| { | |
| "best_metric": 2.0506653785705566, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.16116035455278002, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0064464141821112, | |
| "grad_norm": 2.7321786880493164, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5383, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0064464141821112, | |
| "eval_loss": 2.5283396244049072, | |
| "eval_runtime": 2.5159, | |
| "eval_samples_per_second": 19.874, | |
| "eval_steps_per_second": 5.167, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0128928283642224, | |
| "grad_norm": 2.698495864868164, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5499, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.019339242546333603, | |
| "grad_norm": 1.8402256965637207, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.3426, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0257856567284448, | |
| "grad_norm": 0.5552679896354675, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.1694, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.032232070910556, | |
| "grad_norm": 0.8432245850563049, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.0676, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.038678485092667206, | |
| "grad_norm": 0.7348294854164124, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.0469, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.045124899274778404, | |
| "grad_norm": 0.4715188443660736, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.9357, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0515713134568896, | |
| "grad_norm": 0.39538440108299255, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.7671, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05801772763900081, | |
| "grad_norm": 0.4434206187725067, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.6547, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.064464141821112, | |
| "grad_norm": 0.4737102687358856, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.5741, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07091055600322321, | |
| "grad_norm": 0.5129907131195068, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.7328, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07735697018533441, | |
| "grad_norm": 0.9538379907608032, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.0174, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08380338436744561, | |
| "grad_norm": 0.42058929800987244, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.2917, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09024979854955681, | |
| "grad_norm": 0.3056967258453369, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.1605, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09669621273166801, | |
| "grad_norm": 0.30461686849594116, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.0701, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1031426269137792, | |
| "grad_norm": 0.33966585993766785, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 2.0992, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1095890410958904, | |
| "grad_norm": 0.364210844039917, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.9916, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.11603545527800162, | |
| "grad_norm": 0.4053061008453369, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.9666, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12248186946011282, | |
| "grad_norm": 0.4174206256866455, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.9286, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.128928283642224, | |
| "grad_norm": 0.37758609652519226, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.8147, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13537469782433523, | |
| "grad_norm": 0.45445677638053894, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.6091, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.14182111200644643, | |
| "grad_norm": 0.42483848333358765, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.5241, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.14826752618855762, | |
| "grad_norm": 0.3693537414073944, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.5441, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.15471394037066882, | |
| "grad_norm": 0.5647397637367249, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.7255, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.16116035455278002, | |
| "grad_norm": 0.976772665977478, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 2.1579, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16116035455278002, | |
| "eval_loss": 2.0506653785705566, | |
| "eval_runtime": 2.7588, | |
| "eval_samples_per_second": 18.124, | |
| "eval_steps_per_second": 4.712, | |
| "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": 8.38299861165015e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |