| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.25, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 4.9116, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.2782, | |
| "eval_samples_per_second": 9.473, | |
| "eval_steps_per_second": 1.326, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.015, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.025, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.035, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.045, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00027, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.055, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.065, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.075, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.085, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.095, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.105, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.115, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.807, | |
| "eval_samples_per_second": 10.401, | |
| "eval_steps_per_second": 1.456, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.135, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.145, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.155, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.165, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.175, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.185, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.195, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.205, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.215, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.225, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.235, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.245, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.8136, | |
| "eval_samples_per_second": 10.387, | |
| "eval_steps_per_second": 1.454, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "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": 7.538695408346726e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |