| { | |
| "best_metric": 0.8642035126686096, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.009012256669069935, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003604902667627974, | |
| "grad_norm": 0.4384039640426636, | |
| "learning_rate": 2e-05, | |
| "loss": 3.1068, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003604902667627974, | |
| "eval_loss": 0.8963788151741028, | |
| "eval_runtime": 269.9336, | |
| "eval_samples_per_second": 4.331, | |
| "eval_steps_per_second": 2.167, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007209805335255948, | |
| "grad_norm": 0.3296743631362915, | |
| "learning_rate": 4e-05, | |
| "loss": 3.1023, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0010814708002883922, | |
| "grad_norm": 0.30556032061576843, | |
| "learning_rate": 6e-05, | |
| "loss": 4.0383, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014419610670511895, | |
| "grad_norm": 0.3344082832336426, | |
| "learning_rate": 8e-05, | |
| "loss": 3.5421, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001802451333813987, | |
| "grad_norm": 0.4202673137187958, | |
| "learning_rate": 0.0001, | |
| "loss": 3.4202, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001802451333813987, | |
| "eval_loss": 0.8960877656936646, | |
| "eval_runtime": 270.1364, | |
| "eval_samples_per_second": 4.327, | |
| "eval_steps_per_second": 2.166, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0021629416005767843, | |
| "grad_norm": 0.4712982773780823, | |
| "learning_rate": 0.00012, | |
| "loss": 3.1844, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0025234318673395817, | |
| "grad_norm": 0.3527807593345642, | |
| "learning_rate": 0.00014, | |
| "loss": 3.0069, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002883922134102379, | |
| "grad_norm": 0.4092419445514679, | |
| "learning_rate": 0.00016, | |
| "loss": 3.823, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0032444124008651765, | |
| "grad_norm": 0.38688045740127563, | |
| "learning_rate": 0.00018, | |
| "loss": 3.8777, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003604902667627974, | |
| "grad_norm": 0.3729724586009979, | |
| "learning_rate": 0.0002, | |
| "loss": 3.2592, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003604902667627974, | |
| "eval_loss": 0.8891144394874573, | |
| "eval_runtime": 269.0532, | |
| "eval_samples_per_second": 4.345, | |
| "eval_steps_per_second": 2.174, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003965392934390771, | |
| "grad_norm": 0.7970941662788391, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 4.1142, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004325883201153569, | |
| "grad_norm": 0.5384020805358887, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 3.7093, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004686373467916366, | |
| "grad_norm": 0.6986257433891296, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 3.6642, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005046863734679163, | |
| "grad_norm": 0.4670394957065582, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 3.3371, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005407354001441961, | |
| "grad_norm": 0.5628902316093445, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 3.6892, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005407354001441961, | |
| "eval_loss": 0.8725980520248413, | |
| "eval_runtime": 268.9663, | |
| "eval_samples_per_second": 4.346, | |
| "eval_steps_per_second": 2.175, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005767844268204758, | |
| "grad_norm": 0.4687001407146454, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 3.4787, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0061283345349675555, | |
| "grad_norm": 0.6563277244567871, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 3.2084, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006488824801730353, | |
| "grad_norm": 0.5968443155288696, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 4.0139, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00684931506849315, | |
| "grad_norm": 0.5900570750236511, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 3.2689, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.007209805335255948, | |
| "grad_norm": 0.4784393310546875, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 4.1322, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007209805335255948, | |
| "eval_loss": 0.8654800653457642, | |
| "eval_runtime": 269.1247, | |
| "eval_samples_per_second": 4.344, | |
| "eval_steps_per_second": 2.174, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007570295602018745, | |
| "grad_norm": 0.5336175560951233, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 2.5656, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.007930785868781542, | |
| "grad_norm": 0.5913262963294983, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 2.8729, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.00829127613554434, | |
| "grad_norm": 0.6144100427627563, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 3.9989, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.008651766402307137, | |
| "grad_norm": 0.5489720106124878, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 3.3369, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.009012256669069935, | |
| "grad_norm": 0.596045970916748, | |
| "learning_rate": 0.0, | |
| "loss": 3.0519, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.009012256669069935, | |
| "eval_loss": 0.8642035126686096, | |
| "eval_runtime": 267.2033, | |
| "eval_samples_per_second": 4.375, | |
| "eval_steps_per_second": 2.189, | |
| "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": 8103027479150592.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |