| { | |
| "best_metric": 1.217628002166748, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", | |
| "epoch": 0.004551001078018381, | |
| "eval_steps": 100, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.27550053900919e-05, | |
| "eval_loss": 1.937334656715393, | |
| "eval_runtime": 3346.8176, | |
| "eval_samples_per_second": 5.529, | |
| "eval_steps_per_second": 5.529, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00022755005390091902, | |
| "grad_norm": 1.970492959022522, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.8738, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00045510010780183804, | |
| "grad_norm": 1.727200984954834, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.2257, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.000682650161702757, | |
| "grad_norm": 2.1002678871154785, | |
| "learning_rate": 3e-06, | |
| "loss": 1.4908, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0009102002156036761, | |
| "grad_norm": 2.082857370376587, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.0918, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0011377502695045952, | |
| "grad_norm": 24.92116928100586, | |
| "learning_rate": 5e-06, | |
| "loss": 2.7639, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.001365300323405514, | |
| "grad_norm": 0.9576764106750488, | |
| "learning_rate": 6e-06, | |
| "loss": 0.8391, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.001592850377306433, | |
| "grad_norm": 1.03590726852417, | |
| "learning_rate": 7e-06, | |
| "loss": 1.0317, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0018204004312073522, | |
| "grad_norm": 1.580169916152954, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.1755, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.002047950485108271, | |
| "grad_norm": 2.075538396835327, | |
| "learning_rate": 9e-06, | |
| "loss": 0.9404, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0022755005390091903, | |
| "grad_norm": 15.543938636779785, | |
| "learning_rate": 1e-05, | |
| "loss": 2.6955, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0022755005390091903, | |
| "eval_loss": 1.4104949235916138, | |
| "eval_runtime": 3340.471, | |
| "eval_samples_per_second": 5.539, | |
| "eval_steps_per_second": 5.539, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.002503050592910109, | |
| "grad_norm": 1.1351838111877441, | |
| "learning_rate": 9.755282581475769e-06, | |
| "loss": 0.6866, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.002730600646811028, | |
| "grad_norm": 1.3157535791397095, | |
| "learning_rate": 9.045084971874738e-06, | |
| "loss": 0.8786, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.0029581507007119473, | |
| "grad_norm": 1.2388049364089966, | |
| "learning_rate": 7.938926261462366e-06, | |
| "loss": 1.1656, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.003185700754612866, | |
| "grad_norm": 1.667664885520935, | |
| "learning_rate": 6.545084971874738e-06, | |
| "loss": 0.6019, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.003413250808513785, | |
| "grad_norm": 14.491639137268066, | |
| "learning_rate": 5e-06, | |
| "loss": 2.5697, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0036408008624147043, | |
| "grad_norm": 1.081459879875183, | |
| "learning_rate": 3.4549150281252635e-06, | |
| "loss": 0.6925, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.003868350916315623, | |
| "grad_norm": 2.302001953125, | |
| "learning_rate": 2.061073738537635e-06, | |
| "loss": 0.7282, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.004095900970216542, | |
| "grad_norm": 1.375418782234192, | |
| "learning_rate": 9.549150281252633e-07, | |
| "loss": 0.8401, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.004323451024117461, | |
| "grad_norm": 1.4581494331359863, | |
| "learning_rate": 2.447174185242324e-07, | |
| "loss": 0.4591, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.004551001078018381, | |
| "grad_norm": 9.276606559753418, | |
| "learning_rate": 0.0, | |
| "loss": 2.4783, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.004551001078018381, | |
| "eval_loss": 1.217628002166748, | |
| "eval_runtime": 3338.5785, | |
| "eval_samples_per_second": 5.542, | |
| "eval_steps_per_second": 5.542, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 1.363637353536553e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |