| { | |
| "best_metric": 0.3907972276210785, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.02332089552238806, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009328358208955224, | |
| "grad_norm": 0.15643475949764252, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6072, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009328358208955224, | |
| "eval_loss": 0.5362926125526428, | |
| "eval_runtime": 215.0845, | |
| "eval_samples_per_second": 2.102, | |
| "eval_steps_per_second": 1.051, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018656716417910447, | |
| "grad_norm": 0.14539337158203125, | |
| "learning_rate": 4e-05, | |
| "loss": 0.5895, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002798507462686567, | |
| "grad_norm": 0.1438995748758316, | |
| "learning_rate": 6e-05, | |
| "loss": 0.5563, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0037313432835820895, | |
| "grad_norm": 0.136636421084404, | |
| "learning_rate": 8e-05, | |
| "loss": 0.58, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0046641791044776115, | |
| "grad_norm": 0.15362198650836945, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5469, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0046641791044776115, | |
| "eval_loss": 0.5330179333686829, | |
| "eval_runtime": 213.7237, | |
| "eval_samples_per_second": 2.115, | |
| "eval_steps_per_second": 1.057, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005597014925373134, | |
| "grad_norm": 0.148357555270195, | |
| "learning_rate": 0.00012, | |
| "loss": 0.5368, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0065298507462686565, | |
| "grad_norm": 0.15877765417099, | |
| "learning_rate": 0.00014, | |
| "loss": 0.5009, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007462686567164179, | |
| "grad_norm": 0.23175980150699615, | |
| "learning_rate": 0.00016, | |
| "loss": 0.7121, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008395522388059701, | |
| "grad_norm": 0.22547464072704315, | |
| "learning_rate": 0.00018, | |
| "loss": 0.5383, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009328358208955223, | |
| "grad_norm": 0.22632212936878204, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4945, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009328358208955223, | |
| "eval_loss": 0.46882349252700806, | |
| "eval_runtime": 211.8107, | |
| "eval_samples_per_second": 2.134, | |
| "eval_steps_per_second": 1.067, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010261194029850746, | |
| "grad_norm": 0.2173951268196106, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 0.539, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.011194029850746268, | |
| "grad_norm": 0.17697711288928986, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 0.3917, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.012126865671641791, | |
| "grad_norm": 0.16931317746639252, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.5017, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.013059701492537313, | |
| "grad_norm": 0.20356027781963348, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.5613, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.013992537313432836, | |
| "grad_norm": 0.17862637341022491, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.4629, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013992537313432836, | |
| "eval_loss": 0.4177614152431488, | |
| "eval_runtime": 213.5402, | |
| "eval_samples_per_second": 2.117, | |
| "eval_steps_per_second": 1.058, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.014925373134328358, | |
| "grad_norm": 0.20311962068080902, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.3588, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01585820895522388, | |
| "grad_norm": 0.19799074530601501, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.4922, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.016791044776119403, | |
| "grad_norm": 0.20521485805511475, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.4532, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.017723880597014924, | |
| "grad_norm": 0.1826445609331131, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.3642, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.018656716417910446, | |
| "grad_norm": 0.18291088938713074, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.4163, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.018656716417910446, | |
| "eval_loss": 0.3951972424983978, | |
| "eval_runtime": 213.9225, | |
| "eval_samples_per_second": 2.113, | |
| "eval_steps_per_second": 1.056, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01958955223880597, | |
| "grad_norm": 0.19263756275177002, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 0.3699, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.020522388059701493, | |
| "grad_norm": 0.2069644331932068, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.4451, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.021455223880597014, | |
| "grad_norm": 0.18779270350933075, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 0.4153, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.022388059701492536, | |
| "grad_norm": 0.20380006730556488, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 0.4172, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02332089552238806, | |
| "grad_norm": 0.1967461258172989, | |
| "learning_rate": 0.0, | |
| "loss": 0.4723, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02332089552238806, | |
| "eval_loss": 0.3907972276210785, | |
| "eval_runtime": 212.4073, | |
| "eval_samples_per_second": 2.128, | |
| "eval_steps_per_second": 1.064, | |
| "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": 1.5831020863488e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |