| { | |
| "best_metric": 0.577286958694458, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.21482277121374865, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004296455424274973, | |
| "eval_loss": 2.1307930946350098, | |
| "eval_runtime": 28.1102, | |
| "eval_samples_per_second": 13.945, | |
| "eval_steps_per_second": 3.486, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01288936627282492, | |
| "grad_norm": 1.528664469718933, | |
| "learning_rate": 3e-05, | |
| "loss": 0.972, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02577873254564984, | |
| "grad_norm": 1.3626580238342285, | |
| "learning_rate": 6e-05, | |
| "loss": 1.121, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03866809881847476, | |
| "grad_norm": 1.3309577703475952, | |
| "learning_rate": 9e-05, | |
| "loss": 0.8185, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05155746509129968, | |
| "grad_norm": 0.9471054673194885, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.6157, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0644468313641246, | |
| "grad_norm": 0.9540927410125732, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.5652, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07733619763694952, | |
| "grad_norm": 0.6078122854232788, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.4848, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.09022556390977443, | |
| "grad_norm": 0.7932108044624329, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 0.5499, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.10311493018259936, | |
| "grad_norm": 1.142189383506775, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 0.641, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11600429645542427, | |
| "grad_norm": 0.6621695160865784, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 0.5546, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1288936627282492, | |
| "grad_norm": 0.7103697061538696, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5791, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.14178302900107412, | |
| "grad_norm": 0.895531415939331, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 0.5553, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.15467239527389903, | |
| "grad_norm": 0.9948716163635254, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.5597, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.16756176154672395, | |
| "grad_norm": 0.86716628074646, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 0.554, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.18045112781954886, | |
| "grad_norm": 1.1389826536178589, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.5895, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1933404940923738, | |
| "grad_norm": 1.0115134716033936, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.5991, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.20622986036519872, | |
| "grad_norm": 1.2202413082122803, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 0.6189, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.21482277121374865, | |
| "eval_loss": 0.577286958694458, | |
| "eval_runtime": 28.7161, | |
| "eval_samples_per_second": 13.651, | |
| "eval_steps_per_second": 3.413, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "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": 6.65248289783808e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |