| { | |
| "best_metric": 1.9018210172653198, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.0057185337679419, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00022874135071767598, | |
| "grad_norm": 3.1676807403564453, | |
| "learning_rate": 2e-05, | |
| "loss": 15.7884, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00022874135071767598, | |
| "eval_loss": 4.049134254455566, | |
| "eval_runtime": 317.0162, | |
| "eval_samples_per_second": 5.807, | |
| "eval_steps_per_second": 2.905, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00045748270143535196, | |
| "grad_norm": 3.3963818550109863, | |
| "learning_rate": 4e-05, | |
| "loss": 15.5728, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006862240521530279, | |
| "grad_norm": 3.2129127979278564, | |
| "learning_rate": 6e-05, | |
| "loss": 14.4822, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009149654028707039, | |
| "grad_norm": 3.7225141525268555, | |
| "learning_rate": 8e-05, | |
| "loss": 17.6575, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00114370675358838, | |
| "grad_norm": 3.091374397277832, | |
| "learning_rate": 0.0001, | |
| "loss": 15.4111, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00114370675358838, | |
| "eval_loss": 4.0190510749816895, | |
| "eval_runtime": 316.0493, | |
| "eval_samples_per_second": 5.825, | |
| "eval_steps_per_second": 2.914, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0013724481043060558, | |
| "grad_norm": 3.7836978435516357, | |
| "learning_rate": 0.00012, | |
| "loss": 15.3633, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0016011894550237318, | |
| "grad_norm": 4.331509590148926, | |
| "learning_rate": 0.00014, | |
| "loss": 14.4719, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0018299308057414079, | |
| "grad_norm": 6.673212051391602, | |
| "learning_rate": 0.00016, | |
| "loss": 19.2312, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002058672156459084, | |
| "grad_norm": 6.4779863357543945, | |
| "learning_rate": 0.00018, | |
| "loss": 16.3462, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00228741350717676, | |
| "grad_norm": 6.56136417388916, | |
| "learning_rate": 0.0002, | |
| "loss": 12.3944, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00228741350717676, | |
| "eval_loss": 3.267272472381592, | |
| "eval_runtime": 316.0973, | |
| "eval_samples_per_second": 5.824, | |
| "eval_steps_per_second": 2.914, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0025161548578944357, | |
| "grad_norm": 7.548186779022217, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 14.214, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0027448962086121117, | |
| "grad_norm": 10.005125999450684, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 14.8289, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0029736375593297877, | |
| "grad_norm": 7.77647590637207, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 10.9902, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0032023789100474637, | |
| "grad_norm": 9.317489624023438, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 11.2201, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0034311202607651397, | |
| "grad_norm": 8.553632736206055, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 9.4567, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0034311202607651397, | |
| "eval_loss": 2.2402334213256836, | |
| "eval_runtime": 317.5791, | |
| "eval_samples_per_second": 5.797, | |
| "eval_steps_per_second": 2.9, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0036598616114828157, | |
| "grad_norm": 7.3252387046813965, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 6.2007, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0038886029622004917, | |
| "grad_norm": 9.066070556640625, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 7.0014, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004117344312918168, | |
| "grad_norm": 13.760567665100098, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 9.2674, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004346085663635844, | |
| "grad_norm": 9.562538146972656, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 8.6528, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00457482701435352, | |
| "grad_norm": 12.553031921386719, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 9.9563, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00457482701435352, | |
| "eval_loss": 1.9547957181930542, | |
| "eval_runtime": 317.0485, | |
| "eval_samples_per_second": 5.807, | |
| "eval_steps_per_second": 2.905, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004803568365071196, | |
| "grad_norm": 10.91247844696045, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 6.3325, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005032309715788871, | |
| "grad_norm": 10.488737106323242, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 8.6445, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.005261051066506548, | |
| "grad_norm": 9.67850399017334, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 6.8417, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.005489792417224223, | |
| "grad_norm": 9.22018814086914, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 5.6596, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0057185337679419, | |
| "grad_norm": 10.53501033782959, | |
| "learning_rate": 0.0, | |
| "loss": 7.4384, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0057185337679419, | |
| "eval_loss": 1.9018210172653198, | |
| "eval_runtime": 317.3453, | |
| "eval_samples_per_second": 5.801, | |
| "eval_steps_per_second": 2.902, | |
| "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": 8493418414080000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |