| { | |
| "best_metric": 1.593575119972229, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.01934984520123839, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007739938080495357, | |
| "grad_norm": 0.6112090349197388, | |
| "learning_rate": 1e-05, | |
| "loss": 5.9449, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007739938080495357, | |
| "eval_loss": 1.638183832168579, | |
| "eval_runtime": 123.6155, | |
| "eval_samples_per_second": 4.409, | |
| "eval_steps_per_second": 2.208, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015479876160990713, | |
| "grad_norm": 0.7082736492156982, | |
| "learning_rate": 2e-05, | |
| "loss": 5.8472, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0023219814241486067, | |
| "grad_norm": 0.8556309938430786, | |
| "learning_rate": 3e-05, | |
| "loss": 6.6413, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0030959752321981426, | |
| "grad_norm": 1.0540803670883179, | |
| "learning_rate": 4e-05, | |
| "loss": 6.5789, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003869969040247678, | |
| "grad_norm": 0.5907458662986755, | |
| "learning_rate": 5e-05, | |
| "loss": 4.927, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003869969040247678, | |
| "eval_loss": 1.6376686096191406, | |
| "eval_runtime": 124.049, | |
| "eval_samples_per_second": 4.393, | |
| "eval_steps_per_second": 2.201, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0046439628482972135, | |
| "grad_norm": 0.6620371341705322, | |
| "learning_rate": 6e-05, | |
| "loss": 6.2809, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005417956656346749, | |
| "grad_norm": 0.5814986228942871, | |
| "learning_rate": 7e-05, | |
| "loss": 5.0479, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006191950464396285, | |
| "grad_norm": 0.6137049198150635, | |
| "learning_rate": 8e-05, | |
| "loss": 6.1478, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00696594427244582, | |
| "grad_norm": 0.6229683756828308, | |
| "learning_rate": 9e-05, | |
| "loss": 4.2841, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007739938080495356, | |
| "grad_norm": 0.8397112488746643, | |
| "learning_rate": 0.0001, | |
| "loss": 4.238, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007739938080495356, | |
| "eval_loss": 1.6313807964324951, | |
| "eval_runtime": 123.9718, | |
| "eval_samples_per_second": 4.396, | |
| "eval_steps_per_second": 2.202, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008513931888544891, | |
| "grad_norm": 0.5993853807449341, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 4.7124, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.009287925696594427, | |
| "grad_norm": 0.98615562915802, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 9.0319, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.010061919504643963, | |
| "grad_norm": 0.7699627876281738, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 8.72, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.010835913312693499, | |
| "grad_norm": 0.905797004699707, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 6.5687, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.011609907120743035, | |
| "grad_norm": 0.6917111873626709, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 7.6529, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011609907120743035, | |
| "eval_loss": 1.6112371683120728, | |
| "eval_runtime": 124.5295, | |
| "eval_samples_per_second": 4.376, | |
| "eval_steps_per_second": 2.192, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01238390092879257, | |
| "grad_norm": 0.8985219597816467, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 8.5202, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.013157894736842105, | |
| "grad_norm": 0.7589756846427917, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 6.8425, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01393188854489164, | |
| "grad_norm": 0.8652344346046448, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 7.2533, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.014705882352941176, | |
| "grad_norm": 1.1718361377716064, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 7.3282, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.015479876160990712, | |
| "grad_norm": 1.478440761566162, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 6.26, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.015479876160990712, | |
| "eval_loss": 1.5969746112823486, | |
| "eval_runtime": 125.3564, | |
| "eval_samples_per_second": 4.348, | |
| "eval_steps_per_second": 2.178, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.016253869969040248, | |
| "grad_norm": 0.923443615436554, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 7.6624, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.017027863777089782, | |
| "grad_norm": 0.8137747049331665, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 6.3292, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01780185758513932, | |
| "grad_norm": 0.922442615032196, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 5.1466, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.018575851393188854, | |
| "grad_norm": 0.8308588862419128, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 5.8502, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01934984520123839, | |
| "grad_norm": 1.1300650835037231, | |
| "learning_rate": 0.0, | |
| "loss": 7.9132, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01934984520123839, | |
| "eval_loss": 1.593575119972229, | |
| "eval_runtime": 124.4941, | |
| "eval_samples_per_second": 4.378, | |
| "eval_steps_per_second": 2.193, | |
| "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": 7288652858130432.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |