| { | |
| "best_metric": 1.4121884107589722, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.05830903790087463, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0023323615160349854, | |
| "grad_norm": 1.5346574783325195, | |
| "learning_rate": 2e-05, | |
| "loss": 2.2105, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0023323615160349854, | |
| "eval_loss": 1.6742810010910034, | |
| "eval_runtime": 36.5226, | |
| "eval_samples_per_second": 4.956, | |
| "eval_steps_per_second": 2.492, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004664723032069971, | |
| "grad_norm": 1.4139418601989746, | |
| "learning_rate": 4e-05, | |
| "loss": 1.4349, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006997084548104956, | |
| "grad_norm": 0.9706037044525146, | |
| "learning_rate": 6e-05, | |
| "loss": 0.9538, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009329446064139942, | |
| "grad_norm": 1.288402795791626, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5789, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011661807580174927, | |
| "grad_norm": 1.1371190547943115, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4299, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.011661807580174927, | |
| "eval_loss": 1.5869524478912354, | |
| "eval_runtime": 36.6166, | |
| "eval_samples_per_second": 4.943, | |
| "eval_steps_per_second": 2.485, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013994169096209912, | |
| "grad_norm": 1.3522026538848877, | |
| "learning_rate": 0.00012, | |
| "loss": 2.1149, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0163265306122449, | |
| "grad_norm": 0.786292314529419, | |
| "learning_rate": 0.00014, | |
| "loss": 1.0683, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.018658892128279883, | |
| "grad_norm": 0.6935855150222778, | |
| "learning_rate": 0.00016, | |
| "loss": 1.747, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02099125364431487, | |
| "grad_norm": 0.5766379237174988, | |
| "learning_rate": 0.00018, | |
| "loss": 1.4661, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.023323615160349854, | |
| "grad_norm": 0.5700016021728516, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0889, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.023323615160349854, | |
| "eval_loss": 1.4536380767822266, | |
| "eval_runtime": 36.7676, | |
| "eval_samples_per_second": 4.923, | |
| "eval_steps_per_second": 2.475, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02565597667638484, | |
| "grad_norm": 0.7684414982795715, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 1.7667, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.027988338192419825, | |
| "grad_norm": 0.6388105154037476, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 1.0316, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.030320699708454812, | |
| "grad_norm": 0.6296985149383545, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.4975, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0326530612244898, | |
| "grad_norm": 0.39826327562332153, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.9386, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03498542274052478, | |
| "grad_norm": 0.5714980363845825, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.6855, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03498542274052478, | |
| "eval_loss": 1.4195315837860107, | |
| "eval_runtime": 36.5975, | |
| "eval_samples_per_second": 4.946, | |
| "eval_steps_per_second": 2.487, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.037317784256559766, | |
| "grad_norm": 0.6020028591156006, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.8779, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03965014577259475, | |
| "grad_norm": 0.49338093400001526, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.465, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04198250728862974, | |
| "grad_norm": 0.7286747694015503, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.2786, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.044314868804664724, | |
| "grad_norm": 0.5588726997375488, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.398, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04664723032069971, | |
| "grad_norm": 0.5118404626846313, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.3029, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04664723032069971, | |
| "eval_loss": 1.4150354862213135, | |
| "eval_runtime": 36.6336, | |
| "eval_samples_per_second": 4.941, | |
| "eval_steps_per_second": 2.484, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04897959183673469, | |
| "grad_norm": 0.6569919586181641, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 2.004, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05131195335276968, | |
| "grad_norm": 0.45704540610313416, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 1.1221, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.053644314868804666, | |
| "grad_norm": 0.5303517580032349, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 1.7539, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05597667638483965, | |
| "grad_norm": 0.5232126116752625, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 1.5575, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05830903790087463, | |
| "grad_norm": 0.5050119161605835, | |
| "learning_rate": 0.0, | |
| "loss": 1.474, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05830903790087463, | |
| "eval_loss": 1.4121884107589722, | |
| "eval_runtime": 36.7496, | |
| "eval_samples_per_second": 4.925, | |
| "eval_steps_per_second": 2.476, | |
| "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": 2487984220274688.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |