| { | |
| "best_metric": 0.5158158540725708, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.07766990291262135, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003883495145631068, | |
| "eval_loss": 1.0717418193817139, | |
| "eval_runtime": 17.149, | |
| "eval_samples_per_second": 12.654, | |
| "eval_steps_per_second": 3.207, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011650485436893204, | |
| "grad_norm": 0.9641898274421692, | |
| "learning_rate": 0.00012, | |
| "loss": 2.9964, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.019417475728155338, | |
| "eval_loss": 0.9520554542541504, | |
| "eval_runtime": 17.1006, | |
| "eval_samples_per_second": 12.69, | |
| "eval_steps_per_second": 3.216, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02330097087378641, | |
| "grad_norm": 0.9554243087768555, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 3.0132, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03495145631067961, | |
| "grad_norm": 1.0470486879348755, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 2.5962, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.038834951456310676, | |
| "eval_loss": 0.678810179233551, | |
| "eval_runtime": 17.1964, | |
| "eval_samples_per_second": 12.619, | |
| "eval_steps_per_second": 3.198, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04660194174757282, | |
| "grad_norm": 2.3093507289886475, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 2.4677, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05825242718446602, | |
| "grad_norm": 1.2664294242858887, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.2427, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05825242718446602, | |
| "eval_loss": 0.5657013654708862, | |
| "eval_runtime": 17.2405, | |
| "eval_samples_per_second": 12.587, | |
| "eval_steps_per_second": 3.19, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06990291262135923, | |
| "grad_norm": 1.203683853149414, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 2.3629, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07766990291262135, | |
| "eval_loss": 0.5158158540725708, | |
| "eval_runtime": 17.1662, | |
| "eval_samples_per_second": 12.641, | |
| "eval_steps_per_second": 3.204, | |
| "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": 2.53913198493696e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |