| { | |
| "best_metric": 11.929529190063477, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-30", | |
| "epoch": 0.06944444444444445, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0023148148148148147, | |
| "eval_loss": 11.930611610412598, | |
| "eval_runtime": 1.598, | |
| "eval_samples_per_second": 227.79, | |
| "eval_steps_per_second": 56.948, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006944444444444444, | |
| "grad_norm": 0.02261943556368351, | |
| "learning_rate": 0.00012, | |
| "loss": 11.9246, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.011574074074074073, | |
| "eval_loss": 11.930468559265137, | |
| "eval_runtime": 1.6073, | |
| "eval_samples_per_second": 226.461, | |
| "eval_steps_per_second": 56.615, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013888888888888888, | |
| "grad_norm": 0.01975701004266739, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 11.9281, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.020833333333333332, | |
| "grad_norm": 0.017253711819648743, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 11.9262, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.023148148148148147, | |
| "eval_loss": 11.930161476135254, | |
| "eval_runtime": 1.5999, | |
| "eval_samples_per_second": 227.509, | |
| "eval_steps_per_second": 56.877, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.027777777777777776, | |
| "grad_norm": 0.023446418344974518, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 11.9293, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.034722222222222224, | |
| "grad_norm": 0.02882510796189308, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 11.9301, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.034722222222222224, | |
| "eval_loss": 11.929879188537598, | |
| "eval_runtime": 1.6311, | |
| "eval_samples_per_second": 223.163, | |
| "eval_steps_per_second": 55.791, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.041666666666666664, | |
| "grad_norm": 0.030566686764359474, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 11.9306, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.046296296296296294, | |
| "eval_loss": 11.92967414855957, | |
| "eval_runtime": 1.6038, | |
| "eval_samples_per_second": 226.954, | |
| "eval_steps_per_second": 56.739, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04861111111111111, | |
| "grad_norm": 0.029043123126029968, | |
| "learning_rate": 5.7422070843492734e-05, | |
| "loss": 11.9315, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05555555555555555, | |
| "grad_norm": 0.025579649955034256, | |
| "learning_rate": 2.7103137257858868e-05, | |
| "loss": 11.9287, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05787037037037037, | |
| "eval_loss": 11.9295654296875, | |
| "eval_runtime": 1.6087, | |
| "eval_samples_per_second": 226.27, | |
| "eval_steps_per_second": 56.568, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0625, | |
| "grad_norm": 0.0232111643999815, | |
| "learning_rate": 7.022351411174866e-06, | |
| "loss": 11.9299, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06944444444444445, | |
| "grad_norm": 0.02337847463786602, | |
| "learning_rate": 0.0, | |
| "loss": 11.9304, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06944444444444445, | |
| "eval_loss": 11.929529190063477, | |
| "eval_runtime": 1.6127, | |
| "eval_samples_per_second": 225.703, | |
| "eval_steps_per_second": 56.426, | |
| "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": 22484090880.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |