| { | |
| "best_metric": 2.718066692352295, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.4106776180698152, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01642710472279261, | |
| "grad_norm": 0.83213871717453, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 4.1897, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01642710472279261, | |
| "eval_loss": 4.481392860412598, | |
| "eval_runtime": 2.0431, | |
| "eval_samples_per_second": 24.472, | |
| "eval_steps_per_second": 6.363, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03285420944558522, | |
| "grad_norm": 0.8668023943901062, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 4.2593, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.049281314168377825, | |
| "grad_norm": 0.893962025642395, | |
| "learning_rate": 0.0001, | |
| "loss": 4.1721, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06570841889117043, | |
| "grad_norm": 0.9961223602294922, | |
| "learning_rate": 9.99571699711836e-05, | |
| "loss": 4.157, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08213552361396304, | |
| "grad_norm": 1.0611786842346191, | |
| "learning_rate": 9.982876141412856e-05, | |
| "loss": 4.1331, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09856262833675565, | |
| "grad_norm": 1.086363673210144, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 4.0068, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11498973305954825, | |
| "grad_norm": 1.2030413150787354, | |
| "learning_rate": 9.931634888554937e-05, | |
| "loss": 3.7748, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.13141683778234087, | |
| "grad_norm": 1.2147985696792603, | |
| "learning_rate": 9.893332032039701e-05, | |
| "loss": 3.7078, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.14784394250513347, | |
| "grad_norm": 1.1192842721939087, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 3.4211, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.16427104722792607, | |
| "grad_norm": 1.0096282958984375, | |
| "learning_rate": 9.791726278367022e-05, | |
| "loss": 3.4068, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1806981519507187, | |
| "grad_norm": 1.0285571813583374, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 3.2925, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1971252566735113, | |
| "grad_norm": 1.28445303440094, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 3.2952, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2135523613963039, | |
| "grad_norm": 0.6762813925743103, | |
| "learning_rate": 9.578385041664925e-05, | |
| "loss": 3.0429, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2299794661190965, | |
| "grad_norm": 0.7080486416816711, | |
| "learning_rate": 9.491548749301997e-05, | |
| "loss": 3.2334, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2464065708418891, | |
| "grad_norm": 0.7197335362434387, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 3.1313, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.26283367556468173, | |
| "grad_norm": 0.742653489112854, | |
| "learning_rate": 9.295261506157986e-05, | |
| "loss": 3.0879, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2792607802874743, | |
| "grad_norm": 0.6773972511291504, | |
| "learning_rate": 9.186184199300464e-05, | |
| "loss": 2.9061, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.29568788501026694, | |
| "grad_norm": 0.6461683511734009, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.8895, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.31211498973305957, | |
| "grad_norm": 0.5850861072540283, | |
| "learning_rate": 8.947199994035401e-05, | |
| "loss": 2.9273, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.32854209445585214, | |
| "grad_norm": 0.6079311966896057, | |
| "learning_rate": 8.817748015645558e-05, | |
| "loss": 2.8932, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.34496919917864477, | |
| "grad_norm": 0.6674569845199585, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.65, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3613963039014374, | |
| "grad_norm": 0.7020171284675598, | |
| "learning_rate": 8.540155934270471e-05, | |
| "loss": 2.79, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.37782340862423, | |
| "grad_norm": 0.6968078017234802, | |
| "learning_rate": 8.392544243589427e-05, | |
| "loss": 2.883, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3942505133470226, | |
| "grad_norm": 0.9217126965522766, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 2.7329, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4106776180698152, | |
| "grad_norm": 1.5251928567886353, | |
| "learning_rate": 8.081093963579707e-05, | |
| "loss": 2.4426, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4106776180698152, | |
| "eval_loss": 2.718066692352295, | |
| "eval_runtime": 2.0417, | |
| "eval_samples_per_second": 24.49, | |
| "eval_steps_per_second": 6.367, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 5.27587608625152e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |