| { | |
| "best_metric": 0.8232725858688354, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.0015144172522413375, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.05766900896535e-05, | |
| "grad_norm": 1.4260191917419434, | |
| "learning_rate": 2e-05, | |
| "loss": 4.3411, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.05766900896535e-05, | |
| "eval_loss": 1.1264984607696533, | |
| "eval_runtime": 1822.6857, | |
| "eval_samples_per_second": 3.814, | |
| "eval_steps_per_second": 1.907, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000121153380179307, | |
| "grad_norm": 1.2020275592803955, | |
| "learning_rate": 4e-05, | |
| "loss": 3.9647, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0001817300702689605, | |
| "grad_norm": 1.0031434297561646, | |
| "learning_rate": 6e-05, | |
| "loss": 4.5757, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000242306760358614, | |
| "grad_norm": 1.25130295753479, | |
| "learning_rate": 8e-05, | |
| "loss": 5.2439, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0003028834504482675, | |
| "grad_norm": 1.5368229150772095, | |
| "learning_rate": 0.0001, | |
| "loss": 5.0161, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0003028834504482675, | |
| "eval_loss": 1.1220825910568237, | |
| "eval_runtime": 1825.9983, | |
| "eval_samples_per_second": 3.807, | |
| "eval_steps_per_second": 1.904, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000363460140537921, | |
| "grad_norm": 1.1691585779190063, | |
| "learning_rate": 0.00012, | |
| "loss": 4.5836, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0004240368306275745, | |
| "grad_norm": 1.1613962650299072, | |
| "learning_rate": 0.00014, | |
| "loss": 4.7666, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.000484613520717228, | |
| "grad_norm": 1.5307047367095947, | |
| "learning_rate": 0.00016, | |
| "loss": 5.1628, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0005451902108068815, | |
| "grad_norm": 2.651588201522827, | |
| "learning_rate": 0.00018, | |
| "loss": 4.6813, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000605766900896535, | |
| "grad_norm": 2.275118112564087, | |
| "learning_rate": 0.0002, | |
| "loss": 3.931, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000605766900896535, | |
| "eval_loss": 0.9754608869552612, | |
| "eval_runtime": 1820.9699, | |
| "eval_samples_per_second": 3.817, | |
| "eval_steps_per_second": 1.909, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006663435909861885, | |
| "grad_norm": 2.1838300228118896, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 3.4532, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.000726920281075842, | |
| "grad_norm": 3.5601911544799805, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 3.6117, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0007874969711654955, | |
| "grad_norm": 2.2791738510131836, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 3.292, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.000848073661255149, | |
| "grad_norm": 2.384220838546753, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 3.4256, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0009086503513448025, | |
| "grad_norm": 3.14040207862854, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 3.6856, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0009086503513448025, | |
| "eval_loss": 0.8792188167572021, | |
| "eval_runtime": 1814.5544, | |
| "eval_samples_per_second": 3.831, | |
| "eval_steps_per_second": 1.916, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.000969227041434456, | |
| "grad_norm": 2.542506217956543, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.8472, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0010298037315241094, | |
| "grad_norm": 3.992337226867676, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 3.9006, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.001090380421613763, | |
| "grad_norm": 3.300311326980591, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 2.8979, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0011509571117034165, | |
| "grad_norm": 2.4355976581573486, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 3.3161, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00121153380179307, | |
| "grad_norm": 2.5673999786376953, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 3.8681, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00121153380179307, | |
| "eval_loss": 0.8308025002479553, | |
| "eval_runtime": 1817.2994, | |
| "eval_samples_per_second": 3.825, | |
| "eval_steps_per_second": 1.913, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0012721104918827235, | |
| "grad_norm": 2.17309832572937, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 3.0809, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.001332687181972377, | |
| "grad_norm": 2.5467963218688965, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 2.9565, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0013932638720620305, | |
| "grad_norm": 2.220905065536499, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 2.8154, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.001453840562151684, | |
| "grad_norm": 2.369903802871704, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 3.3989, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0015144172522413375, | |
| "grad_norm": 2.4179704189300537, | |
| "learning_rate": 0.0, | |
| "loss": 2.5863, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0015144172522413375, | |
| "eval_loss": 0.8232725858688354, | |
| "eval_runtime": 1821.2062, | |
| "eval_samples_per_second": 3.817, | |
| "eval_steps_per_second": 1.909, | |
| "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": 1.698683682816e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |