| { | |
| "best_metric": 11.929757118225098, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-30", | |
| "epoch": 0.030503304524656837, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010167768174885613, | |
| "eval_loss": 11.931282997131348, | |
| "eval_runtime": 11.4254, | |
| "eval_samples_per_second": 36.323, | |
| "eval_steps_per_second": 18.205, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003050330452465684, | |
| "grad_norm": 0.033007942140102386, | |
| "learning_rate": 0.00012, | |
| "loss": 11.9303, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005083884087442806, | |
| "eval_loss": 11.931082725524902, | |
| "eval_runtime": 12.2714, | |
| "eval_samples_per_second": 33.818, | |
| "eval_steps_per_second": 16.95, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006100660904931368, | |
| "grad_norm": 0.034894056618213654, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 11.931, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009150991357397052, | |
| "grad_norm": 0.02531345933675766, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 11.9333, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010167768174885612, | |
| "eval_loss": 11.93061351776123, | |
| "eval_runtime": 12.0789, | |
| "eval_samples_per_second": 34.357, | |
| "eval_steps_per_second": 17.22, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012201321809862735, | |
| "grad_norm": 0.027055680751800537, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 11.9299, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.015251652262328419, | |
| "grad_norm": 0.049009058624506, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 11.9281, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.015251652262328419, | |
| "eval_loss": 11.930212020874023, | |
| "eval_runtime": 11.7264, | |
| "eval_samples_per_second": 35.39, | |
| "eval_steps_per_second": 17.738, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.018301982714794104, | |
| "grad_norm": 0.0452025905251503, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 11.9301, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.020335536349771224, | |
| "eval_loss": 11.929913520812988, | |
| "eval_runtime": 12.0694, | |
| "eval_samples_per_second": 34.385, | |
| "eval_steps_per_second": 17.234, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.021352313167259787, | |
| "grad_norm": 0.03248075395822525, | |
| "learning_rate": 5.7422070843492734e-05, | |
| "loss": 11.9307, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02440264361972547, | |
| "grad_norm": 0.023889845237135887, | |
| "learning_rate": 2.7103137257858868e-05, | |
| "loss": 11.9311, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02541942043721403, | |
| "eval_loss": 11.929779052734375, | |
| "eval_runtime": 12.1206, | |
| "eval_samples_per_second": 34.239, | |
| "eval_steps_per_second": 17.161, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.027452974072191154, | |
| "grad_norm": 0.03272699564695358, | |
| "learning_rate": 7.022351411174866e-06, | |
| "loss": 11.9295, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.030503304524656837, | |
| "grad_norm": 0.023512979969382286, | |
| "learning_rate": 0.0, | |
| "loss": 11.9302, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.030503304524656837, | |
| "eval_loss": 11.929757118225098, | |
| "eval_runtime": 12.1269, | |
| "eval_samples_per_second": 34.221, | |
| "eval_steps_per_second": 17.152, | |
| "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": 16956751872.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |