| { | |
| "best_metric": 2.806708812713623, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.010225994477962982, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00040903977911851925, | |
| "grad_norm": 3.403695583343506, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 3.1488, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00040903977911851925, | |
| "eval_loss": 3.3169796466827393, | |
| "eval_runtime": 1340.6622, | |
| "eval_samples_per_second": 6.142, | |
| "eval_steps_per_second": 1.536, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008180795582370385, | |
| "grad_norm": 2.9494946002960205, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 3.3498, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0012271193373555578, | |
| "grad_norm": 3.267648696899414, | |
| "learning_rate": 1.5e-06, | |
| "loss": 3.2544, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001636159116474077, | |
| "grad_norm": 3.318493366241455, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 3.1657, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0020451988955925964, | |
| "grad_norm": 3.43685245513916, | |
| "learning_rate": 2.5e-06, | |
| "loss": 3.308, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0024542386747111156, | |
| "grad_norm": 3.164874315261841, | |
| "learning_rate": 3e-06, | |
| "loss": 3.1142, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002863278453829635, | |
| "grad_norm": 3.233035087585449, | |
| "learning_rate": 3.5000000000000004e-06, | |
| "loss": 3.1668, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003272318232948154, | |
| "grad_norm": 3.4403860569000244, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 3.3036, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0036813580120666736, | |
| "grad_norm": 3.094191074371338, | |
| "learning_rate": 4.5e-06, | |
| "loss": 3.1118, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004090397791185193, | |
| "grad_norm": 2.5749802589416504, | |
| "learning_rate": 5e-06, | |
| "loss": 3.0396, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0044994375703037125, | |
| "grad_norm": 2.707096576690674, | |
| "learning_rate": 5.500000000000001e-06, | |
| "loss": 3.0415, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004908477349422231, | |
| "grad_norm": 2.787351369857788, | |
| "learning_rate": 6e-06, | |
| "loss": 3.1743, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005317517128540751, | |
| "grad_norm": 2.5418272018432617, | |
| "learning_rate": 6.5000000000000004e-06, | |
| "loss": 3.066, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00572655690765927, | |
| "grad_norm": 2.0689032077789307, | |
| "learning_rate": 7.000000000000001e-06, | |
| "loss": 3.117, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006135596686777789, | |
| "grad_norm": 2.001984119415283, | |
| "learning_rate": 7.5e-06, | |
| "loss": 2.7965, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006544636465896308, | |
| "grad_norm": 1.8868132829666138, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 3.1269, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.006953676245014828, | |
| "grad_norm": 1.6948388814926147, | |
| "learning_rate": 8.500000000000002e-06, | |
| "loss": 3.0812, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.007362716024133347, | |
| "grad_norm": 1.6606471538543701, | |
| "learning_rate": 9e-06, | |
| "loss": 3.0924, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007771755803251866, | |
| "grad_norm": 1.5790302753448486, | |
| "learning_rate": 9.5e-06, | |
| "loss": 3.0746, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.008180795582370386, | |
| "grad_norm": 1.3386214971542358, | |
| "learning_rate": 1e-05, | |
| "loss": 2.8878, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008589835361488905, | |
| "grad_norm": 1.2734287977218628, | |
| "learning_rate": 1.05e-05, | |
| "loss": 2.852, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.008998875140607425, | |
| "grad_norm": 1.254805326461792, | |
| "learning_rate": 1.1000000000000001e-05, | |
| "loss": 2.8355, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.009407914919725943, | |
| "grad_norm": 1.2211179733276367, | |
| "learning_rate": 1.1500000000000002e-05, | |
| "loss": 2.7881, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.009816954698844462, | |
| "grad_norm": 1.1198757886886597, | |
| "learning_rate": 1.2e-05, | |
| "loss": 2.7087, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.010225994477962982, | |
| "grad_norm": 1.0582196712493896, | |
| "learning_rate": 1.25e-05, | |
| "loss": 2.7473, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010225994477962982, | |
| "eval_loss": 2.806708812713623, | |
| "eval_runtime": 1349.0669, | |
| "eval_samples_per_second": 6.104, | |
| "eval_steps_per_second": 1.526, | |
| "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": 1.5273699984801792e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |