| { | |
| "best_metric": 2.4719741344451904, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.053966540744738264, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0021586616297895305, | |
| "grad_norm": 0.4805165231227875, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 2.3053, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0021586616297895305, | |
| "eval_loss": 2.4950923919677734, | |
| "eval_runtime": 35.2547, | |
| "eval_samples_per_second": 5.531, | |
| "eval_steps_per_second": 2.78, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004317323259579061, | |
| "grad_norm": 0.5265409350395203, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 2.4779, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0064759848893685915, | |
| "grad_norm": 0.4193825423717499, | |
| "learning_rate": 6e-06, | |
| "loss": 2.3878, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008634646519158122, | |
| "grad_norm": 0.4574205279350281, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 2.4617, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010793308148947653, | |
| "grad_norm": 0.5360931754112244, | |
| "learning_rate": 1e-05, | |
| "loss": 2.5719, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010793308148947653, | |
| "eval_loss": 2.4947731494903564, | |
| "eval_runtime": 34.8268, | |
| "eval_samples_per_second": 5.599, | |
| "eval_steps_per_second": 2.814, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012951969778737183, | |
| "grad_norm": 0.5430278182029724, | |
| "learning_rate": 1.2e-05, | |
| "loss": 2.6329, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015110631408526714, | |
| "grad_norm": 0.44120287895202637, | |
| "learning_rate": 1.4e-05, | |
| "loss": 2.4466, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.017269293038316244, | |
| "grad_norm": 0.44740861654281616, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 2.2921, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.019427954668105773, | |
| "grad_norm": 0.482614666223526, | |
| "learning_rate": 1.8e-05, | |
| "loss": 2.4402, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.021586616297895305, | |
| "grad_norm": 0.4554874002933502, | |
| "learning_rate": 2e-05, | |
| "loss": 2.6203, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.021586616297895305, | |
| "eval_loss": 2.4917423725128174, | |
| "eval_runtime": 33.0385, | |
| "eval_samples_per_second": 5.902, | |
| "eval_steps_per_second": 2.966, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.023745277927684834, | |
| "grad_norm": 0.4039216935634613, | |
| "learning_rate": 1.9781476007338058e-05, | |
| "loss": 2.3033, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.025903939557474366, | |
| "grad_norm": 0.4976852536201477, | |
| "learning_rate": 1.913545457642601e-05, | |
| "loss": 2.5265, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.028062601187263895, | |
| "grad_norm": 0.40776801109313965, | |
| "learning_rate": 1.8090169943749477e-05, | |
| "loss": 2.4908, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.030221262817053427, | |
| "grad_norm": 0.49444299936294556, | |
| "learning_rate": 1.6691306063588583e-05, | |
| "loss": 2.476, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.032379924446842956, | |
| "grad_norm": 0.6038114428520203, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 2.3912, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.032379924446842956, | |
| "eval_loss": 2.4828007221221924, | |
| "eval_runtime": 34.2086, | |
| "eval_samples_per_second": 5.7, | |
| "eval_steps_per_second": 2.865, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03453858607663249, | |
| "grad_norm": 0.5087575912475586, | |
| "learning_rate": 1.3090169943749475e-05, | |
| "loss": 2.6166, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03669724770642202, | |
| "grad_norm": 0.6161304712295532, | |
| "learning_rate": 1.1045284632676535e-05, | |
| "loss": 2.3413, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.038855909336211546, | |
| "grad_norm": 0.8429335951805115, | |
| "learning_rate": 8.954715367323468e-06, | |
| "loss": 2.8171, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04101457096600108, | |
| "grad_norm": 0.46091142296791077, | |
| "learning_rate": 6.909830056250527e-06, | |
| "loss": 2.2982, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04317323259579061, | |
| "grad_norm": 0.5474252700805664, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 2.563, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04317323259579061, | |
| "eval_loss": 2.474599599838257, | |
| "eval_runtime": 34.2783, | |
| "eval_samples_per_second": 5.689, | |
| "eval_steps_per_second": 2.859, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04533189422558014, | |
| "grad_norm": 0.4824274480342865, | |
| "learning_rate": 3.308693936411421e-06, | |
| "loss": 2.461, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04749055585536967, | |
| "grad_norm": 0.5804234147071838, | |
| "learning_rate": 1.9098300562505266e-06, | |
| "loss": 2.3954, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0496492174851592, | |
| "grad_norm": 0.4935641884803772, | |
| "learning_rate": 8.645454235739903e-07, | |
| "loss": 2.5672, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05180787911494873, | |
| "grad_norm": 0.5770930051803589, | |
| "learning_rate": 2.1852399266194312e-07, | |
| "loss": 2.5701, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.053966540744738264, | |
| "grad_norm": 0.590212881565094, | |
| "learning_rate": 0.0, | |
| "loss": 2.4887, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.053966540744738264, | |
| "eval_loss": 2.4719741344451904, | |
| "eval_runtime": 33.3118, | |
| "eval_samples_per_second": 5.854, | |
| "eval_steps_per_second": 2.942, | |
| "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": 7915510431744000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |