| { |
| "best_metric": 2.6063930988311768, |
| "best_model_checkpoint": "miner_id_24/checkpoint-30", |
| "epoch": 0.00975371860521824, |
| "eval_steps": 5, |
| "global_step": 30, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0003251239535072746, |
| "eval_loss": 3.9193971157073975, |
| "eval_runtime": 228.562, |
| "eval_samples_per_second": 11.336, |
| "eval_steps_per_second": 2.835, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.000975371860521824, |
| "grad_norm": 1.5996079444885254, |
| "learning_rate": 0.00012, |
| "loss": 2.557, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.0016256197675363732, |
| "eval_loss": 3.553191900253296, |
| "eval_runtime": 228.5198, |
| "eval_samples_per_second": 11.338, |
| "eval_steps_per_second": 2.836, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.001950743721043648, |
| "grad_norm": 2.073932647705078, |
| "learning_rate": 0.0001992114701314478, |
| "loss": 2.4685, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.002926115581565472, |
| "grad_norm": 1.3495839834213257, |
| "learning_rate": 0.00018763066800438636, |
| "loss": 2.2953, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.0032512395350727465, |
| "eval_loss": 3.028703212738037, |
| "eval_runtime": 228.8022, |
| "eval_samples_per_second": 11.324, |
| "eval_steps_per_second": 2.832, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.003901487442087296, |
| "grad_norm": 1.0149577856063843, |
| "learning_rate": 0.000163742398974869, |
| "loss": 2.2831, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.00487685930260912, |
| "grad_norm": 1.0780360698699951, |
| "learning_rate": 0.00013090169943749476, |
| "loss": 2.2027, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.00487685930260912, |
| "eval_loss": 2.7850940227508545, |
| "eval_runtime": 228.566, |
| "eval_samples_per_second": 11.336, |
| "eval_steps_per_second": 2.835, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.005852231163130944, |
| "grad_norm": 1.1503500938415527, |
| "learning_rate": 9.372094804706867e-05, |
| "loss": 2.3607, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.006502479070145493, |
| "eval_loss": 2.664445400238037, |
| "eval_runtime": 229.157, |
| "eval_samples_per_second": 11.307, |
| "eval_steps_per_second": 2.828, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.006827603023652768, |
| "grad_norm": 1.208409309387207, |
| "learning_rate": 5.7422070843492734e-05, |
| "loss": 2.3119, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.007802974884174592, |
| "grad_norm": 1.367969274520874, |
| "learning_rate": 2.7103137257858868e-05, |
| "loss": 2.3106, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.008128098837681867, |
| "eval_loss": 2.616642951965332, |
| "eval_runtime": 228.6629, |
| "eval_samples_per_second": 11.331, |
| "eval_steps_per_second": 2.834, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.008778346744696415, |
| "grad_norm": 1.717703104019165, |
| "learning_rate": 7.022351411174866e-06, |
| "loss": 2.3972, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.00975371860521824, |
| "grad_norm": 1.9316027164459229, |
| "learning_rate": 0.0, |
| "loss": 2.2749, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.00975371860521824, |
| "eval_loss": 2.6063930988311768, |
| "eval_runtime": 228.8831, |
| "eval_samples_per_second": 11.32, |
| "eval_steps_per_second": 2.831, |
| "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": 2.470837626077184e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
