| { |
| "best_metric": 1.4709290266036987, |
| "best_model_checkpoint": "miner_id_24/checkpoint-30", |
| "epoch": 0.0011969119671248179, |
| "eval_steps": 5, |
| "global_step": 30, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 3.9897065570827266e-05, |
| "eval_loss": 2.117204189300537, |
| "eval_runtime": 2251.1802, |
| "eval_samples_per_second": 4.688, |
| "eval_steps_per_second": 2.344, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0001196911967124818, |
| "grad_norm": 1.0353018045425415, |
| "learning_rate": 0.00012, |
| "loss": 1.8489, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.00019948532785413634, |
| "eval_loss": 1.8039857149124146, |
| "eval_runtime": 2284.5934, |
| "eval_samples_per_second": 4.62, |
| "eval_steps_per_second": 2.31, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0002393823934249636, |
| "grad_norm": 0.9052342772483826, |
| "learning_rate": 0.0001992114701314478, |
| "loss": 1.7178, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.0003590735901374454, |
| "grad_norm": 0.7083010673522949, |
| "learning_rate": 0.00018763066800438636, |
| "loss": 1.5257, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.0003989706557082727, |
| "eval_loss": 1.5616681575775146, |
| "eval_runtime": 2281.4959, |
| "eval_samples_per_second": 4.626, |
| "eval_steps_per_second": 2.313, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0004787647868499272, |
| "grad_norm": 0.612604558467865, |
| "learning_rate": 0.000163742398974869, |
| "loss": 1.5036, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.0005984559835624089, |
| "grad_norm": 0.6625750660896301, |
| "learning_rate": 0.00013090169943749476, |
| "loss": 1.5145, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.0005984559835624089, |
| "eval_loss": 1.4995189905166626, |
| "eval_runtime": 2282.0838, |
| "eval_samples_per_second": 4.625, |
| "eval_steps_per_second": 2.312, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.0007181471802748908, |
| "grad_norm": 0.6003637909889221, |
| "learning_rate": 9.372094804706867e-05, |
| "loss": 1.4118, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.0007979413114165454, |
| "eval_loss": 1.4814709424972534, |
| "eval_runtime": 2279.4137, |
| "eval_samples_per_second": 4.63, |
| "eval_steps_per_second": 2.315, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0008378383769873726, |
| "grad_norm": 0.5599179863929749, |
| "learning_rate": 5.7422070843492734e-05, |
| "loss": 1.4394, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.0009575295736998544, |
| "grad_norm": 0.5533298254013062, |
| "learning_rate": 2.7103137257858868e-05, |
| "loss": 1.3392, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.0009974266392706816, |
| "eval_loss": 1.47230863571167, |
| "eval_runtime": 2280.0193, |
| "eval_samples_per_second": 4.629, |
| "eval_steps_per_second": 2.314, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.0010772207704123362, |
| "grad_norm": 0.5216392874717712, |
| "learning_rate": 7.022351411174866e-06, |
| "loss": 1.4882, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.0011969119671248179, |
| "grad_norm": 0.5612313747406006, |
| "learning_rate": 0.0, |
| "loss": 1.4671, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.0011969119671248179, |
| "eval_loss": 1.4709290266036987, |
| "eval_runtime": 2282.1443, |
| "eval_samples_per_second": 4.625, |
| "eval_steps_per_second": 2.312, |
| "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": 1.1221045163851776e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
