| { | |
| "best_metric": 1.2940274477005005, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.011363636363636364, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00045454545454545455, | |
| "grad_norm": 0.31628403067588806, | |
| "learning_rate": 1e-05, | |
| "loss": 1.362, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00045454545454545455, | |
| "eval_loss": 1.3756574392318726, | |
| "eval_runtime": 83.7745, | |
| "eval_samples_per_second": 11.065, | |
| "eval_steps_per_second": 5.539, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009090909090909091, | |
| "grad_norm": 0.2886245548725128, | |
| "learning_rate": 2e-05, | |
| "loss": 1.4369, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0013636363636363637, | |
| "grad_norm": 0.21225334703922272, | |
| "learning_rate": 3e-05, | |
| "loss": 0.8945, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0018181818181818182, | |
| "grad_norm": 0.30762138962745667, | |
| "learning_rate": 4e-05, | |
| "loss": 1.5411, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0022727272727272726, | |
| "grad_norm": 0.2719841003417969, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2252, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0022727272727272726, | |
| "eval_loss": 1.3746238946914673, | |
| "eval_runtime": 82.7616, | |
| "eval_samples_per_second": 11.201, | |
| "eval_steps_per_second": 5.606, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0027272727272727275, | |
| "grad_norm": 0.30843380093574524, | |
| "learning_rate": 6e-05, | |
| "loss": 1.4724, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003181818181818182, | |
| "grad_norm": 0.2783626914024353, | |
| "learning_rate": 7e-05, | |
| "loss": 1.1183, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0036363636363636364, | |
| "grad_norm": 0.28724151849746704, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5419, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004090909090909091, | |
| "grad_norm": 0.2586436867713928, | |
| "learning_rate": 9e-05, | |
| "loss": 1.3643, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004545454545454545, | |
| "grad_norm": 0.2510312497615814, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2918, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004545454545454545, | |
| "eval_loss": 1.3567347526550293, | |
| "eval_runtime": 79.2338, | |
| "eval_samples_per_second": 11.7, | |
| "eval_steps_per_second": 5.856, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005, | |
| "grad_norm": 0.29608702659606934, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.3418, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005454545454545455, | |
| "grad_norm": 0.27602267265319824, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.069, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005909090909090909, | |
| "grad_norm": 0.30428454279899597, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.4957, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006363636363636364, | |
| "grad_norm": 0.32315993309020996, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.0698, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006818181818181818, | |
| "grad_norm": 0.2515247166156769, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.2932, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006818181818181818, | |
| "eval_loss": 1.3137667179107666, | |
| "eval_runtime": 85.1577, | |
| "eval_samples_per_second": 10.886, | |
| "eval_steps_per_second": 5.449, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007272727272727273, | |
| "grad_norm": 0.28928083181381226, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.1773, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.007727272727272728, | |
| "grad_norm": 0.4229072034358978, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 1.5595, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.008181818181818182, | |
| "grad_norm": 0.24980007112026215, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 1.0698, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008636363636363636, | |
| "grad_norm": 0.38862258195877075, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.3397, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00909090909090909, | |
| "grad_norm": 0.2815423011779785, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.004, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00909090909090909, | |
| "eval_loss": 1.2963515520095825, | |
| "eval_runtime": 76.7123, | |
| "eval_samples_per_second": 12.084, | |
| "eval_steps_per_second": 6.049, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009545454545454546, | |
| "grad_norm": 0.27244335412979126, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 1.2956, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.329553484916687, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.0757, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.010454545454545454, | |
| "grad_norm": 0.3100622296333313, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 1.1361, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01090909090909091, | |
| "grad_norm": 0.2915355861186981, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 1.0331, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.011363636363636364, | |
| "grad_norm": 0.293474018573761, | |
| "learning_rate": 0.0, | |
| "loss": 1.4389, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.011363636363636364, | |
| "eval_loss": 1.2940274477005005, | |
| "eval_runtime": 82.6057, | |
| "eval_samples_per_second": 11.222, | |
| "eval_steps_per_second": 5.617, | |
| "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": 1313407946981376.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |