897532477515567, | |
| "eval_loss": 2.1423521041870117, | |
| "eval_runtime": 70.532, | |
| "eval_samples_per_second": 19.424, | |
| "eval_steps_per_second": 9.712, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004150972403720501, | |
| "grad_norm": 0.6265854239463806, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 2.0725, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005534629871627335, | |
| "grad_norm": 0.6093112826347351, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 1.8182, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0069182873395341685, | |
| "grad_norm": 0.7321146726608276, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.9648, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0073795064955031135, | |
| "eval_loss": 1.894142746925354, | |
| "eval_runtime": 70.5427, | |
| "eval_samples_per_second": 19.421, | |
| "eval_steps_per_second": 9.71, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008301944807441002, | |
| "grad_norm": 0.6654065847396851, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 1.893, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009685602275347836, | |
| "grad_norm": 0.612069845199585, | |
| "learning_rate": 5.7422070843492734e-05, | |
| "loss": 1.8113, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01106925974325467, | |
| "grad_norm": 0.6409688591957092, | |
| "learning_rate": 2.7103137257858868e-05, | |
| "loss": 1.697, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01106925974325467, | |
| "eval_loss": 1.803785800933838, | |
| "eval_runtime": 70.5929, | |
| "eval_samples_per_second": 19.407, | |
| "eval_steps_per_second": 9.704, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.012452917211161504, | |
| "grad_norm": 0.5429406762123108, | |
| "learning_rate": 7.022351411174866e-06, | |
| "loss": 1.8863, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.013836574679068337, | |
| "grad_norm": 0.5207058787345886, | |
| "learning_rate": 0.0, | |
| "loss": 1.8584, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6238028100009984.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |