| { |
| "best_metric": 1.940207600593567, |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", |
| "epoch": 1.0, |
| "eval_steps": 25, |
| "global_step": 27, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.037037037037037035, |
| "grad_norm": 2.6908509731292725, |
| "learning_rate": 2e-05, |
| "loss": 3.3476, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.037037037037037035, |
| "eval_loss": 3.1031181812286377, |
| "eval_runtime": 3.1419, |
| "eval_samples_per_second": 14.641, |
| "eval_steps_per_second": 1.91, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.07407407407407407, |
| "grad_norm": 2.918897867202759, |
| "learning_rate": 4e-05, |
| "loss": 3.2139, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.1111111111111111, |
| "grad_norm": 2.835937261581421, |
| "learning_rate": 6e-05, |
| "loss": 2.8209, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.14814814814814814, |
| "grad_norm": 3.0771942138671875, |
| "learning_rate": 8e-05, |
| "loss": 2.954, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.18518518518518517, |
| "grad_norm": 2.512427568435669, |
| "learning_rate": 0.0001, |
| "loss": 2.4512, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.2222222222222222, |
| "grad_norm": 2.5859789848327637, |
| "learning_rate": 9.949107209404665e-05, |
| "loss": 2.3364, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.25925925925925924, |
| "grad_norm": 1.733902931213379, |
| "learning_rate": 9.797464868072488e-05, |
| "loss": 2.3506, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.2962962962962963, |
| "grad_norm": 2.2299413681030273, |
| "learning_rate": 9.548159976772592e-05, |
| "loss": 2.7624, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.3333333333333333, |
| "grad_norm": 3.0543603897094727, |
| "learning_rate": 9.206267664155907e-05, |
| "loss": 2.1164, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.37037037037037035, |
| "grad_norm": 1.5863101482391357, |
| "learning_rate": 8.778747871771292e-05, |
| "loss": 1.7827, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4074074074074074, |
| "grad_norm": 1.7515696287155151, |
| "learning_rate": 8.274303669726426e-05, |
| "loss": 2.278, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.4444444444444444, |
| "grad_norm": 1.6946384906768799, |
| "learning_rate": 7.703204087277988e-05, |
| "loss": 1.9675, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.48148148148148145, |
| "grad_norm": 1.7334179878234863, |
| "learning_rate": 7.077075065009433e-05, |
| "loss": 2.0629, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.5185185185185185, |
| "grad_norm": 1.7637220621109009, |
| "learning_rate": 6.408662784207149e-05, |
| "loss": 1.9724, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.5555555555555556, |
| "grad_norm": 1.2732926607131958, |
| "learning_rate": 5.7115741913664264e-05, |
| "loss": 1.9902, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "grad_norm": 1.2487651109695435, |
| "learning_rate": 5e-05, |
| "loss": 1.9001, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.6296296296296297, |
| "grad_norm": 1.343316912651062, |
| "learning_rate": 4.288425808633575e-05, |
| "loss": 1.8352, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 1.3064125776290894, |
| "learning_rate": 3.591337215792852e-05, |
| "loss": 2.151, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.7037037037037037, |
| "grad_norm": 1.4898581504821777, |
| "learning_rate": 2.9229249349905684e-05, |
| "loss": 1.8626, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.7407407407407407, |
| "grad_norm": 1.7274696826934814, |
| "learning_rate": 2.296795912722014e-05, |
| "loss": 1.9821, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.7777777777777778, |
| "grad_norm": 1.1525099277496338, |
| "learning_rate": 1.725696330273575e-05, |
| "loss": 1.917, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.8148148148148148, |
| "grad_norm": 1.4067116975784302, |
| "learning_rate": 1.2212521282287092e-05, |
| "loss": 1.6533, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.8518518518518519, |
| "grad_norm": 1.2512614727020264, |
| "learning_rate": 7.937323358440935e-06, |
| "loss": 1.9396, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.8888888888888888, |
| "grad_norm": 1.2110347747802734, |
| "learning_rate": 4.5184002322740785e-06, |
| "loss": 1.8162, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.9259259259259259, |
| "grad_norm": 1.2910479307174683, |
| "learning_rate": 2.0253513192751373e-06, |
| "loss": 1.8365, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.9259259259259259, |
| "eval_loss": 1.940207600593567, |
| "eval_runtime": 2.9484, |
| "eval_samples_per_second": 15.602, |
| "eval_steps_per_second": 2.035, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.9629629629629629, |
| "grad_norm": 1.2259421348571777, |
| "learning_rate": 5.089279059533658e-07, |
| "loss": 1.9491, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 1.2239744663238525, |
| "learning_rate": 0.0, |
| "loss": 1.9371, |
| "step": 27 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 27, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 25, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 5, |
| "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": 2.468309889712128e+16, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
