| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0066945606694560665, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006694560669456067, | |
| "grad_norm": 0.34888479113578796, | |
| "learning_rate": 2e-05, | |
| "loss": 10.35, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006694560669456067, | |
| "eval_loss": 10.36190414428711, | |
| "eval_runtime": 5.6591, | |
| "eval_samples_per_second": 55.663, | |
| "eval_steps_per_second": 55.663, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013389121338912135, | |
| "grad_norm": 0.3063121736049652, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3663, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0020083682008368202, | |
| "grad_norm": 0.30662232637405396, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3876, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0020083682008368202, | |
| "eval_loss": 10.36156940460205, | |
| "eval_runtime": 5.663, | |
| "eval_samples_per_second": 55.624, | |
| "eval_steps_per_second": 55.624, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002677824267782427, | |
| "grad_norm": 0.28410905599594116, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3661, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0033472803347280333, | |
| "grad_norm": 0.2462787628173828, | |
| "learning_rate": 0.0001, | |
| "loss": 10.381, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0040167364016736404, | |
| "grad_norm": 0.22651918232440948, | |
| "learning_rate": 0.00012, | |
| "loss": 10.4118, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0040167364016736404, | |
| "eval_loss": 10.36028003692627, | |
| "eval_runtime": 8.3625, | |
| "eval_samples_per_second": 37.668, | |
| "eval_steps_per_second": 37.668, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004686192468619247, | |
| "grad_norm": 0.2924443483352661, | |
| "learning_rate": 0.00014, | |
| "loss": 10.3447, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005355648535564854, | |
| "grad_norm": 0.34267693758010864, | |
| "learning_rate": 0.00016, | |
| "loss": 10.4094, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006025104602510461, | |
| "grad_norm": 0.25677916407585144, | |
| "learning_rate": 0.00018, | |
| "loss": 10.4359, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006025104602510461, | |
| "eval_loss": 10.358124732971191, | |
| "eval_runtime": 6.2047, | |
| "eval_samples_per_second": 50.768, | |
| "eval_steps_per_second": 50.768, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0066945606694560665, | |
| "grad_norm": 0.24333161115646362, | |
| "learning_rate": 0.0002, | |
| "loss": 10.402, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 523024465920.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |