| { | |
| "best_metric": 2.542313575744629, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.30499428135722456, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012199771254288982, | |
| "grad_norm": 1.166663646697998, | |
| "learning_rate": 2e-05, | |
| "loss": 4.5306, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012199771254288982, | |
| "eval_loss": 6.460769176483154, | |
| "eval_runtime": 1.4227, | |
| "eval_samples_per_second": 35.143, | |
| "eval_steps_per_second": 9.137, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.024399542508577964, | |
| "grad_norm": 1.2659770250320435, | |
| "learning_rate": 4e-05, | |
| "loss": 4.8882, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.036599313762866945, | |
| "grad_norm": 1.2624318599700928, | |
| "learning_rate": 6e-05, | |
| "loss": 5.0064, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04879908501715593, | |
| "grad_norm": 1.5363656282424927, | |
| "learning_rate": 8e-05, | |
| "loss": 5.3547, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06099885627144491, | |
| "grad_norm": 1.9164278507232666, | |
| "learning_rate": 0.0001, | |
| "loss": 5.0749, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07319862752573389, | |
| "grad_norm": 2.4485414028167725, | |
| "learning_rate": 9.997539658034168e-05, | |
| "loss": 5.2012, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08539839878002288, | |
| "grad_norm": 2.5348973274230957, | |
| "learning_rate": 9.990161322484486e-05, | |
| "loss": 4.5183, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09759817003431186, | |
| "grad_norm": 1.8544416427612305, | |
| "learning_rate": 9.977873061452552e-05, | |
| "loss": 4.0716, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.10979794128860083, | |
| "grad_norm": 1.933067798614502, | |
| "learning_rate": 9.96068831197139e-05, | |
| "loss": 3.8384, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.12199771254288982, | |
| "grad_norm": 2.36763072013855, | |
| "learning_rate": 9.938625865312251e-05, | |
| "loss": 3.4286, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1341974837971788, | |
| "grad_norm": 2.299260139465332, | |
| "learning_rate": 9.911709846436641e-05, | |
| "loss": 3.4454, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.14639725505146778, | |
| "grad_norm": 3.964050531387329, | |
| "learning_rate": 9.879969687616027e-05, | |
| "loss": 3.7988, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.15859702630575676, | |
| "grad_norm": 24.955421447753906, | |
| "learning_rate": 9.84344009624807e-05, | |
| "loss": 4.0564, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.17079679756004576, | |
| "grad_norm": 4.6906256675720215, | |
| "learning_rate": 9.80216101690461e-05, | |
| "loss": 3.9187, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.18299656881433474, | |
| "grad_norm": 4.218716144561768, | |
| "learning_rate": 9.756177587652856e-05, | |
| "loss": 3.6779, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1951963400686237, | |
| "grad_norm": 2.8284833431243896, | |
| "learning_rate": 9.705540090697575e-05, | |
| "loss": 3.3503, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2073961113229127, | |
| "grad_norm": 1.921479344367981, | |
| "learning_rate": 9.650303897398232e-05, | |
| "loss": 3.0593, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.21959588257720167, | |
| "grad_norm": 1.7184988260269165, | |
| "learning_rate": 9.590529407721231e-05, | |
| "loss": 2.761, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.23179565383149067, | |
| "grad_norm": 1.6135209798812866, | |
| "learning_rate": 9.526281984193436e-05, | |
| "loss": 2.6214, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.24399542508577965, | |
| "grad_norm": 1.5472686290740967, | |
| "learning_rate": 9.4576318804292e-05, | |
| "loss": 2.594, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2561951963400686, | |
| "grad_norm": 1.5360417366027832, | |
| "learning_rate": 9.384654164309083e-05, | |
| "loss": 2.4474, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2683949675943576, | |
| "grad_norm": 1.5541893243789673, | |
| "learning_rate": 9.30742863589421e-05, | |
| "loss": 2.4182, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2805947388486466, | |
| "grad_norm": 1.6636126041412354, | |
| "learning_rate": 9.226039740166091e-05, | |
| "loss": 2.4277, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.29279451010293556, | |
| "grad_norm": 1.7966293096542358, | |
| "learning_rate": 9.140576474687264e-05, | |
| "loss": 2.0648, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.30499428135722456, | |
| "grad_norm": 4.8820672035217285, | |
| "learning_rate": 9.051132292283771e-05, | |
| "loss": 3.1713, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.30499428135722456, | |
| "eval_loss": 2.542313575744629, | |
| "eval_runtime": 1.4246, | |
| "eval_samples_per_second": 35.097, | |
| "eval_steps_per_second": 9.125, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 25, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.812028905324544e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |