| { | |
| "best_metric": 0.253146231174469, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.0015966534144433268, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.386613657773307e-05, | |
| "grad_norm": 0.8590987920761108, | |
| "learning_rate": 2e-05, | |
| "loss": 1.0055, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.386613657773307e-05, | |
| "eval_loss": 1.0578943490982056, | |
| "eval_runtime": 1038.2948, | |
| "eval_samples_per_second": 6.35, | |
| "eval_steps_per_second": 3.175, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00012773227315546613, | |
| "grad_norm": 0.8940750956535339, | |
| "learning_rate": 4e-05, | |
| "loss": 1.0022, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0001915984097331992, | |
| "grad_norm": 0.88837069272995, | |
| "learning_rate": 6e-05, | |
| "loss": 1.016, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00025546454631093226, | |
| "grad_norm": 0.8922818303108215, | |
| "learning_rate": 8e-05, | |
| "loss": 0.9639, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00031933068288866537, | |
| "grad_norm": 1.091623067855835, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0482, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00031933068288866537, | |
| "eval_loss": 0.9187586903572083, | |
| "eval_runtime": 1037.2065, | |
| "eval_samples_per_second": 6.356, | |
| "eval_steps_per_second": 3.179, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0003831968194663984, | |
| "grad_norm": 0.9860396385192871, | |
| "learning_rate": 0.00012, | |
| "loss": 0.8989, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0004470629560441315, | |
| "grad_norm": 0.7333329916000366, | |
| "learning_rate": 0.00014, | |
| "loss": 0.7677, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005109290926218645, | |
| "grad_norm": 0.7881752252578735, | |
| "learning_rate": 0.00016, | |
| "loss": 0.6707, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0005747952291995977, | |
| "grad_norm": 1.1973943710327148, | |
| "learning_rate": 0.00018, | |
| "loss": 0.6567, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006386613657773307, | |
| "grad_norm": 1.0787795782089233, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5205, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006386613657773307, | |
| "eval_loss": 0.4261242747306824, | |
| "eval_runtime": 1057.0365, | |
| "eval_samples_per_second": 6.237, | |
| "eval_steps_per_second": 3.119, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007025275023550638, | |
| "grad_norm": 0.8175431489944458, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 0.4296, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0007663936389327968, | |
| "grad_norm": 0.7449086904525757, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 0.4055, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0008302597755105299, | |
| "grad_norm": 1.2498811483383179, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.3413, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.000894125912088263, | |
| "grad_norm": 0.8443876504898071, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.3248, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0009579920486659961, | |
| "grad_norm": 0.8828296065330505, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.3644, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0009579920486659961, | |
| "eval_loss": 0.3001621663570404, | |
| "eval_runtime": 1043.9309, | |
| "eval_samples_per_second": 6.316, | |
| "eval_steps_per_second": 3.158, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.001021858185243729, | |
| "grad_norm": 0.7488011717796326, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.2425, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0010857243218214622, | |
| "grad_norm": 0.6179611086845398, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.3411, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0011495904583991954, | |
| "grad_norm": 0.7472450137138367, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.3922, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0012134565949769283, | |
| "grad_norm": 0.6675222516059875, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.4745, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0012773227315546615, | |
| "grad_norm": 0.5154255032539368, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.2231, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0012773227315546615, | |
| "eval_loss": 0.2597002685070038, | |
| "eval_runtime": 1046.8452, | |
| "eval_samples_per_second": 6.298, | |
| "eval_steps_per_second": 3.149, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0013411888681323944, | |
| "grad_norm": 0.6128504872322083, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 0.2518, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0014050550047101276, | |
| "grad_norm": 0.6355711817741394, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.2522, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0014689211412878607, | |
| "grad_norm": 0.6158922910690308, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 0.3557, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0015327872778655937, | |
| "grad_norm": 0.565183162689209, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 0.3031, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0015966534144433268, | |
| "grad_norm": 0.6277245283126831, | |
| "learning_rate": 0.0, | |
| "loss": 0.4473, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0015966534144433268, | |
| "eval_loss": 0.253146231174469, | |
| "eval_runtime": 1036.8027, | |
| "eval_samples_per_second": 6.359, | |
| "eval_steps_per_second": 3.18, | |
| "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": 5594931850641408.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |