| { | |
| "best_metric": 1.7028899192810059, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.0019612842489261967, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.845136995704788e-05, | |
| "grad_norm": 0.9734085202217102, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1146, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.845136995704788e-05, | |
| "eval_loss": 2.1862733364105225, | |
| "eval_runtime": 1765.745, | |
| "eval_samples_per_second": 3.04, | |
| "eval_steps_per_second": 1.52, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00015690273991409576, | |
| "grad_norm": 1.1216297149658203, | |
| "learning_rate": 4e-05, | |
| "loss": 2.4345, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00023535410987114363, | |
| "grad_norm": 1.157699465751648, | |
| "learning_rate": 6e-05, | |
| "loss": 2.1212, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003138054798281915, | |
| "grad_norm": 1.105882167816162, | |
| "learning_rate": 8e-05, | |
| "loss": 2.0143, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00039225684978523936, | |
| "grad_norm": 0.8526667952537537, | |
| "learning_rate": 0.0001, | |
| "loss": 2.2834, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00039225684978523936, | |
| "eval_loss": 2.1460585594177246, | |
| "eval_runtime": 1768.6661, | |
| "eval_samples_per_second": 3.035, | |
| "eval_steps_per_second": 1.518, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00047070821974228727, | |
| "grad_norm": 0.9058842062950134, | |
| "learning_rate": 0.00012, | |
| "loss": 2.1771, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005491595896993352, | |
| "grad_norm": 0.7835561037063599, | |
| "learning_rate": 0.00014, | |
| "loss": 2.1572, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.000627610959656383, | |
| "grad_norm": 0.7639698386192322, | |
| "learning_rate": 0.00016, | |
| "loss": 1.8649, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007060623296134309, | |
| "grad_norm": 0.6497108936309814, | |
| "learning_rate": 0.00018, | |
| "loss": 2.1549, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007845136995704787, | |
| "grad_norm": 1.7419626712799072, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9657, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007845136995704787, | |
| "eval_loss": 1.9750728607177734, | |
| "eval_runtime": 1790.5683, | |
| "eval_samples_per_second": 2.998, | |
| "eval_steps_per_second": 1.499, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008629650695275266, | |
| "grad_norm": 0.8262554407119751, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 2.0639, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0009414164394845745, | |
| "grad_norm": 1.002493143081665, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 1.8902, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0010198678094416223, | |
| "grad_norm": 0.8235588073730469, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.8743, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0010983191793986703, | |
| "grad_norm": 0.91981041431427, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 1.9061, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0011767705493557182, | |
| "grad_norm": 0.7380278706550598, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.9508, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0011767705493557182, | |
| "eval_loss": 1.8117865324020386, | |
| "eval_runtime": 1768.5844, | |
| "eval_samples_per_second": 3.035, | |
| "eval_steps_per_second": 1.518, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.001255221919312766, | |
| "grad_norm": 0.757776141166687, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.7871, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.001333673289269814, | |
| "grad_norm": 0.7072300314903259, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.6816, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0014121246592268617, | |
| "grad_norm": 0.7770305871963501, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.566, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0014905760291839096, | |
| "grad_norm": 0.8346571326255798, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.6497, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0015690273991409574, | |
| "grad_norm": 0.7390028238296509, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.8454, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0015690273991409574, | |
| "eval_loss": 1.7211201190948486, | |
| "eval_runtime": 1788.6648, | |
| "eval_samples_per_second": 3.001, | |
| "eval_steps_per_second": 1.501, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0016474787690980053, | |
| "grad_norm": 0.7469911575317383, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 1.6775, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0017259301390550531, | |
| "grad_norm": 0.8389664888381958, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 1.5515, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0018043815090121012, | |
| "grad_norm": 0.7729347348213196, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 1.6718, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.001882832878969149, | |
| "grad_norm": 0.998233437538147, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 1.7309, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0019612842489261967, | |
| "grad_norm": 0.9571971297264099, | |
| "learning_rate": 0.0, | |
| "loss": 1.6594, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0019612842489261967, | |
| "eval_loss": 1.7028899192810059, | |
| "eval_runtime": 1794.3519, | |
| "eval_samples_per_second": 2.992, | |
| "eval_steps_per_second": 1.496, | |
| "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": 1.013847699750912e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |