| { | |
| "best_metric": 0.3661760091781616, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.28530670470756064, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.011412268188302425, | |
| "grad_norm": 36.33183670043945, | |
| "learning_rate": 5e-05, | |
| "loss": 11.7588, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011412268188302425, | |
| "eval_loss": 12.253931045532227, | |
| "eval_runtime": 5.1277, | |
| "eval_samples_per_second": 115.061, | |
| "eval_steps_per_second": 14.431, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02282453637660485, | |
| "grad_norm": 38.03749465942383, | |
| "learning_rate": 0.0001, | |
| "loss": 11.7128, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.034236804564907276, | |
| "grad_norm": 34.40321731567383, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.2924, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0456490727532097, | |
| "grad_norm": 35.03947448730469, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 6.1685, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05706134094151213, | |
| "grad_norm": 34.541263580322266, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.3378, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06847360912981455, | |
| "grad_norm": 29.1164608001709, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.0856, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07988587731811697, | |
| "grad_norm": 12.02340316772461, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.7802, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0912981455064194, | |
| "grad_norm": 2.4589977264404297, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.3801, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.10271041369472182, | |
| "grad_norm": 21.196531295776367, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.6962, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11412268188302425, | |
| "grad_norm": 40.947784423828125, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.308, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12553495007132667, | |
| "grad_norm": 17.053909301757812, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.7331, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1369472182596291, | |
| "grad_norm": 1.7771241664886475, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.3574, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14835948644793154, | |
| "grad_norm": 5.181107044219971, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.4103, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.15977175463623394, | |
| "grad_norm": 1.4818410873413086, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.3617, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.17118402282453637, | |
| "grad_norm": 1.908239722251892, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.3531, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1825962910128388, | |
| "grad_norm": 0.7846085429191589, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.3429, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.19400855920114124, | |
| "grad_norm": 1.3545622825622559, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.3578, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.20542082738944364, | |
| "grad_norm": 0.6806542277336121, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.3485, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.21683309557774608, | |
| "grad_norm": 0.9577310681343079, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.3522, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2282453637660485, | |
| "grad_norm": 1.8114031553268433, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.3566, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2396576319543509, | |
| "grad_norm": 0.8351974487304688, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.3394, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.25106990014265335, | |
| "grad_norm": 0.902949333190918, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.3412, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2624821683309558, | |
| "grad_norm": 2.9680609703063965, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.3829, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2738944365192582, | |
| "grad_norm": 2.181551456451416, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.3636, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.28530670470756064, | |
| "grad_norm": 1.35411536693573, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.3406, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.28530670470756064, | |
| "eval_loss": 0.3661760091781616, | |
| "eval_runtime": 5.1237, | |
| "eval_samples_per_second": 115.152, | |
| "eval_steps_per_second": 14.443, | |
| "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": 3.91521434075136e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |