| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.08040201005025126, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004020100502512563, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004020100502512563, | |
| "eval_loss": NaN, | |
| "eval_runtime": 32.7011, | |
| "eval_samples_per_second": 3.211, | |
| "eval_steps_per_second": 1.621, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008040201005025126, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.2161, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.012060301507537688, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.016080402010050253, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.020100502512562814, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1143, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.020100502512562814, | |
| "eval_loss": NaN, | |
| "eval_runtime": 32.2553, | |
| "eval_samples_per_second": 3.255, | |
| "eval_steps_per_second": 1.643, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.024120603015075376, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 1.7707, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02814070351758794, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.5047, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.032160804020100506, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.9608, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.036180904522613064, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 1.1242, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04020100502512563, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04020100502512563, | |
| "eval_loss": NaN, | |
| "eval_runtime": 32.469, | |
| "eval_samples_per_second": 3.234, | |
| "eval_steps_per_second": 1.632, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.044221105527638194, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 1.1982, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04824120603015075, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 0.2992, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05226130653266332, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.9155, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.05628140703517588, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 1.4225, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06030150753768844, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.1828, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06030150753768844, | |
| "eval_loss": NaN, | |
| "eval_runtime": 32.793, | |
| "eval_samples_per_second": 3.202, | |
| "eval_steps_per_second": 1.616, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06432160804020101, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.5887, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06834170854271357, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.6496, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07236180904522613, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0763819095477387, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.22, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.08040201005025126, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08040201005025126, | |
| "eval_loss": NaN, | |
| "eval_runtime": 32.4206, | |
| "eval_samples_per_second": 3.239, | |
| "eval_steps_per_second": 1.635, | |
| "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": 2 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.378799358836736e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |