| { | |
| "best_metric": 0.4004054665565491, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.11695906432748537, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004678362573099415, | |
| "grad_norm": 1.2472007274627686, | |
| "learning_rate": 2e-05, | |
| "loss": 2.9851, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004678362573099415, | |
| "eval_loss": 0.8073704838752747, | |
| "eval_runtime": 11.5144, | |
| "eval_samples_per_second": 7.816, | |
| "eval_steps_per_second": 3.908, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00935672514619883, | |
| "grad_norm": 1.2594548463821411, | |
| "learning_rate": 4e-05, | |
| "loss": 3.3131, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.014035087719298246, | |
| "grad_norm": 1.1184676885604858, | |
| "learning_rate": 6e-05, | |
| "loss": 3.4015, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01871345029239766, | |
| "grad_norm": 1.0936832427978516, | |
| "learning_rate": 8e-05, | |
| "loss": 3.0634, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.023391812865497075, | |
| "grad_norm": 1.1260085105895996, | |
| "learning_rate": 0.0001, | |
| "loss": 2.9785, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.023391812865497075, | |
| "eval_loss": 0.784497082233429, | |
| "eval_runtime": 11.4915, | |
| "eval_samples_per_second": 7.832, | |
| "eval_steps_per_second": 3.916, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.028070175438596492, | |
| "grad_norm": 1.3645236492156982, | |
| "learning_rate": 0.00012, | |
| "loss": 2.8643, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03274853801169591, | |
| "grad_norm": 1.2561713457107544, | |
| "learning_rate": 0.00014, | |
| "loss": 3.1489, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03742690058479532, | |
| "grad_norm": 1.1961866617202759, | |
| "learning_rate": 0.00016, | |
| "loss": 3.2281, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.042105263157894736, | |
| "grad_norm": 1.0367659330368042, | |
| "learning_rate": 0.00018, | |
| "loss": 2.4508, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04678362573099415, | |
| "grad_norm": 1.1590759754180908, | |
| "learning_rate": 0.0002, | |
| "loss": 2.7763, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04678362573099415, | |
| "eval_loss": 0.639099657535553, | |
| "eval_runtime": 11.4984, | |
| "eval_samples_per_second": 7.827, | |
| "eval_steps_per_second": 3.914, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05146198830409357, | |
| "grad_norm": 1.2848360538482666, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 2.7303, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.056140350877192984, | |
| "grad_norm": 1.070992350578308, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 2.1943, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0608187134502924, | |
| "grad_norm": 1.0095195770263672, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.8425, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06549707602339182, | |
| "grad_norm": 1.2132809162139893, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 2.1708, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07017543859649122, | |
| "grad_norm": 1.2868399620056152, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.1133, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07017543859649122, | |
| "eval_loss": 0.47883766889572144, | |
| "eval_runtime": 11.4883, | |
| "eval_samples_per_second": 7.834, | |
| "eval_steps_per_second": 3.917, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07485380116959064, | |
| "grad_norm": 1.098825454711914, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.5518, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.07953216374269007, | |
| "grad_norm": 1.039568305015564, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 2.0939, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08421052631578947, | |
| "grad_norm": 1.1298397779464722, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.8204, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08888888888888889, | |
| "grad_norm": 1.1970208883285522, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.7516, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0935672514619883, | |
| "grad_norm": 1.1430251598358154, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.8547, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0935672514619883, | |
| "eval_loss": 0.4108954071998596, | |
| "eval_runtime": 11.4942, | |
| "eval_samples_per_second": 7.83, | |
| "eval_steps_per_second": 3.915, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09824561403508772, | |
| "grad_norm": 1.1456410884857178, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 1.5951, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.10292397660818714, | |
| "grad_norm": 0.8460454344749451, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 1.6078, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.10760233918128655, | |
| "grad_norm": 0.872773289680481, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 1.71, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.11228070175438597, | |
| "grad_norm": 0.9382916688919067, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 1.7091, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11695906432748537, | |
| "grad_norm": 0.804826557636261, | |
| "learning_rate": 0.0, | |
| "loss": 1.2807, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11695906432748537, | |
| "eval_loss": 0.4004054665565491, | |
| "eval_runtime": 11.4784, | |
| "eval_samples_per_second": 7.841, | |
| "eval_steps_per_second": 3.92, | |
| "step": 25 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3488222835376128.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |