| { | |
| "best_metric": 0.0013156335335224867, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.5988023952095808, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.023952095808383235, | |
| "grad_norm": 3.7263946533203125, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8484, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.023952095808383235, | |
| "eval_loss": 0.9376181364059448, | |
| "eval_runtime": 3.7013, | |
| "eval_samples_per_second": 4.863, | |
| "eval_steps_per_second": 2.432, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04790419161676647, | |
| "grad_norm": 3.7982215881347656, | |
| "learning_rate": 4e-05, | |
| "loss": 0.8896, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0718562874251497, | |
| "grad_norm": 3.451525926589966, | |
| "learning_rate": 6e-05, | |
| "loss": 0.7829, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09580838323353294, | |
| "grad_norm": 4.226587772369385, | |
| "learning_rate": 8e-05, | |
| "loss": 0.911, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.11976047904191617, | |
| "grad_norm": 3.7717223167419434, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7462, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.11976047904191617, | |
| "eval_loss": 0.5861342549324036, | |
| "eval_runtime": 2.7506, | |
| "eval_samples_per_second": 6.544, | |
| "eval_steps_per_second": 3.272, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1437125748502994, | |
| "grad_norm": 3.504315137863159, | |
| "learning_rate": 0.00012, | |
| "loss": 0.5477, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.16766467065868262, | |
| "grad_norm": 3.789900541305542, | |
| "learning_rate": 0.00014, | |
| "loss": 0.3561, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.19161676646706588, | |
| "grad_norm": 3.0215561389923096, | |
| "learning_rate": 0.00016, | |
| "loss": 0.1654, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2155688622754491, | |
| "grad_norm": 1.313277244567871, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0746, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.23952095808383234, | |
| "grad_norm": 0.9874714016914368, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0358, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.23952095808383234, | |
| "eval_loss": 0.015803173184394836, | |
| "eval_runtime": 2.7587, | |
| "eval_samples_per_second": 6.525, | |
| "eval_steps_per_second": 3.262, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2634730538922156, | |
| "grad_norm": 0.5950635075569153, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 0.0158, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2874251497005988, | |
| "grad_norm": 0.2746161222457886, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 0.0066, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.31137724550898205, | |
| "grad_norm": 0.1909645050764084, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.004, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.33532934131736525, | |
| "grad_norm": 0.0654994398355484, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.0018, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3592814371257485, | |
| "grad_norm": 0.04653725028038025, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0016, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3592814371257485, | |
| "eval_loss": 0.0017086381558328867, | |
| "eval_runtime": 2.7421, | |
| "eval_samples_per_second": 6.564, | |
| "eval_steps_per_second": 3.282, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.38323353293413176, | |
| "grad_norm": 0.05396345630288124, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0015, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.40718562874251496, | |
| "grad_norm": 0.05413348600268364, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.0018, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4311377245508982, | |
| "grad_norm": 0.045410510152578354, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.0018, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.4550898203592814, | |
| "grad_norm": 0.05225275084376335, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.0018, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.47904191616766467, | |
| "grad_norm": 0.03295710310339928, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0015, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.47904191616766467, | |
| "eval_loss": 0.0014264764031395316, | |
| "eval_runtime": 2.7392, | |
| "eval_samples_per_second": 6.571, | |
| "eval_steps_per_second": 3.286, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5029940119760479, | |
| "grad_norm": 0.03260622173547745, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 0.0014, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5269461077844312, | |
| "grad_norm": 0.028929762542247772, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.0012, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5508982035928144, | |
| "grad_norm": 0.025760218501091003, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 0.0011, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5748502994011976, | |
| "grad_norm": 0.023113111034035683, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 0.0011, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5988023952095808, | |
| "grad_norm": 0.022324662655591965, | |
| "learning_rate": 0.0, | |
| "loss": 0.0011, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5988023952095808, | |
| "eval_loss": 0.0013156335335224867, | |
| "eval_runtime": 3.108, | |
| "eval_samples_per_second": 5.791, | |
| "eval_steps_per_second": 2.896, | |
| "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": 222595409510400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |