| { | |
| "best_metric": 3.6232075691223145, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.003885003885003885, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001554001554001554, | |
| "grad_norm": 2.5673227310180664, | |
| "learning_rate": 2e-05, | |
| "loss": 5.5472, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001554001554001554, | |
| "eval_loss": 5.986268520355225, | |
| "eval_runtime": 566.3771, | |
| "eval_samples_per_second": 4.785, | |
| "eval_steps_per_second": 2.392, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003108003108003108, | |
| "grad_norm": 1.6972694396972656, | |
| "learning_rate": 4e-05, | |
| "loss": 4.2218, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0004662004662004662, | |
| "grad_norm": 2.8526394367218018, | |
| "learning_rate": 6e-05, | |
| "loss": 5.9584, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006216006216006216, | |
| "grad_norm": 2.478783369064331, | |
| "learning_rate": 8e-05, | |
| "loss": 6.3449, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.000777000777000777, | |
| "grad_norm": 1.8824713230133057, | |
| "learning_rate": 0.0001, | |
| "loss": 4.375, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000777000777000777, | |
| "eval_loss": 5.915567398071289, | |
| "eval_runtime": 564.1912, | |
| "eval_samples_per_second": 4.803, | |
| "eval_steps_per_second": 2.402, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009324009324009324, | |
| "grad_norm": 3.456815719604492, | |
| "learning_rate": 0.00012, | |
| "loss": 5.8716, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010878010878010878, | |
| "grad_norm": 2.796623945236206, | |
| "learning_rate": 0.00014, | |
| "loss": 4.7266, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0012432012432012432, | |
| "grad_norm": 3.301687479019165, | |
| "learning_rate": 0.00016, | |
| "loss": 5.6329, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0013986013986013986, | |
| "grad_norm": 3.4667627811431885, | |
| "learning_rate": 0.00018, | |
| "loss": 4.7288, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001554001554001554, | |
| "grad_norm": 3.678271770477295, | |
| "learning_rate": 0.0002, | |
| "loss": 4.7863, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001554001554001554, | |
| "eval_loss": 4.775293827056885, | |
| "eval_runtime": 567.9607, | |
| "eval_samples_per_second": 4.771, | |
| "eval_steps_per_second": 2.386, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0017094017094017094, | |
| "grad_norm": 4.809173583984375, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 5.2656, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0018648018648018648, | |
| "grad_norm": 3.9845523834228516, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 4.2018, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00202020202020202, | |
| "grad_norm": 5.280404090881348, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 3.6398, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0021756021756021756, | |
| "grad_norm": 6.346953868865967, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 4.059, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.002331002331002331, | |
| "grad_norm": 6.631599426269531, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 3.5895, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002331002331002331, | |
| "eval_loss": 3.8978869915008545, | |
| "eval_runtime": 566.1304, | |
| "eval_samples_per_second": 4.787, | |
| "eval_steps_per_second": 2.393, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0024864024864024864, | |
| "grad_norm": 7.2223639488220215, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 3.8472, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002641802641802642, | |
| "grad_norm": 5.9055914878845215, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 3.7537, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.002797202797202797, | |
| "grad_norm": 6.683732986450195, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 3.7141, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0029526029526029526, | |
| "grad_norm": 5.297791481018066, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 3.7497, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.003108003108003108, | |
| "grad_norm": 6.327470779418945, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 3.485, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003108003108003108, | |
| "eval_loss": 3.669083595275879, | |
| "eval_runtime": 566.2418, | |
| "eval_samples_per_second": 4.786, | |
| "eval_steps_per_second": 2.393, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0032634032634032634, | |
| "grad_norm": 5.759369373321533, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 3.7142, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003418803418803419, | |
| "grad_norm": 5.7423415184021, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 3.8142, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.003574203574203574, | |
| "grad_norm": 5.087298393249512, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 3.4748, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0037296037296037296, | |
| "grad_norm": 4.315537929534912, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 3.5559, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003885003885003885, | |
| "grad_norm": 4.743892192840576, | |
| "learning_rate": 0.0, | |
| "loss": 3.7569, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.003885003885003885, | |
| "eval_loss": 3.6232075691223145, | |
| "eval_runtime": 568.0455, | |
| "eval_samples_per_second": 4.771, | |
| "eval_steps_per_second": 2.385, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "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": 6889626824343552.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |