| { | |
| "best_metric": 11.024052619934082, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.00934317481080071, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003737269924320284, | |
| "grad_norm": 2.00592041015625, | |
| "learning_rate": 2e-05, | |
| "loss": 44.5025, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003737269924320284, | |
| "eval_loss": 11.121650695800781, | |
| "eval_runtime": 8.1818, | |
| "eval_samples_per_second": 137.744, | |
| "eval_steps_per_second": 68.933, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007474539848640568, | |
| "grad_norm": 2.147092342376709, | |
| "learning_rate": 4e-05, | |
| "loss": 44.5508, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011211809772960853, | |
| "grad_norm": 2.1971206665039062, | |
| "learning_rate": 6e-05, | |
| "loss": 44.5813, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014949079697281135, | |
| "grad_norm": 2.0062906742095947, | |
| "learning_rate": 8e-05, | |
| "loss": 44.4318, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001868634962160142, | |
| "grad_norm": 1.9143476486206055, | |
| "learning_rate": 0.0001, | |
| "loss": 44.4406, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001868634962160142, | |
| "eval_loss": 11.114669799804688, | |
| "eval_runtime": 7.0647, | |
| "eval_samples_per_second": 159.525, | |
| "eval_steps_per_second": 79.833, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0022423619545921705, | |
| "grad_norm": 2.12149715423584, | |
| "learning_rate": 0.00012, | |
| "loss": 44.4751, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002616088947024199, | |
| "grad_norm": 1.9612126350402832, | |
| "learning_rate": 0.00014, | |
| "loss": 44.4143, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002989815939456227, | |
| "grad_norm": 2.099393844604492, | |
| "learning_rate": 0.00016, | |
| "loss": 44.502, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0033635429318882555, | |
| "grad_norm": 2.058532953262329, | |
| "learning_rate": 0.00018, | |
| "loss": 44.3788, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003737269924320284, | |
| "grad_norm": 1.868243932723999, | |
| "learning_rate": 0.0002, | |
| "loss": 44.3308, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003737269924320284, | |
| "eval_loss": 11.091446876525879, | |
| "eval_runtime": 7.1172, | |
| "eval_samples_per_second": 158.35, | |
| "eval_steps_per_second": 79.245, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0041109969167523125, | |
| "grad_norm": 2.0944066047668457, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 44.3654, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004484723909184341, | |
| "grad_norm": 2.1180760860443115, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 44.4339, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0048584509016163695, | |
| "grad_norm": 2.2716116905212402, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 44.2943, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005232177894048398, | |
| "grad_norm": 2.27824330329895, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 44.2583, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005605904886480426, | |
| "grad_norm": 2.1385979652404785, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 44.249, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005605904886480426, | |
| "eval_loss": 11.055086135864258, | |
| "eval_runtime": 7.0721, | |
| "eval_samples_per_second": 159.358, | |
| "eval_steps_per_second": 79.75, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005979631878912454, | |
| "grad_norm": 2.326420545578003, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 44.1148, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.006353358871344483, | |
| "grad_norm": 2.224518060684204, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 44.2163, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006727085863776511, | |
| "grad_norm": 2.348910331726074, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 44.1174, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00710081285620854, | |
| "grad_norm": 2.201992988586426, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 44.064, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.007474539848640568, | |
| "grad_norm": 2.425978660583496, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 44.2236, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007474539848640568, | |
| "eval_loss": 11.029707908630371, | |
| "eval_runtime": 7.2874, | |
| "eval_samples_per_second": 154.651, | |
| "eval_steps_per_second": 77.394, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007848266841072597, | |
| "grad_norm": 2.3549764156341553, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 44.1263, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.008221993833504625, | |
| "grad_norm": 2.45450496673584, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 44.045, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.008595720825936654, | |
| "grad_norm": 2.3912954330444336, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 44.1419, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.008969447818368682, | |
| "grad_norm": 2.5055766105651855, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 44.0682, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00934317481080071, | |
| "grad_norm": 2.4970130920410156, | |
| "learning_rate": 0.0, | |
| "loss": 44.0782, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00934317481080071, | |
| "eval_loss": 11.024052619934082, | |
| "eval_runtime": 7.133, | |
| "eval_samples_per_second": 157.997, | |
| "eval_steps_per_second": 79.069, | |
| "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": 279699259392.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |