| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 125, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008, | |
| "grad_norm": 0.679400622844696, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 0.4779, | |
| "mean_token_accuracy": 0.8891920745372772, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.6668949127197266, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 0.4667, | |
| "mean_token_accuracy": 0.8981523290276527, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.3423958718776703, | |
| "learning_rate": 0.00015384615384615385, | |
| "loss": 0.3903, | |
| "mean_token_accuracy": 0.9041526615619659, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.28169184923171997, | |
| "learning_rate": 0.00019984268150178167, | |
| "loss": 0.2622, | |
| "mean_token_accuracy": 0.9287902176380157, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.22763028740882874, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 0.1656, | |
| "mean_token_accuracy": 0.9465068757534028, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.1743064969778061, | |
| "learning_rate": 0.00019438833303083678, | |
| "loss": 0.0896, | |
| "mean_token_accuracy": 0.9682954549789429, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.0910598486661911, | |
| "learning_rate": 0.00018884456359788724, | |
| "loss": 0.0624, | |
| "mean_token_accuracy": 0.9762519419193267, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.1415988653898239, | |
| "learning_rate": 0.00018155608689592604, | |
| "loss": 0.0676, | |
| "mean_token_accuracy": 0.9724054753780365, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.15753652155399323, | |
| "learning_rate": 0.0001726660322034027, | |
| "loss": 0.0631, | |
| "mean_token_accuracy": 0.9734513998031616, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.14174672961235046, | |
| "learning_rate": 0.00016234898018587337, | |
| "loss": 0.0558, | |
| "mean_token_accuracy": 0.976895785331726, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.1046091765165329, | |
| "learning_rate": 0.00015080753452465296, | |
| "loss": 0.0582, | |
| "mean_token_accuracy": 0.9748494327068329, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.09198472648859024, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.0552, | |
| "mean_token_accuracy": 0.9761805891990661, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.07517699152231216, | |
| "learning_rate": 0.0001249776478167227, | |
| "loss": 0.0542, | |
| "mean_token_accuracy": 0.9768649995326996, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.09316771477460861, | |
| "learning_rate": 0.00011119644761033078, | |
| "loss": 0.0511, | |
| "mean_token_accuracy": 0.9787204623222351, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.09173958748579025, | |
| "learning_rate": 9.719537437241312e-05, | |
| "loss": 0.05, | |
| "mean_token_accuracy": 0.9781815230846405, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.10948050022125244, | |
| "learning_rate": 8.324937766952638e-05, | |
| "loss": 0.05, | |
| "mean_token_accuracy": 0.9780394077301026, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.06583424657583237, | |
| "learning_rate": 6.963232548903853e-05, | |
| "loss": 0.0512, | |
| "mean_token_accuracy": 0.9775851011276245, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.081637904047966, | |
| "learning_rate": 5.6611626088244194e-05, | |
| "loss": 0.0537, | |
| "mean_token_accuracy": 0.9765498995780945, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.12278567999601364, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.0486, | |
| "mean_token_accuracy": 0.9790335714817047, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.06769045442342758, | |
| "learning_rate": 3.336534220479961e-05, | |
| "loss": 0.0515, | |
| "mean_token_accuracy": 0.9783276081085205, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.08743651956319809, | |
| "learning_rate": 2.3596262417839255e-05, | |
| "loss": 0.0475, | |
| "mean_token_accuracy": 0.9792425632476807, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.07326360791921616, | |
| "learning_rate": 1.5327580077171587e-05, | |
| "loss": 0.0489, | |
| "mean_token_accuracy": 0.9790730774402618, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.0983777642250061, | |
| "learning_rate": 8.72167349386811e-06, | |
| "loss": 0.0511, | |
| "mean_token_accuracy": 0.9783868014812469, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.08176760375499725, | |
| "learning_rate": 3.908267805490051e-06, | |
| "loss": 0.0496, | |
| "mean_token_accuracy": 0.9781703352928162, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.08720585703849792, | |
| "learning_rate": 9.818874663554357e-07, | |
| "loss": 0.0455, | |
| "mean_token_accuracy": 0.9797735631465911, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.07412629574537277, | |
| "learning_rate": 0.0, | |
| "loss": 0.0492, | |
| "mean_token_accuracy": 0.9789807200431824, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.04896746948361397, | |
| "eval_mean_token_accuracy": 0.9787813196182251, | |
| "eval_runtime": 82.9625, | |
| "eval_samples_per_second": 12.054, | |
| "eval_steps_per_second": 1.507, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 125, | |
| "total_flos": 4403744057851904.0, | |
| "train_loss": 0.09763943994045257, | |
| "train_runtime": 360.1115, | |
| "train_samples_per_second": 2.777, | |
| "train_steps_per_second": 0.347 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 125, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4403744057851904.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |