| { | |
| "best_metric": 2.014415979385376, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.017185821697099892, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008592910848549946, | |
| "eval_loss": 2.2387137413024902, | |
| "eval_runtime": 5.7865, | |
| "eval_samples_per_second": 84.68, | |
| "eval_steps_per_second": 42.34, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0025778732545649837, | |
| "grad_norm": 3.978283405303955, | |
| "learning_rate": 0.00012, | |
| "loss": 9.4812, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004296455424274973, | |
| "eval_loss": 2.1830053329467773, | |
| "eval_runtime": 5.1809, | |
| "eval_samples_per_second": 94.578, | |
| "eval_steps_per_second": 47.289, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0051557465091299675, | |
| "grad_norm": 3.263312339782715, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 9.12, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007733619763694952, | |
| "grad_norm": 3.912200689315796, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 8.8957, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008592910848549946, | |
| "eval_loss": 2.0985138416290283, | |
| "eval_runtime": 5.237, | |
| "eval_samples_per_second": 93.565, | |
| "eval_steps_per_second": 46.783, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010311493018259935, | |
| "grad_norm": 4.199799537658691, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 8.8299, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01288936627282492, | |
| "grad_norm": 4.125592231750488, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 8.6592, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01288936627282492, | |
| "eval_loss": 2.04288911819458, | |
| "eval_runtime": 5.327, | |
| "eval_samples_per_second": 91.983, | |
| "eval_steps_per_second": 45.992, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.015467239527389903, | |
| "grad_norm": 3.9506421089172363, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 8.3345, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.017185821697099892, | |
| "eval_loss": 2.014415979385376, | |
| "eval_runtime": 5.1833, | |
| "eval_samples_per_second": 94.534, | |
| "eval_steps_per_second": 47.267, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 92689341087744.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |