| { | |
| "best_metric": 1.775823950767517, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-30", | |
| "epoch": 0.015887726731100223, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005295908910366742, | |
| "eval_loss": 3.4901366233825684, | |
| "eval_runtime": 229.7728, | |
| "eval_samples_per_second": 6.92, | |
| "eval_steps_per_second": 1.732, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015887726731100226, | |
| "grad_norm": 1.0055546760559082, | |
| "learning_rate": 0.00012, | |
| "loss": 2.6317, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0026479544551833707, | |
| "eval_loss": 3.3171494007110596, | |
| "eval_runtime": 230.8171, | |
| "eval_samples_per_second": 6.889, | |
| "eval_steps_per_second": 1.724, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003177545346220045, | |
| "grad_norm": 1.1987035274505615, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 2.5914, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004766318019330067, | |
| "grad_norm": 1.5815303325653076, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 2.2542, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005295908910366741, | |
| "eval_loss": 2.3986308574676514, | |
| "eval_runtime": 231.9073, | |
| "eval_samples_per_second": 6.856, | |
| "eval_steps_per_second": 1.716, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00635509069244009, | |
| "grad_norm": 1.8081384897232056, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 1.8778, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007943863365550112, | |
| "grad_norm": 3.0349438190460205, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.0174, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007943863365550112, | |
| "eval_loss": 2.0816292762756348, | |
| "eval_runtime": 230.1286, | |
| "eval_samples_per_second": 6.909, | |
| "eval_steps_per_second": 1.729, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009532636038660135, | |
| "grad_norm": 2.317234754562378, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 2.0729, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.010591817820733483, | |
| "eval_loss": 1.8730665445327759, | |
| "eval_runtime": 229.2172, | |
| "eval_samples_per_second": 6.937, | |
| "eval_steps_per_second": 1.736, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011121408711770158, | |
| "grad_norm": 1.6087003946304321, | |
| "learning_rate": 5.7422070843492734e-05, | |
| "loss": 1.7482, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01271018138488018, | |
| "grad_norm": 1.8329598903656006, | |
| "learning_rate": 2.7103137257858868e-05, | |
| "loss": 1.9398, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.013239772275916854, | |
| "eval_loss": 1.7912617921829224, | |
| "eval_runtime": 231.298, | |
| "eval_samples_per_second": 6.874, | |
| "eval_steps_per_second": 1.721, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.014298954057990202, | |
| "grad_norm": 1.8112682104110718, | |
| "learning_rate": 7.022351411174866e-06, | |
| "loss": 1.9812, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.015887726731100223, | |
| "grad_norm": 1.7277368307113647, | |
| "learning_rate": 0.0, | |
| "loss": 1.9401, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.015887726731100223, | |
| "eval_loss": 1.775823950767517, | |
| "eval_runtime": 232.2493, | |
| "eval_samples_per_second": 6.846, | |
| "eval_steps_per_second": 1.714, | |
| "step": 30 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9840583979827200.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |