| { | |
| "best_metric": 0.7971799373626709, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.073446327683616, | |
| "eval_steps": 25, | |
| "global_step": 34, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0903954802259887, | |
| "grad_norm": 36.14955520629883, | |
| "learning_rate": 5e-05, | |
| "loss": 7.4587, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0903954802259887, | |
| "eval_loss": 7.517584800720215, | |
| "eval_runtime": 3.9481, | |
| "eval_samples_per_second": 12.664, | |
| "eval_steps_per_second": 3.293, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1807909604519774, | |
| "grad_norm": 36.21140670776367, | |
| "learning_rate": 0.0001, | |
| "loss": 7.4388, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2711864406779661, | |
| "grad_norm": 49.9202880859375, | |
| "learning_rate": 9.978331270024886e-05, | |
| "loss": 4.5541, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.3615819209039548, | |
| "grad_norm": 18.69330596923828, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.6457, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.4519774011299435, | |
| "grad_norm": 6.892326354980469, | |
| "learning_rate": 9.80623151079494e-05, | |
| "loss": 1.0008, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5423728813559322, | |
| "grad_norm": 6.923241138458252, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.9578, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.632768361581921, | |
| "grad_norm": 17.618833541870117, | |
| "learning_rate": 9.468645689567598e-05, | |
| "loss": 1.0453, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.7231638418079096, | |
| "grad_norm": 2.573690414428711, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.8191, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.8135593220338984, | |
| "grad_norm": 9.989768028259277, | |
| "learning_rate": 8.978547040132317e-05, | |
| "loss": 1.1795, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.903954802259887, | |
| "grad_norm": 1.8748440742492676, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.8322, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9943502824858758, | |
| "grad_norm": 6.087851524353027, | |
| "learning_rate": 8.354769778736406e-05, | |
| "loss": 0.9989, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.0847457627118644, | |
| "grad_norm": 8.095987319946289, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.7209, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.1751412429378532, | |
| "grad_norm": 5.422818183898926, | |
| "learning_rate": 7.62128531571699e-05, | |
| "loss": 0.8171, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.2655367231638417, | |
| "grad_norm": 6.045770645141602, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.9118, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.3559322033898304, | |
| "grad_norm": 2.086815357208252, | |
| "learning_rate": 6.80628104764508e-05, | |
| "loss": 0.8146, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.4463276836158192, | |
| "grad_norm": 1.1806037425994873, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.7984, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.536723163841808, | |
| "grad_norm": 3.5935990810394287, | |
| "learning_rate": 5.941077131483025e-05, | |
| "loss": 0.9019, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.6271186440677967, | |
| "grad_norm": 0.803607165813446, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.7858, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.7175141242937855, | |
| "grad_norm": 0.7346743941307068, | |
| "learning_rate": 5.058922868516978e-05, | |
| "loss": 0.7894, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.807909604519774, | |
| "grad_norm": 6.340599536895752, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.9671, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.8983050847457628, | |
| "grad_norm": 0.5824771523475647, | |
| "learning_rate": 4.19371895235492e-05, | |
| "loss": 0.769, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.9887005649717513, | |
| "grad_norm": 4.109841823577881, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.8763, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.07909604519774, | |
| "grad_norm": 2.5904746055603027, | |
| "learning_rate": 3.378714684283011e-05, | |
| "loss": 1.5647, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.169491525423729, | |
| "grad_norm": 1.8928107023239136, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.7833, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.2598870056497176, | |
| "grad_norm": 4.098468780517578, | |
| "learning_rate": 2.645230221263596e-05, | |
| "loss": 0.8615, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.2598870056497176, | |
| "eval_loss": 0.7971799373626709, | |
| "eval_runtime": 4.0319, | |
| "eval_samples_per_second": 12.401, | |
| "eval_steps_per_second": 3.224, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.3502824858757063, | |
| "grad_norm": 2.6116600036621094, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.7807, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.440677966101695, | |
| "grad_norm": 2.5598981380462646, | |
| "learning_rate": 2.0214529598676836e-05, | |
| "loss": 0.8252, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.5310734463276834, | |
| "grad_norm": 3.7141711711883545, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.8265, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.621468926553672, | |
| "grad_norm": 2.038482427597046, | |
| "learning_rate": 1.531354310432403e-05, | |
| "loss": 0.7861, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.711864406779661, | |
| "grad_norm": 1.7209573984146118, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.7789, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.8022598870056497, | |
| "grad_norm": 4.278275489807129, | |
| "learning_rate": 1.1937684892050604e-05, | |
| "loss": 0.8473, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.8926553672316384, | |
| "grad_norm": 1.0892584323883057, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.78, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.983050847457627, | |
| "grad_norm": 1.513576626777649, | |
| "learning_rate": 1.0216687299751144e-05, | |
| "loss": 0.8202, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 3.073446327683616, | |
| "grad_norm": 2.245659589767456, | |
| "learning_rate": 1e-05, | |
| "loss": 1.6204, | |
| "step": 34 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 34, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 4.198645954238218e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |