| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.028089887640449437, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009363295880149813, | |
| "eval_loss": 4.221923828125, | |
| "eval_runtime": 17.2882, | |
| "eval_samples_per_second": 26.029, | |
| "eval_steps_per_second": 13.015, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0028089887640449437, | |
| "grad_norm": 4.854282855987549, | |
| "learning_rate": 3e-05, | |
| "loss": 3.7731, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0046816479400749065, | |
| "eval_loss": 3.8615503311157227, | |
| "eval_runtime": 17.3041, | |
| "eval_samples_per_second": 26.005, | |
| "eval_steps_per_second": 13.003, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0056179775280898875, | |
| "grad_norm": 5.491639614105225, | |
| "learning_rate": 6e-05, | |
| "loss": 3.4279, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008426966292134831, | |
| "grad_norm": 5.037136554718018, | |
| "learning_rate": 9e-05, | |
| "loss": 3.449, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009363295880149813, | |
| "eval_loss": 2.944920539855957, | |
| "eval_runtime": 17.3228, | |
| "eval_samples_per_second": 25.977, | |
| "eval_steps_per_second": 12.989, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011235955056179775, | |
| "grad_norm": 2.2041521072387695, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 2.7967, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.014044943820224719, | |
| "grad_norm": 3.344524621963501, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.8162, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.014044943820224719, | |
| "eval_loss": 2.658323049545288, | |
| "eval_runtime": 17.3475, | |
| "eval_samples_per_second": 25.94, | |
| "eval_steps_per_second": 12.97, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.016853932584269662, | |
| "grad_norm": 3.165560007095337, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 2.3992, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.018726591760299626, | |
| "eval_loss": 2.4839394092559814, | |
| "eval_runtime": 17.3394, | |
| "eval_samples_per_second": 25.953, | |
| "eval_steps_per_second": 12.976, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.019662921348314606, | |
| "grad_norm": 2.2143537998199463, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 2.4941, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02247191011235955, | |
| "grad_norm": 2.414954662322998, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 2.4648, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.023408239700374533, | |
| "eval_loss": 2.4180245399475098, | |
| "eval_runtime": 17.3252, | |
| "eval_samples_per_second": 25.974, | |
| "eval_steps_per_second": 12.987, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.025280898876404494, | |
| "grad_norm": 2.5250325202941895, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 2.2861, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.028089887640449437, | |
| "grad_norm": 2.655407428741455, | |
| "learning_rate": 0.0, | |
| "loss": 2.3158, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.028089887640449437, | |
| "eval_loss": 2.4034595489501953, | |
| "eval_runtime": 17.3258, | |
| "eval_samples_per_second": 25.973, | |
| "eval_steps_per_second": 12.986, | |
| "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": 3041027328835584.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |