| { | |
| "best_metric": 4.565509796142578, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.0010716735253772291, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.286694101508916e-05, | |
| "eval_loss": 5.070206165313721, | |
| "eval_runtime": 190.0249, | |
| "eval_samples_per_second": 12.925, | |
| "eval_steps_per_second": 6.462, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001286008230452675, | |
| "grad_norm": 142.68789672851562, | |
| "learning_rate": 6e-05, | |
| "loss": 4.9754, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002143347050754458, | |
| "eval_loss": 5.033393383026123, | |
| "eval_runtime": 188.1953, | |
| "eval_samples_per_second": 13.05, | |
| "eval_steps_per_second": 6.525, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000257201646090535, | |
| "grad_norm": 130.1358184814453, | |
| "learning_rate": 0.00012, | |
| "loss": 5.0293, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00038580246913580245, | |
| "grad_norm": 107.51341247558594, | |
| "learning_rate": 0.00018, | |
| "loss": 5.0896, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0004286694101508916, | |
| "eval_loss": 4.878531455993652, | |
| "eval_runtime": 186.2306, | |
| "eval_samples_per_second": 13.188, | |
| "eval_steps_per_second": 6.594, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00051440329218107, | |
| "grad_norm": 98.51611328125, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 4.8034, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0006430041152263374, | |
| "grad_norm": 77.14884185791016, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 5.3444, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0006430041152263374, | |
| "eval_loss": 4.691795825958252, | |
| "eval_runtime": 190.2025, | |
| "eval_samples_per_second": 12.913, | |
| "eval_steps_per_second": 6.456, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0007716049382716049, | |
| "grad_norm": 75.92028045654297, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 4.3554, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0008573388203017832, | |
| "eval_loss": 4.590373992919922, | |
| "eval_runtime": 190.5313, | |
| "eval_samples_per_second": 12.89, | |
| "eval_steps_per_second": 6.445, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0009002057613168725, | |
| "grad_norm": 87.71182250976562, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 4.5126, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00102880658436214, | |
| "grad_norm": 113.87626647949219, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 4.689, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0010716735253772291, | |
| "eval_loss": 4.565509796142578, | |
| "eval_runtime": 187.3875, | |
| "eval_samples_per_second": 13.107, | |
| "eval_steps_per_second": 6.553, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 110627074867200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |