| { | |
| "best_metric": 0.6313887238502502, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.020794343938448742, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008317737575379496, | |
| "grad_norm": 0.38518041372299194, | |
| "learning_rate": 2e-05, | |
| "loss": 5.0495, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008317737575379496, | |
| "eval_loss": 1.2334789037704468, | |
| "eval_runtime": 154.0564, | |
| "eval_samples_per_second": 3.291, | |
| "eval_steps_per_second": 1.649, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016635475150758993, | |
| "grad_norm": 0.3774152398109436, | |
| "learning_rate": 4e-05, | |
| "loss": 4.8592, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002495321272613849, | |
| "grad_norm": 0.3679041564464569, | |
| "learning_rate": 6e-05, | |
| "loss": 4.9567, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0033270950301517986, | |
| "grad_norm": 0.41812360286712646, | |
| "learning_rate": 8e-05, | |
| "loss": 5.1022, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004158868787689748, | |
| "grad_norm": 0.4601084887981415, | |
| "learning_rate": 0.0001, | |
| "loss": 4.9221, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004158868787689748, | |
| "eval_loss": 1.223971962928772, | |
| "eval_runtime": 154.2011, | |
| "eval_samples_per_second": 3.288, | |
| "eval_steps_per_second": 1.647, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004990642545227698, | |
| "grad_norm": 0.5520709156990051, | |
| "learning_rate": 0.00012, | |
| "loss": 4.9145, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005822416302765648, | |
| "grad_norm": 0.6887684464454651, | |
| "learning_rate": 0.00014, | |
| "loss": 4.8719, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006654190060303597, | |
| "grad_norm": 0.9003005027770996, | |
| "learning_rate": 0.00016, | |
| "loss": 4.7106, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007485963817841547, | |
| "grad_norm": 0.8912978768348694, | |
| "learning_rate": 0.00018, | |
| "loss": 4.5687, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008317737575379496, | |
| "grad_norm": 0.9802343845367432, | |
| "learning_rate": 0.0002, | |
| "loss": 4.4491, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008317737575379496, | |
| "eval_loss": 0.9914364218711853, | |
| "eval_runtime": 154.7651, | |
| "eval_samples_per_second": 3.276, | |
| "eval_steps_per_second": 1.641, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009149511332917446, | |
| "grad_norm": 1.0714654922485352, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 4.1108, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.009981285090455396, | |
| "grad_norm": 1.0546401739120483, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 3.7777, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.010813058847993346, | |
| "grad_norm": 1.1804425716400146, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 3.3691, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.011644832605531296, | |
| "grad_norm": 1.2008150815963745, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 3.2537, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.012476606363069246, | |
| "grad_norm": 1.3925896883010864, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 3.0091, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012476606363069246, | |
| "eval_loss": 0.7313758730888367, | |
| "eval_runtime": 153.6298, | |
| "eval_samples_per_second": 3.3, | |
| "eval_steps_per_second": 1.653, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013308380120607194, | |
| "grad_norm": 1.4005178213119507, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 3.0036, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.014140153878145144, | |
| "grad_norm": 1.2651536464691162, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 2.704, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.014971927635683094, | |
| "grad_norm": 1.243115782737732, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 2.8648, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.015803701393221042, | |
| "grad_norm": 1.2719112634658813, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 2.7098, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.016635475150758992, | |
| "grad_norm": 1.1509978771209717, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 2.6089, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.016635475150758992, | |
| "eval_loss": 0.6494202017784119, | |
| "eval_runtime": 153.6805, | |
| "eval_samples_per_second": 3.299, | |
| "eval_steps_per_second": 1.653, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.017467248908296942, | |
| "grad_norm": 1.283953070640564, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 2.6506, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.018299022665834892, | |
| "grad_norm": 1.1710776090621948, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 2.7642, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.019130796423372842, | |
| "grad_norm": 1.0391024351119995, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 2.4619, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.019962570180910792, | |
| "grad_norm": 1.1879003047943115, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 2.5633, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.020794343938448742, | |
| "grad_norm": 1.1049716472625732, | |
| "learning_rate": 0.0, | |
| "loss": 2.5356, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.020794343938448742, | |
| "eval_loss": 0.6313887238502502, | |
| "eval_runtime": 153.4015, | |
| "eval_samples_per_second": 3.305, | |
| "eval_steps_per_second": 1.656, | |
| "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": 1.5831121526784e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |