| { |
| "best_metric": 11.912154197692871, |
| "best_model_checkpoint": "miner_id_24/checkpoint-3000", |
| "epoch": 5.01356710498852, |
| "eval_steps": 300, |
| "global_step": 3000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0016697975370486328, |
| "eval_loss": 11.931979179382324, |
| "eval_runtime": 9.6502, |
| "eval_samples_per_second": 209.115, |
| "eval_steps_per_second": 26.217, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.5009392611145899, |
| "grad_norm": 0.03646502271294594, |
| "learning_rate": 0.00039532411114201737, |
| "loss": 11.9228, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.5009392611145899, |
| "eval_loss": 11.915942192077637, |
| "eval_runtime": 9.5678, |
| "eval_samples_per_second": 210.917, |
| "eval_steps_per_second": 26.443, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.002713420997704, |
| "grad_norm": 0.013963569886982441, |
| "learning_rate": 0.00037137143523351785, |
| "loss": 11.9411, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.002713420997704, |
| "eval_loss": 11.914015769958496, |
| "eval_runtime": 9.5987, |
| "eval_samples_per_second": 210.238, |
| "eval_steps_per_second": 26.358, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.503652682112294, |
| "grad_norm": 0.016350438818335533, |
| "learning_rate": 0.00032947725695636553, |
| "loss": 11.9139, |
| "step": 900 |
| }, |
| { |
| "epoch": 1.503652682112294, |
| "eval_loss": 11.91312026977539, |
| "eval_runtime": 9.5664, |
| "eval_samples_per_second": 210.946, |
| "eval_steps_per_second": 26.447, |
| "step": 900 |
| }, |
| { |
| "epoch": 2.005426841995408, |
| "grad_norm": 0.01071674283593893, |
| "learning_rate": 0.0002740276310679829, |
| "loss": 11.9376, |
| "step": 1200 |
| }, |
| { |
| "epoch": 2.005426841995408, |
| "eval_loss": 11.912792205810547, |
| "eval_runtime": 9.6853, |
| "eval_samples_per_second": 208.356, |
| "eval_steps_per_second": 26.122, |
| "step": 1200 |
| }, |
| { |
| "epoch": 2.5063661031099977, |
| "grad_norm": 0.011973950080573559, |
| "learning_rate": 0.00021082778171708353, |
| "loss": 11.9132, |
| "step": 1500 |
| }, |
| { |
| "epoch": 2.5063661031099977, |
| "eval_loss": 11.91252613067627, |
| "eval_runtime": 9.7489, |
| "eval_samples_per_second": 206.998, |
| "eval_steps_per_second": 25.952, |
| "step": 1500 |
| }, |
| { |
| "epoch": 3.008140262993112, |
| "grad_norm": 0.013220425695180893, |
| "learning_rate": 0.00014649433229415587, |
| "loss": 11.9376, |
| "step": 1800 |
| }, |
| { |
| "epoch": 3.008140262993112, |
| "eval_loss": 11.91238021850586, |
| "eval_runtime": 9.6136, |
| "eval_samples_per_second": 209.911, |
| "eval_steps_per_second": 26.317, |
| "step": 1800 |
| }, |
| { |
| "epoch": 3.509079524107702, |
| "grad_norm": 0.013742562383413315, |
| "learning_rate": 8.776258692752355e-05, |
| "loss": 11.9128, |
| "step": 2100 |
| }, |
| { |
| "epoch": 3.509079524107702, |
| "eval_loss": 11.912261962890625, |
| "eval_runtime": 9.5679, |
| "eval_samples_per_second": 210.914, |
| "eval_steps_per_second": 26.443, |
| "step": 2100 |
| }, |
| { |
| "epoch": 4.010853683990816, |
| "grad_norm": 0.015797816216945648, |
| "learning_rate": 4.078138685887125e-05, |
| "loss": 11.9377, |
| "step": 2400 |
| }, |
| { |
| "epoch": 4.010853683990816, |
| "eval_loss": 11.91218090057373, |
| "eval_runtime": 9.6462, |
| "eval_samples_per_second": 209.202, |
| "eval_steps_per_second": 26.228, |
| "step": 2400 |
| }, |
| { |
| "epoch": 4.511792945105406, |
| "grad_norm": 0.012792945839464664, |
| "learning_rate": 1.0469365763439531e-05, |
| "loss": 11.9128, |
| "step": 2700 |
| }, |
| { |
| "epoch": 4.511792945105406, |
| "eval_loss": 11.912158012390137, |
| "eval_runtime": 9.6282, |
| "eval_samples_per_second": 209.592, |
| "eval_steps_per_second": 26.277, |
| "step": 2700 |
| }, |
| { |
| "epoch": 5.01356710498852, |
| "grad_norm": 0.012090091593563557, |
| "learning_rate": 0.0, |
| "loss": 11.9374, |
| "step": 3000 |
| }, |
| { |
| "epoch": 5.01356710498852, |
| "eval_loss": 11.912154197692871, |
| "eval_runtime": 9.5524, |
| "eval_samples_per_second": 211.256, |
| "eval_steps_per_second": 26.485, |
| "step": 3000 |
| } |
| ], |
| "logging_steps": 300, |
| "max_steps": 3000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "save_steps": 300, |
| "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": 5671747584000.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
