| { | |
| "best_metric": 2.0087664127349854, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.025786487880350695, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010314595152140279, | |
| "grad_norm": 1.3593727350234985, | |
| "learning_rate": 2e-05, | |
| "loss": 9.1967, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010314595152140279, | |
| "eval_loss": 2.4018898010253906, | |
| "eval_runtime": 68.6731, | |
| "eval_samples_per_second": 5.956, | |
| "eval_steps_per_second": 2.985, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0020629190304280558, | |
| "grad_norm": 1.329776644706726, | |
| "learning_rate": 4e-05, | |
| "loss": 8.5769, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0030943785456420837, | |
| "grad_norm": 1.8120794296264648, | |
| "learning_rate": 6e-05, | |
| "loss": 9.506, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0041258380608561115, | |
| "grad_norm": 1.5653033256530762, | |
| "learning_rate": 8e-05, | |
| "loss": 10.0874, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005157297576070139, | |
| "grad_norm": 1.4304020404815674, | |
| "learning_rate": 0.0001, | |
| "loss": 8.6548, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005157297576070139, | |
| "eval_loss": 2.3912577629089355, | |
| "eval_runtime": 68.4837, | |
| "eval_samples_per_second": 5.972, | |
| "eval_steps_per_second": 2.993, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006188757091284167, | |
| "grad_norm": 1.85710608959198, | |
| "learning_rate": 0.00012, | |
| "loss": 9.3077, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007220216606498195, | |
| "grad_norm": 2.369805097579956, | |
| "learning_rate": 0.00014, | |
| "loss": 9.4416, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008251676121712223, | |
| "grad_norm": 2.070528030395508, | |
| "learning_rate": 0.00016, | |
| "loss": 8.8358, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009283135636926251, | |
| "grad_norm": 2.5261223316192627, | |
| "learning_rate": 0.00018, | |
| "loss": 9.7142, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010314595152140279, | |
| "grad_norm": 2.1898765563964844, | |
| "learning_rate": 0.0002, | |
| "loss": 9.3232, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010314595152140279, | |
| "eval_loss": 2.2462997436523438, | |
| "eval_runtime": 68.4932, | |
| "eval_samples_per_second": 5.971, | |
| "eval_steps_per_second": 2.993, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011346054667354307, | |
| "grad_norm": 2.9749982357025146, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 9.3068, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.012377514182568335, | |
| "grad_norm": 2.1659786701202393, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 8.5712, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.013408973697782363, | |
| "grad_norm": 2.9561119079589844, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 8.6487, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01444043321299639, | |
| "grad_norm": 2.650712013244629, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 8.0862, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.015471892728210418, | |
| "grad_norm": 3.0634942054748535, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 9.3175, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.015471892728210418, | |
| "eval_loss": 2.1145219802856445, | |
| "eval_runtime": 68.6027, | |
| "eval_samples_per_second": 5.962, | |
| "eval_steps_per_second": 2.988, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.016503352243424446, | |
| "grad_norm": 2.422914743423462, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 9.0833, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.017534811758638472, | |
| "grad_norm": 2.733120918273926, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 8.5553, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.018566271273852502, | |
| "grad_norm": 4.6515374183654785, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 9.3374, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.019597730789066528, | |
| "grad_norm": 3.3914477825164795, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 8.1143, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.020629190304280558, | |
| "grad_norm": 2.9778213500976562, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 8.22, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.020629190304280558, | |
| "eval_loss": 2.0265042781829834, | |
| "eval_runtime": 68.4228, | |
| "eval_samples_per_second": 5.978, | |
| "eval_steps_per_second": 2.996, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.021660649819494584, | |
| "grad_norm": 2.771341562271118, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 7.916, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.022692109334708613, | |
| "grad_norm": 3.1871821880340576, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 8.2355, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.02372356884992264, | |
| "grad_norm": 3.242716073989868, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 8.2872, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02475502836513667, | |
| "grad_norm": 4.141953468322754, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 8.7691, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.025786487880350695, | |
| "grad_norm": 3.8297622203826904, | |
| "learning_rate": 0.0, | |
| "loss": 8.4916, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.025786487880350695, | |
| "eval_loss": 2.0087664127349854, | |
| "eval_runtime": 68.5404, | |
| "eval_samples_per_second": 5.967, | |
| "eval_steps_per_second": 2.991, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 9512628623769600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |