| { | |
| "best_metric": 11.01673698425293, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.06565988181221274, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0026263952724885093, | |
| "grad_norm": 2.4949302673339844, | |
| "learning_rate": 2e-05, | |
| "loss": 44.3388, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0026263952724885093, | |
| "eval_loss": 11.082923889160156, | |
| "eval_runtime": 2.1167, | |
| "eval_samples_per_second": 76.061, | |
| "eval_steps_per_second": 38.267, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005252790544977019, | |
| "grad_norm": 2.787014961242676, | |
| "learning_rate": 4e-05, | |
| "loss": 44.2647, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007879185817465528, | |
| "grad_norm": 2.6643102169036865, | |
| "learning_rate": 6e-05, | |
| "loss": 44.3388, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010505581089954037, | |
| "grad_norm": 2.3826050758361816, | |
| "learning_rate": 8e-05, | |
| "loss": 44.3201, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013131976362442548, | |
| "grad_norm": 2.5090649127960205, | |
| "learning_rate": 0.0001, | |
| "loss": 44.2966, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013131976362442548, | |
| "eval_loss": 11.073081016540527, | |
| "eval_runtime": 1.1203, | |
| "eval_samples_per_second": 143.712, | |
| "eval_steps_per_second": 72.302, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015758371634931056, | |
| "grad_norm": 2.7648870944976807, | |
| "learning_rate": 0.00012, | |
| "loss": 44.2765, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.018384766907419567, | |
| "grad_norm": 2.6025547981262207, | |
| "learning_rate": 0.00014, | |
| "loss": 44.2209, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.021011162179908074, | |
| "grad_norm": 2.590778112411499, | |
| "learning_rate": 0.00016, | |
| "loss": 44.2336, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.023637557452396585, | |
| "grad_norm": 2.608997106552124, | |
| "learning_rate": 0.00018, | |
| "loss": 44.2379, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.026263952724885097, | |
| "grad_norm": 2.559065103530884, | |
| "learning_rate": 0.0002, | |
| "loss": 44.202, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.026263952724885097, | |
| "eval_loss": 11.054951667785645, | |
| "eval_runtime": 1.0892, | |
| "eval_samples_per_second": 147.808, | |
| "eval_steps_per_second": 74.363, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.028890347997373604, | |
| "grad_norm": 2.563385486602783, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 44.1917, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03151674326986211, | |
| "grad_norm": 2.538567543029785, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 44.1742, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.034143138542350626, | |
| "grad_norm": 2.0529396533966064, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 44.2301, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.036769533814839134, | |
| "grad_norm": 2.5738186836242676, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 44.1165, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03939592908732764, | |
| "grad_norm": 2.3740193843841553, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 44.1275, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03939592908732764, | |
| "eval_loss": 11.034344673156738, | |
| "eval_runtime": 1.1138, | |
| "eval_samples_per_second": 144.552, | |
| "eval_steps_per_second": 72.725, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04202232435981615, | |
| "grad_norm": 2.6196210384368896, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 44.0825, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04464871963230466, | |
| "grad_norm": 2.2003798484802246, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 44.1069, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04727511490479317, | |
| "grad_norm": 2.1585779190063477, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 44.118, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04990151017728168, | |
| "grad_norm": 2.2526192665100098, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 44.0871, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05252790544977019, | |
| "grad_norm": 2.091240167617798, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 44.1213, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05252790544977019, | |
| "eval_loss": 11.020662307739258, | |
| "eval_runtime": 1.094, | |
| "eval_samples_per_second": 147.166, | |
| "eval_steps_per_second": 74.04, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0551543007222587, | |
| "grad_norm": 2.2587475776672363, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 44.0764, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05778069599474721, | |
| "grad_norm": 2.196699857711792, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 44.0714, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.060407091267235716, | |
| "grad_norm": 2.251181125640869, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 44.0403, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06303348653972422, | |
| "grad_norm": 2.1408016681671143, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 44.0624, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06565988181221274, | |
| "grad_norm": 2.081577777862549, | |
| "learning_rate": 0.0, | |
| "loss": 44.0454, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06565988181221274, | |
| "eval_loss": 11.01673698425293, | |
| "eval_runtime": 1.1654, | |
| "eval_samples_per_second": 138.15, | |
| "eval_steps_per_second": 69.504, | |
| "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": 36981964800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |