| { | |
| "best_metric": 1.1055667400360107, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.6451612903225806, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.025806451612903226, | |
| "grad_norm": 0.8220058083534241, | |
| "learning_rate": 5e-05, | |
| "loss": 2.036, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.025806451612903226, | |
| "eval_loss": 1.9736554622650146, | |
| "eval_runtime": 2.9976, | |
| "eval_samples_per_second": 87.403, | |
| "eval_steps_per_second": 11.009, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05161290322580645, | |
| "grad_norm": 0.9786584377288818, | |
| "learning_rate": 0.0001, | |
| "loss": 1.953, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07741935483870968, | |
| "grad_norm": 1.0898869037628174, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.8547, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1032258064516129, | |
| "grad_norm": 0.9177775979042053, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.6855, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.12903225806451613, | |
| "grad_norm": 1.0047584772109985, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.4721, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.15483870967741936, | |
| "grad_norm": 1.099215030670166, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.4536, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.18064516129032257, | |
| "grad_norm": 1.1849559545516968, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.3585, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2064516129032258, | |
| "grad_norm": 1.0470384359359741, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.2279, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.23225806451612904, | |
| "grad_norm": 0.8208673000335693, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.9951, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.25806451612903225, | |
| "grad_norm": 1.2860324382781982, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.659, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2838709677419355, | |
| "grad_norm": 1.092450499534607, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.56, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3096774193548387, | |
| "grad_norm": 0.6195999383926392, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.4472, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.33548387096774196, | |
| "grad_norm": 0.7615762948989868, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.3041, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.36129032258064514, | |
| "grad_norm": 0.8887320160865784, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.0784, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3870967741935484, | |
| "grad_norm": 0.7487991452217102, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.0261, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.4129032258064516, | |
| "grad_norm": 0.6079425811767578, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.0409, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.43870967741935485, | |
| "grad_norm": 0.5330397486686707, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.002, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4645161290322581, | |
| "grad_norm": 0.6109048128128052, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.9235, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.49032258064516127, | |
| "grad_norm": 0.6474350690841675, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.7902, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5161290322580645, | |
| "grad_norm": 0.8159425854682922, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6519, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5419354838709678, | |
| "grad_norm": 0.7559259533882141, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.4361, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.567741935483871, | |
| "grad_norm": 0.6141023635864258, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.2908, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5935483870967742, | |
| "grad_norm": 0.523212730884552, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.1428, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.6193548387096774, | |
| "grad_norm": 0.46284154057502747, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.0109, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6451612903225806, | |
| "grad_norm": 0.5253970623016357, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.0057, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6451612903225806, | |
| "eval_loss": 1.1055667400360107, | |
| "eval_runtime": 2.9956, | |
| "eval_samples_per_second": 87.462, | |
| "eval_steps_per_second": 11.016, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.29768176943104e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |