| { | |
| "best_metric": 0.10687629878520966, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.4333694474539545, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01733477789815818, | |
| "grad_norm": 1.1709370613098145, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2777, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01733477789815818, | |
| "eval_loss": 0.9326940774917603, | |
| "eval_runtime": 3.8155, | |
| "eval_samples_per_second": 13.105, | |
| "eval_steps_per_second": 3.407, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03466955579631636, | |
| "grad_norm": 2.190261125564575, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4933, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.05200433369447454, | |
| "grad_norm": 2.1287896633148193, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.4731, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06933911159263272, | |
| "grad_norm": 1.1221868991851807, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.1852, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0866738894907909, | |
| "grad_norm": 0.45097607374191284, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.101, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.10400866738894908, | |
| "grad_norm": 0.40417975187301636, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.0906, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.12134344528710726, | |
| "grad_norm": 0.2923962473869324, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.0912, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.13867822318526543, | |
| "grad_norm": 0.3543075919151306, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.097, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1560130010834236, | |
| "grad_norm": 0.32288411259651184, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.1074, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1733477789815818, | |
| "grad_norm": 0.23518748581409454, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.1114, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.19068255687973998, | |
| "grad_norm": 0.2938070297241211, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.1206, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.20801733477789816, | |
| "grad_norm": 0.36567267775535583, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.1452, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.22535211267605634, | |
| "grad_norm": 0.18887048959732056, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.0555, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.24268689057421453, | |
| "grad_norm": 0.19256988167762756, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0435, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2600216684723727, | |
| "grad_norm": 0.20813193917274475, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.054, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.27735644637053086, | |
| "grad_norm": 0.30661728978157043, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.0655, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.29469122426868904, | |
| "grad_norm": 0.2554875910282135, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.0658, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3120260021668472, | |
| "grad_norm": 0.19838938117027283, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0707, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3293607800650054, | |
| "grad_norm": 0.22489877045154572, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.0779, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3466955579631636, | |
| "grad_norm": 0.26527872681617737, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0898, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3640303358613218, | |
| "grad_norm": 0.23718084394931793, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0846, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.38136511375947996, | |
| "grad_norm": 0.329249769449234, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0866, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.39869989165763814, | |
| "grad_norm": 0.2758727967739105, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.1015, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.4160346695557963, | |
| "grad_norm": 0.39751315116882324, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.1253, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4333694474539545, | |
| "grad_norm": 0.4145531952381134, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.1512, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4333694474539545, | |
| "eval_loss": 0.10687629878520966, | |
| "eval_runtime": 3.472, | |
| "eval_samples_per_second": 14.401, | |
| "eval_steps_per_second": 3.744, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": 2.984041808658432e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |