| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.23121387283236994, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004624277456647399, | |
| "eval_loss": 8.338584899902344, | |
| "eval_runtime": 4.6061, | |
| "eval_samples_per_second": 19.973, | |
| "eval_steps_per_second": 9.987, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.023121387283236993, | |
| "grad_norm": 11.315285682678223, | |
| "learning_rate": 5e-05, | |
| "loss": 8.4925, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.046242774566473986, | |
| "grad_norm": 14.791265487670898, | |
| "learning_rate": 0.0001, | |
| "loss": 7.152, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.046242774566473986, | |
| "eval_loss": 4.882205963134766, | |
| "eval_runtime": 4.3487, | |
| "eval_samples_per_second": 21.156, | |
| "eval_steps_per_second": 10.578, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06936416184971098, | |
| "grad_norm": 7.700483322143555, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.7382, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09248554913294797, | |
| "grad_norm": 6.397822380065918, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.9039, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09248554913294797, | |
| "eval_loss": 1.7941486835479736, | |
| "eval_runtime": 4.43, | |
| "eval_samples_per_second": 20.767, | |
| "eval_steps_per_second": 10.384, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11560693641618497, | |
| "grad_norm": 8.176989555358887, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6807, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13872832369942195, | |
| "grad_norm": 6.075613975524902, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0513, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13872832369942195, | |
| "eval_loss": 1.3676693439483643, | |
| "eval_runtime": 4.4418, | |
| "eval_samples_per_second": 20.712, | |
| "eval_steps_per_second": 10.356, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.16184971098265896, | |
| "grad_norm": 6.693606376647949, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.388, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.18497109826589594, | |
| "grad_norm": 7.144972801208496, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.3442, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.18497109826589594, | |
| "eval_loss": 1.1969767808914185, | |
| "eval_runtime": 4.4389, | |
| "eval_samples_per_second": 20.726, | |
| "eval_steps_per_second": 10.363, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.20809248554913296, | |
| "grad_norm": 13.571349143981934, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.1415, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.23121387283236994, | |
| "grad_norm": 5.618630409240723, | |
| "learning_rate": 0.0, | |
| "loss": 1.2559, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.23121387283236994, | |
| "eval_loss": 1.1580039262771606, | |
| "eval_runtime": 4.4498, | |
| "eval_samples_per_second": 20.675, | |
| "eval_steps_per_second": 10.338, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4817785906790400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |