| { | |
| "best_metric": 1.4961340427398682, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.044370493621741544, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0022185246810870773, | |
| "grad_norm": 3.410060405731201, | |
| "learning_rate": 2e-05, | |
| "loss": 2.6724, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022185246810870773, | |
| "eval_loss": 3.1044023036956787, | |
| "eval_runtime": 27.7569, | |
| "eval_samples_per_second": 6.845, | |
| "eval_steps_per_second": 3.423, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004437049362174155, | |
| "grad_norm": 6.068449974060059, | |
| "learning_rate": 4e-05, | |
| "loss": 3.3536, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0066555740432612314, | |
| "grad_norm": 4.327425479888916, | |
| "learning_rate": 6e-05, | |
| "loss": 3.4569, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00887409872434831, | |
| "grad_norm": 3.617367744445801, | |
| "learning_rate": 8e-05, | |
| "loss": 2.2977, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011092623405435386, | |
| "grad_norm": 4.4512248039245605, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5123, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.011092623405435386, | |
| "eval_loss": 2.8229851722717285, | |
| "eval_runtime": 27.2081, | |
| "eval_samples_per_second": 6.983, | |
| "eval_steps_per_second": 3.492, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013311148086522463, | |
| "grad_norm": 5.197371482849121, | |
| "learning_rate": 0.00012, | |
| "loss": 2.9662, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01552967276760954, | |
| "grad_norm": 3.9593281745910645, | |
| "learning_rate": 0.00014, | |
| "loss": 2.3009, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01774819744869662, | |
| "grad_norm": 4.19056510925293, | |
| "learning_rate": 0.00016, | |
| "loss": 2.4627, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.019966722129783693, | |
| "grad_norm": 4.832342147827148, | |
| "learning_rate": 0.00018, | |
| "loss": 2.0288, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.022185246810870772, | |
| "grad_norm": 3.161303758621216, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7657, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.022185246810870772, | |
| "eval_loss": 1.832586646080017, | |
| "eval_runtime": 27.1632, | |
| "eval_samples_per_second": 6.995, | |
| "eval_steps_per_second": 3.497, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.024403771491957847, | |
| "grad_norm": 4.72938871383667, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 1.6882, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.026622296173044926, | |
| "grad_norm": 4.860479831695557, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 1.647, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.028840820854132, | |
| "grad_norm": 4.814433574676514, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.5965, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03105934553521908, | |
| "grad_norm": 5.18036413192749, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 1.7878, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.033277870216306155, | |
| "grad_norm": 4.883513927459717, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.3328, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.033277870216306155, | |
| "eval_loss": 1.5886924266815186, | |
| "eval_runtime": 27.426, | |
| "eval_samples_per_second": 6.928, | |
| "eval_steps_per_second": 3.464, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03549639489739324, | |
| "grad_norm": 3.9491324424743652, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.4555, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03771491957848031, | |
| "grad_norm": 5.12498140335083, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.5828, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03993344425956739, | |
| "grad_norm": 3.5658392906188965, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.3126, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04215196894065446, | |
| "grad_norm": 3.676525354385376, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.4991, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.044370493621741544, | |
| "grad_norm": 3.1659774780273438, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.341, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.044370493621741544, | |
| "eval_loss": 1.4961340427398682, | |
| "eval_runtime": 27.3853, | |
| "eval_samples_per_second": 6.938, | |
| "eval_steps_per_second": 3.469, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 3699128496291840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |