| { |
| "best_metric": 0.9118663668632507, |
| "best_model_checkpoint": "miner_id_24/checkpoint-30", |
| "epoch": 0.012759170653907496, |
| "eval_steps": 5, |
| "global_step": 30, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0004253056884635832, |
| "eval_loss": 1.2463724613189697, |
| "eval_runtime": 122.6395, |
| "eval_samples_per_second": 8.072, |
| "eval_steps_per_second": 4.036, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0012759170653907496, |
| "grad_norm": 1.6945698261260986, |
| "learning_rate": 0.00012, |
| "loss": 5.0546, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.002126528442317916, |
| "eval_loss": 1.191353678703308, |
| "eval_runtime": 131.926, |
| "eval_samples_per_second": 7.504, |
| "eval_steps_per_second": 3.752, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.002551834130781499, |
| "grad_norm": 1.9442307949066162, |
| "learning_rate": 0.0001992114701314478, |
| "loss": 4.9964, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.003827751196172249, |
| "grad_norm": 1.6142292022705078, |
| "learning_rate": 0.00018763066800438636, |
| "loss": 4.512, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.004253056884635832, |
| "eval_loss": 1.0152685642242432, |
| "eval_runtime": 132.286, |
| "eval_samples_per_second": 7.484, |
| "eval_steps_per_second": 3.742, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.005103668261562998, |
| "grad_norm": 1.5451229810714722, |
| "learning_rate": 0.000163742398974869, |
| "loss": 4.1829, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.006379585326953748, |
| "grad_norm": 1.718298316001892, |
| "learning_rate": 0.00013090169943749476, |
| "loss": 3.8613, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.006379585326953748, |
| "eval_loss": 0.9558627009391785, |
| "eval_runtime": 131.2427, |
| "eval_samples_per_second": 7.543, |
| "eval_steps_per_second": 3.772, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.007655502392344498, |
| "grad_norm": 1.5778453350067139, |
| "learning_rate": 9.372094804706867e-05, |
| "loss": 3.7291, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.008506113769271665, |
| "eval_loss": 0.9269101023674011, |
| "eval_runtime": 131.2019, |
| "eval_samples_per_second": 7.546, |
| "eval_steps_per_second": 3.773, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.008931419457735247, |
| "grad_norm": 1.3416038751602173, |
| "learning_rate": 5.7422070843492734e-05, |
| "loss": 3.798, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.010207336523125997, |
| "grad_norm": 1.850062608718872, |
| "learning_rate": 2.7103137257858868e-05, |
| "loss": 3.9275, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.01063264221158958, |
| "eval_loss": 0.9143272042274475, |
| "eval_runtime": 131.3764, |
| "eval_samples_per_second": 7.536, |
| "eval_steps_per_second": 3.768, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.011483253588516746, |
| "grad_norm": 1.4373589754104614, |
| "learning_rate": 7.022351411174866e-06, |
| "loss": 3.4133, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.012759170653907496, |
| "grad_norm": 1.2759556770324707, |
| "learning_rate": 0.0, |
| "loss": 3.5974, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.012759170653907496, |
| "eval_loss": 0.9118663668632507, |
| "eval_runtime": 131.5224, |
| "eval_samples_per_second": 7.527, |
| "eval_steps_per_second": 3.764, |
| "step": 30 |
| } |
| ], |
| "logging_steps": 3, |
| "max_steps": 30, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 10, |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 5526274525102080.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
