| { | |
| "best_metric": 11.051278114318848, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.08156606851549755, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0032626427406199023, | |
| "grad_norm": 0.9323341846466064, | |
| "learning_rate": 2e-05, | |
| "loss": 44.3182, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0032626427406199023, | |
| "eval_loss": 11.076725006103516, | |
| "eval_runtime": 1.4226, | |
| "eval_samples_per_second": 91.379, | |
| "eval_steps_per_second": 45.69, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0065252854812398045, | |
| "grad_norm": 1.062995195388794, | |
| "learning_rate": 4e-05, | |
| "loss": 44.2994, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009787928221859706, | |
| "grad_norm": 1.0153011083602905, | |
| "learning_rate": 6e-05, | |
| "loss": 44.2882, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013050570962479609, | |
| "grad_norm": 0.991928219795227, | |
| "learning_rate": 8e-05, | |
| "loss": 44.3067, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01631321370309951, | |
| "grad_norm": 0.9939742684364319, | |
| "learning_rate": 0.0001, | |
| "loss": 44.2967, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01631321370309951, | |
| "eval_loss": 11.075981140136719, | |
| "eval_runtime": 0.7294, | |
| "eval_samples_per_second": 178.229, | |
| "eval_steps_per_second": 89.115, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01957585644371941, | |
| "grad_norm": 0.976222574710846, | |
| "learning_rate": 0.00012, | |
| "loss": 44.2904, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.022838499184339316, | |
| "grad_norm": 1.0003511905670166, | |
| "learning_rate": 0.00014, | |
| "loss": 44.2975, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.026101141924959218, | |
| "grad_norm": 1.0365238189697266, | |
| "learning_rate": 0.00016, | |
| "loss": 44.2978, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02936378466557912, | |
| "grad_norm": 1.065255880355835, | |
| "learning_rate": 0.00018, | |
| "loss": 44.2773, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03262642740619902, | |
| "grad_norm": 0.9979621767997742, | |
| "learning_rate": 0.0002, | |
| "loss": 44.3153, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03262642740619902, | |
| "eval_loss": 11.069252967834473, | |
| "eval_runtime": 0.724, | |
| "eval_samples_per_second": 179.563, | |
| "eval_steps_per_second": 89.781, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03588907014681892, | |
| "grad_norm": 1.0355585813522339, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 44.2574, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03915171288743882, | |
| "grad_norm": 0.9954984188079834, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 44.2634, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04241435562805873, | |
| "grad_norm": 1.012833595275879, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 44.2439, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04567699836867863, | |
| "grad_norm": 1.0343108177185059, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 44.2441, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.048939641109298535, | |
| "grad_norm": 0.9532853960990906, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 44.2595, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.048939641109298535, | |
| "eval_loss": 11.059078216552734, | |
| "eval_runtime": 0.8276, | |
| "eval_samples_per_second": 157.081, | |
| "eval_steps_per_second": 78.541, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.052202283849918436, | |
| "grad_norm": 1.0444512367248535, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 44.234, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05546492659053834, | |
| "grad_norm": 1.0665297508239746, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 44.2096, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05872756933115824, | |
| "grad_norm": 1.0649420022964478, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 44.1898, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06199021207177814, | |
| "grad_norm": 1.1307687759399414, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 44.2054, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06525285481239804, | |
| "grad_norm": 0.9438048601150513, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 44.2332, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06525285481239804, | |
| "eval_loss": 11.052212715148926, | |
| "eval_runtime": 0.8374, | |
| "eval_samples_per_second": 155.247, | |
| "eval_steps_per_second": 77.623, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06851549755301795, | |
| "grad_norm": 1.0551722049713135, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 44.1937, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07177814029363784, | |
| "grad_norm": 0.9978577494621277, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 44.2144, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07504078303425775, | |
| "grad_norm": 1.056475043296814, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 44.2002, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07830342577487764, | |
| "grad_norm": 1.0541832447052002, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 44.2104, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08156606851549755, | |
| "grad_norm": 1.0341196060180664, | |
| "learning_rate": 0.0, | |
| "loss": 44.2035, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08156606851549755, | |
| "eval_loss": 11.051278114318848, | |
| "eval_runtime": 0.7873, | |
| "eval_samples_per_second": 165.123, | |
| "eval_steps_per_second": 82.562, | |
| "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": 20919091200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |