| { | |
| "best_metric": 10.343125343322754, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6808510638297872, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013617021276595745, | |
| "grad_norm": 31.260223388671875, | |
| "learning_rate": 5e-05, | |
| "loss": 179.1719, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013617021276595745, | |
| "eval_loss": 11.210249900817871, | |
| "eval_runtime": 0.7004, | |
| "eval_samples_per_second": 71.388, | |
| "eval_steps_per_second": 18.561, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02723404255319149, | |
| "grad_norm": 38.27791213989258, | |
| "learning_rate": 0.0001, | |
| "loss": 179.33, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04085106382978723, | |
| "grad_norm": 34.22037124633789, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 179.0171, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05446808510638298, | |
| "grad_norm": 32.08433151245117, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 178.1888, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06808510638297872, | |
| "grad_norm": 30.398303985595703, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 177.8481, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08170212765957446, | |
| "grad_norm": 29.144142150878906, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 177.4651, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09531914893617022, | |
| "grad_norm": 30.449281692504883, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 176.808, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10893617021276596, | |
| "grad_norm": 29.39048957824707, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 176.475, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1225531914893617, | |
| "grad_norm": 30.308015823364258, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 175.9786, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13617021276595745, | |
| "grad_norm": 29.521896362304688, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 175.0975, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1497872340425532, | |
| "grad_norm": 29.471303939819336, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 174.9922, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.16340425531914893, | |
| "grad_norm": 29.049652099609375, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 174.6531, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.17702127659574468, | |
| "grad_norm": 29.36743927001953, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 175.1359, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.19063829787234043, | |
| "grad_norm": 38.21333694458008, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 172.7683, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.20425531914893616, | |
| "grad_norm": 36.98329162597656, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 172.4297, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2178723404255319, | |
| "grad_norm": 33.906951904296875, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 172.1532, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.23148936170212767, | |
| "grad_norm": 32.73712921142578, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 172.097, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2451063829787234, | |
| "grad_norm": 33.81500244140625, | |
| "learning_rate": 7.75e-05, | |
| "loss": 171.3027, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.25872340425531914, | |
| "grad_norm": 31.76679229736328, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 171.3058, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2723404255319149, | |
| "grad_norm": 31.578975677490234, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 170.9581, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.28595744680851065, | |
| "grad_norm": 30.295276641845703, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 170.86, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2995744680851064, | |
| "grad_norm": 31.39499855041504, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 170.3138, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3131914893617021, | |
| "grad_norm": 29.06229019165039, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 170.4506, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.32680851063829786, | |
| "grad_norm": 30.135881423950195, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 169.6599, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3404255319148936, | |
| "grad_norm": 30.49418830871582, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 171.7904, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3404255319148936, | |
| "eval_loss": 10.581374168395996, | |
| "eval_runtime": 0.353, | |
| "eval_samples_per_second": 141.661, | |
| "eval_steps_per_second": 36.832, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.35404255319148936, | |
| "grad_norm": 33.990882873535156, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 168.028, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3676595744680851, | |
| "grad_norm": 35.0228385925293, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 167.0524, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.38127659574468087, | |
| "grad_norm": 33.29133224487305, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 167.292, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3948936170212766, | |
| "grad_norm": 31.941789627075195, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 167.1951, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.4085106382978723, | |
| "grad_norm": 30.474773406982422, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 167.147, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4221276595744681, | |
| "grad_norm": 30.455781936645508, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 166.9363, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4357446808510638, | |
| "grad_norm": 29.7111873626709, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 166.833, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4493617021276596, | |
| "grad_norm": 29.804931640625, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 166.6142, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.46297872340425533, | |
| "grad_norm": 29.273719787597656, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 166.5084, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.4765957446808511, | |
| "grad_norm": 28.390575408935547, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 166.8301, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4902127659574468, | |
| "grad_norm": 28.319622039794922, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 166.4397, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5038297872340426, | |
| "grad_norm": 27.683088302612305, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 166.8986, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5174468085106383, | |
| "grad_norm": 33.09490203857422, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 169.1795, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.531063829787234, | |
| "grad_norm": 32.074981689453125, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 164.2301, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5446808510638298, | |
| "grad_norm": 34.14289474487305, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 163.6617, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5582978723404255, | |
| "grad_norm": 29.819684982299805, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 164.8387, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5719148936170213, | |
| "grad_norm": 29.242847442626953, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 164.9634, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.585531914893617, | |
| "grad_norm": 29.04056167602539, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 164.6975, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5991489361702128, | |
| "grad_norm": 28.505887985229492, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 164.7266, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6127659574468085, | |
| "grad_norm": 28.198604583740234, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 164.8328, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6263829787234042, | |
| "grad_norm": 27.653589248657227, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 165.505, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 27.47649383544922, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 164.8701, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6536170212765957, | |
| "grad_norm": 27.234596252441406, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 165.0507, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6672340425531915, | |
| "grad_norm": 26.7624454498291, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 165.8583, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6808510638297872, | |
| "grad_norm": 34.30644607543945, | |
| "learning_rate": 1e-05, | |
| "loss": 169.6575, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6808510638297872, | |
| "eval_loss": 10.343125343322754, | |
| "eval_runtime": 0.3469, | |
| "eval_samples_per_second": 144.115, | |
| "eval_steps_per_second": 37.47, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "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": 38111123865600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |