| { | |
| "best_metric": 0.9508792757987976, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.3421727972626176, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013686911890504704, | |
| "grad_norm": 0.2839342951774597, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9237, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013686911890504704, | |
| "eval_loss": 1.1619060039520264, | |
| "eval_runtime": 0.8972, | |
| "eval_samples_per_second": 55.728, | |
| "eval_steps_per_second": 14.489, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02737382378100941, | |
| "grad_norm": 0.293414443731308, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9281, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.041060735671514116, | |
| "grad_norm": 0.2849063575267792, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 0.9689, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05474764756201882, | |
| "grad_norm": 0.2456403225660324, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 0.9948, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06843455945252352, | |
| "grad_norm": 0.23837387561798096, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 1.0023, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08212147134302823, | |
| "grad_norm": 0.28003859519958496, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 1.012, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09580838323353294, | |
| "grad_norm": 0.27999797463417053, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 1.0161, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10949529512403763, | |
| "grad_norm": 0.2867315113544464, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 1.0349, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12318220701454234, | |
| "grad_norm": 0.2672511339187622, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 1.0462, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13686911890504705, | |
| "grad_norm": 0.3040759265422821, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 1.0649, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15055603079555174, | |
| "grad_norm": 0.32777538895606995, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 1.0774, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.16424294268605646, | |
| "grad_norm": 0.339109867811203, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 1.0691, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.17792985457656116, | |
| "grad_norm": 0.2890492081642151, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 0.8679, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.19161676646706588, | |
| "grad_norm": 0.2887008786201477, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 0.8448, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.20530367835757057, | |
| "grad_norm": 0.2689841091632843, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 0.8396, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.21899059024807527, | |
| "grad_norm": 0.21305231750011444, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 0.8863, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.23267750213858, | |
| "grad_norm": 0.1798112839460373, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 0.8613, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.24636441402908468, | |
| "grad_norm": 0.18163719773292542, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 0.9082, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2600513259195894, | |
| "grad_norm": 0.19334067404270172, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 0.9359, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2737382378100941, | |
| "grad_norm": 0.20036861300468445, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 0.9288, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2874251497005988, | |
| "grad_norm": 0.23231102526187897, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 0.9439, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3011120615911035, | |
| "grad_norm": 0.249299556016922, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 0.9275, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.31479897348160824, | |
| "grad_norm": 0.29132458567619324, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 0.9782, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.32848588537211293, | |
| "grad_norm": 0.36819663643836975, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 1.0517, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3421727972626176, | |
| "grad_norm": 0.4708142578601837, | |
| "learning_rate": 1e-05, | |
| "loss": 0.9962, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3421727972626176, | |
| "eval_loss": 0.9508792757987976, | |
| "eval_runtime": 0.8843, | |
| "eval_samples_per_second": 56.543, | |
| "eval_steps_per_second": 14.701, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": 4.172290816212992e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |