| { | |
| "best_metric": 1.8613815307617188, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.18365472910927455, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0073461891643709825, | |
| "grad_norm": 7.234932899475098, | |
| "learning_rate": 5e-05, | |
| "loss": 6.8656, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0073461891643709825, | |
| "eval_loss": 8.155715942382812, | |
| "eval_runtime": 62.1084, | |
| "eval_samples_per_second": 14.764, | |
| "eval_steps_per_second": 1.852, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014692378328741965, | |
| "grad_norm": 8.7951021194458, | |
| "learning_rate": 0.0001, | |
| "loss": 7.2664, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02203856749311295, | |
| "grad_norm": 9.78209114074707, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 7.0224, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02938475665748393, | |
| "grad_norm": 9.359648704528809, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 5.2157, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03673094582185491, | |
| "grad_norm": 9.396818161010742, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 4.1793, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0440771349862259, | |
| "grad_norm": 6.48800802230835, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.7958, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.051423324150596875, | |
| "grad_norm": 3.9417362213134766, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.5118, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05876951331496786, | |
| "grad_norm": 4.9853434562683105, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.5798, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06611570247933884, | |
| "grad_norm": 4.6500325202941895, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.4128, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07346189164370982, | |
| "grad_norm": 3.4421136379241943, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.2821, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08080808080808081, | |
| "grad_norm": 3.7127418518066406, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.967, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0881542699724518, | |
| "grad_norm": 4.257928848266602, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.0112, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09550045913682277, | |
| "grad_norm": 3.667210578918457, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.2075, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.10284664830119375, | |
| "grad_norm": 4.1568217277526855, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.5852, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.11019283746556474, | |
| "grad_norm": 3.56781268119812, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.2733, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11753902662993572, | |
| "grad_norm": 2.3509628772735596, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.2579, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1248852157943067, | |
| "grad_norm": 2.533644676208496, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.1316, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1322314049586777, | |
| "grad_norm": 2.614610195159912, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.8133, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.13957759412304868, | |
| "grad_norm": 2.463763952255249, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.8367, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.14692378328741965, | |
| "grad_norm": 2.8602094650268555, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.9788, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15426997245179064, | |
| "grad_norm": 3.1375627517700195, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.2217, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.16161616161616163, | |
| "grad_norm": 3.0039854049682617, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.8634, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1689623507805326, | |
| "grad_norm": 2.858977794647217, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.9036, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1763085399449036, | |
| "grad_norm": 3.589897394180298, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.7665, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.18365472910927455, | |
| "grad_norm": 3.1547627449035645, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.6272, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.18365472910927455, | |
| "eval_loss": 1.8613815307617188, | |
| "eval_runtime": 62.1061, | |
| "eval_samples_per_second": 14.765, | |
| "eval_steps_per_second": 1.852, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.984041808658432e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |