| { | |
| "best_metric": 11.929618835449219, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.11217049915872125, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002243409983174425, | |
| "grad_norm": 0.020893922075629234, | |
| "learning_rate": 5e-06, | |
| "loss": 11.9328, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002243409983174425, | |
| "eval_loss": 11.932412147521973, | |
| "eval_runtime": 4.0488, | |
| "eval_samples_per_second": 185.485, | |
| "eval_steps_per_second": 23.217, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00448681996634885, | |
| "grad_norm": 0.02059100568294525, | |
| "learning_rate": 1e-05, | |
| "loss": 11.9339, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006730229949523275, | |
| "grad_norm": 0.019679663702845573, | |
| "learning_rate": 1.5e-05, | |
| "loss": 11.9333, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0089736399326977, | |
| "grad_norm": 0.01955411024391651, | |
| "learning_rate": 2e-05, | |
| "loss": 11.9326, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011217049915872126, | |
| "grad_norm": 0.017372841015458107, | |
| "learning_rate": 2.5e-05, | |
| "loss": 11.9329, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01346045989904655, | |
| "grad_norm": 0.018285011872649193, | |
| "learning_rate": 3e-05, | |
| "loss": 11.9328, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015703869882220976, | |
| "grad_norm": 0.019042452797293663, | |
| "learning_rate": 3.5e-05, | |
| "loss": 11.9325, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0179472798653954, | |
| "grad_norm": 0.01803368702530861, | |
| "learning_rate": 4e-05, | |
| "loss": 11.933, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.020190689848569827, | |
| "grad_norm": 0.016315225511789322, | |
| "learning_rate": 4.5e-05, | |
| "loss": 11.9328, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.022434099831744252, | |
| "grad_norm": 0.01673940010368824, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9328, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.024677509814918678, | |
| "grad_norm": 0.013101082295179367, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 11.9339, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0269209197980931, | |
| "grad_norm": 0.012066581286489964, | |
| "learning_rate": 6e-05, | |
| "loss": 11.9315, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.029164329781267526, | |
| "grad_norm": 0.013472984544932842, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 11.9321, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03140773976444195, | |
| "grad_norm": 0.01844089850783348, | |
| "learning_rate": 7e-05, | |
| "loss": 11.9313, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03365114974761638, | |
| "grad_norm": 0.016358327120542526, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 11.9319, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0358945597307908, | |
| "grad_norm": 0.01452179066836834, | |
| "learning_rate": 8e-05, | |
| "loss": 11.9312, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03813796971396523, | |
| "grad_norm": 0.014436909928917885, | |
| "learning_rate": 8.5e-05, | |
| "loss": 11.9319, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.040381379697139654, | |
| "grad_norm": 0.014677215367555618, | |
| "learning_rate": 9e-05, | |
| "loss": 11.9322, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04262478968031408, | |
| "grad_norm": 0.020382890477776527, | |
| "learning_rate": 9.5e-05, | |
| "loss": 11.9319, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.044868199663488505, | |
| "grad_norm": 0.020231682807207108, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9305, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04711160964666293, | |
| "grad_norm": 0.018099000677466393, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 11.9309, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.049355019629837356, | |
| "grad_norm": 0.015480943955481052, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 11.9323, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.051598429613011774, | |
| "grad_norm": 0.016374170780181885, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 11.9319, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0538418395961862, | |
| "grad_norm": 0.024180244654417038, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 11.9327, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.056085249579360626, | |
| "grad_norm": 0.025373732671141624, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 11.9319, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.056085249579360626, | |
| "eval_loss": 11.931512832641602, | |
| "eval_runtime": 4.0447, | |
| "eval_samples_per_second": 185.677, | |
| "eval_steps_per_second": 23.241, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05832865956253505, | |
| "grad_norm": 0.021957021206617355, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 11.9322, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06057206954570948, | |
| "grad_norm": 0.025794783607125282, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 11.9327, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0628154795288839, | |
| "grad_norm": 0.034966181963682175, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 11.9313, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06505888951205833, | |
| "grad_norm": 0.032141417264938354, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 11.9309, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.06730229949523275, | |
| "grad_norm": 0.036759525537490845, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 11.9322, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06954570947840717, | |
| "grad_norm": 0.028740139678120613, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 11.9313, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0717891194615816, | |
| "grad_norm": 0.03210673853754997, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 11.931, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.07403252944475602, | |
| "grad_norm": 0.05024946480989456, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 11.9295, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.07627593942793046, | |
| "grad_norm": 0.041959248483181, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 11.932, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.07851934941110487, | |
| "grad_norm": 0.050003744661808014, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9288, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08076275939427931, | |
| "grad_norm": 0.04736671969294548, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 11.9286, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.08300616937745373, | |
| "grad_norm": 0.0493813119828701, | |
| "learning_rate": 3.960441545911204e-05, | |
| "loss": 11.9302, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.08524957936062816, | |
| "grad_norm": 0.04406358674168587, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 11.9318, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.08749298934380258, | |
| "grad_norm": 0.05293726176023483, | |
| "learning_rate": 2.9663167846209998e-05, | |
| "loss": 11.9301, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.08973639932697701, | |
| "grad_norm": 0.04568186402320862, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 11.9317, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09197980931015143, | |
| "grad_norm": 0.06105807051062584, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 11.9306, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.09422321929332586, | |
| "grad_norm": 0.05900374799966812, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 11.9279, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.09646662927650028, | |
| "grad_norm": 0.05491477623581886, | |
| "learning_rate": 1.2842758726130283e-05, | |
| "loss": 11.9291, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.09871003925967471, | |
| "grad_norm": 0.039628300815820694, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 11.9298, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.10095344924284913, | |
| "grad_norm": 0.05878068134188652, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 11.9303, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10319685922602355, | |
| "grad_norm": 0.06594429910182953, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 11.9312, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.10544026920919798, | |
| "grad_norm": 0.05928008258342743, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 11.9317, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1076836791923724, | |
| "grad_norm": 0.07683888077735901, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 11.9279, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.10992708917554683, | |
| "grad_norm": 0.06153682991862297, | |
| "learning_rate": 2.7390523158633554e-07, | |
| "loss": 11.9302, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.11217049915872125, | |
| "grad_norm": 0.06444248557090759, | |
| "learning_rate": 0.0, | |
| "loss": 11.9299, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11217049915872125, | |
| "eval_loss": 11.929618835449219, | |
| "eval_runtime": 4.0408, | |
| "eval_samples_per_second": 185.856, | |
| "eval_steps_per_second": 23.263, | |
| "step": 50 | |
| } | |
| ], | |
| "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": 3, | |
| "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": 241041408000.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |