| { | |
| "best_metric": 2.580864906311035, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.05, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001, | |
| "grad_norm": 0.2811749279499054, | |
| "learning_rate": 2e-05, | |
| "loss": 2.6895, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001, | |
| "eval_loss": 3.0125324726104736, | |
| "eval_runtime": 4.6936, | |
| "eval_samples_per_second": 4.474, | |
| "eval_steps_per_second": 4.474, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002, | |
| "grad_norm": 0.2987586557865143, | |
| "learning_rate": 4e-05, | |
| "loss": 2.8912, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003, | |
| "grad_norm": 0.452608197927475, | |
| "learning_rate": 6e-05, | |
| "loss": 3.4357, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004, | |
| "grad_norm": 0.38785919547080994, | |
| "learning_rate": 8e-05, | |
| "loss": 2.5889, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005, | |
| "grad_norm": 0.38931822776794434, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7513, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006, | |
| "grad_norm": 0.516417384147644, | |
| "learning_rate": 0.00012, | |
| "loss": 3.2128, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007, | |
| "grad_norm": 0.4206741750240326, | |
| "learning_rate": 0.00014, | |
| "loss": 2.9368, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008, | |
| "grad_norm": 0.48171964287757874, | |
| "learning_rate": 0.00016, | |
| "loss": 2.8618, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009, | |
| "grad_norm": 0.8544142842292786, | |
| "learning_rate": 0.00018, | |
| "loss": 3.0312, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.848558247089386, | |
| "learning_rate": 0.0002, | |
| "loss": 2.9334, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011, | |
| "grad_norm": 0.8914313316345215, | |
| "learning_rate": 0.00019999996900269505, | |
| "loss": 2.7981, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.012, | |
| "grad_norm": 0.6103464365005493, | |
| "learning_rate": 0.0001999998760107994, | |
| "loss": 2.7247, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.013, | |
| "grad_norm": 0.7618600726127625, | |
| "learning_rate": 0.00019999972102437074, | |
| "loss": 2.472, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.014, | |
| "grad_norm": 0.6825264692306519, | |
| "learning_rate": 0.00019999950404350512, | |
| "loss": 2.6008, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.015, | |
| "grad_norm": 0.5940832495689392, | |
| "learning_rate": 0.00019999922506833704, | |
| "loss": 2.1996, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.016, | |
| "grad_norm": 0.6273623108863831, | |
| "learning_rate": 0.00019999888409903948, | |
| "loss": 2.3565, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.017, | |
| "grad_norm": 0.7437952160835266, | |
| "learning_rate": 0.00019999848113582384, | |
| "loss": 2.7232, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.018, | |
| "grad_norm": 0.5971533060073853, | |
| "learning_rate": 0.0001999980161789399, | |
| "loss": 2.509, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.019, | |
| "grad_norm": 0.5190719962120056, | |
| "learning_rate": 0.00019999748922867592, | |
| "loss": 2.3535, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.9244285821914673, | |
| "learning_rate": 0.00019999690028535855, | |
| "loss": 2.7599, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.021, | |
| "grad_norm": 0.8340674638748169, | |
| "learning_rate": 0.00019999624934935296, | |
| "loss": 3.0057, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.022, | |
| "grad_norm": 1.0633089542388916, | |
| "learning_rate": 0.00019999553642106266, | |
| "loss": 2.2808, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.023, | |
| "grad_norm": 4.8767266273498535, | |
| "learning_rate": 0.00019999476150092967, | |
| "loss": 2.8268, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.024, | |
| "grad_norm": 2.7197344303131104, | |
| "learning_rate": 0.00019999392458943432, | |
| "loss": 2.6517, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.025, | |
| "grad_norm": 0.9329593777656555, | |
| "learning_rate": 0.00019999302568709547, | |
| "loss": 2.212, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.026, | |
| "grad_norm": 0.6679103374481201, | |
| "learning_rate": 0.00019999206479447045, | |
| "loss": 2.0117, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.027, | |
| "grad_norm": 0.5428286790847778, | |
| "learning_rate": 0.00019999104191215493, | |
| "loss": 2.7582, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.028, | |
| "grad_norm": 0.5552177429199219, | |
| "learning_rate": 0.00019998995704078305, | |
| "loss": 2.54, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.029, | |
| "grad_norm": 0.5453671216964722, | |
| "learning_rate": 0.00019998881018102737, | |
| "loss": 2.5358, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.47653189301490784, | |
| "learning_rate": 0.00019998760133359885, | |
| "loss": 2.2443, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.031, | |
| "grad_norm": 0.755976140499115, | |
| "learning_rate": 0.0001999863304992469, | |
| "loss": 2.5519, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.032, | |
| "grad_norm": 0.7680912017822266, | |
| "learning_rate": 0.00019998499767875943, | |
| "loss": 2.7503, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.033, | |
| "grad_norm": 3.768080472946167, | |
| "learning_rate": 0.0001999836028729627, | |
| "loss": 2.6051, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.034, | |
| "grad_norm": 0.5304062962532043, | |
| "learning_rate": 0.00019998214608272136, | |
| "loss": 2.2065, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.035, | |
| "grad_norm": 1.1568998098373413, | |
| "learning_rate": 0.00019998062730893862, | |
| "loss": 2.444, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.036, | |
| "grad_norm": 0.8356309533119202, | |
| "learning_rate": 0.000199979046552556, | |
| "loss": 2.5763, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.037, | |
| "grad_norm": 0.5210471749305725, | |
| "learning_rate": 0.00019997740381455346, | |
| "loss": 2.8545, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.038, | |
| "grad_norm": 1.550714373588562, | |
| "learning_rate": 0.00019997569909594947, | |
| "loss": 2.6236, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.039, | |
| "grad_norm": 0.6044741868972778, | |
| "learning_rate": 0.0001999739323978008, | |
| "loss": 2.5349, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.9703565239906311, | |
| "learning_rate": 0.00019997210372120274, | |
| "loss": 3.1004, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.041, | |
| "grad_norm": 0.7796650528907776, | |
| "learning_rate": 0.000199970213067289, | |
| "loss": 2.5757, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.042, | |
| "grad_norm": 0.6824871301651001, | |
| "learning_rate": 0.00019996826043723162, | |
| "loss": 2.6766, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.043, | |
| "grad_norm": 0.8048773407936096, | |
| "learning_rate": 0.00019996624583224114, | |
| "loss": 2.3065, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.044, | |
| "grad_norm": 0.5458154082298279, | |
| "learning_rate": 0.00019996416925356652, | |
| "loss": 2.4336, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.045, | |
| "grad_norm": 0.623190701007843, | |
| "learning_rate": 0.00019996203070249516, | |
| "loss": 2.3835, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.046, | |
| "grad_norm": 0.5928781032562256, | |
| "learning_rate": 0.00019995983018035278, | |
| "loss": 2.3408, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.047, | |
| "grad_norm": 0.5790976881980896, | |
| "learning_rate": 0.00019995756768850364, | |
| "loss": 2.3878, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.048, | |
| "grad_norm": 0.5648425817489624, | |
| "learning_rate": 0.00019995524322835034, | |
| "loss": 2.2885, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.049, | |
| "grad_norm": 0.526339054107666, | |
| "learning_rate": 0.00019995285680133394, | |
| "loss": 2.408, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.6333803534507751, | |
| "learning_rate": 0.00019995040840893388, | |
| "loss": 2.4391, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.580864906311035, | |
| "eval_runtime": 4.8038, | |
| "eval_samples_per_second": 4.372, | |
| "eval_steps_per_second": 4.372, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 4000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 50, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4108715871436800.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |