| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.976, | |
| "eval_steps": 500, | |
| "global_step": 186, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.374408483505249, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 1.1454, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.311002641916275, | |
| "learning_rate": 4.999557652060729e-05, | |
| "loss": 1.0246, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.30777308344841003, | |
| "learning_rate": 4.946665048328287e-05, | |
| "loss": 0.9632, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.4400554895401001, | |
| "learning_rate": 4.807442755497524e-05, | |
| "loss": 0.978, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.4841279983520508, | |
| "learning_rate": 4.586803181690609e-05, | |
| "loss": 0.968, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.34245041012763977, | |
| "learning_rate": 4.292531514268008e-05, | |
| "loss": 0.9348, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.4096768796443939, | |
| "learning_rate": 3.9350110223152844e-05, | |
| "loss": 0.7968, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.6328812837600708, | |
| "learning_rate": 3.526856686758269e-05, | |
| "loss": 0.7295, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.47058913111686707, | |
| "learning_rate": 3.082470085335133e-05, | |
| "loss": 0.6724, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.46030929684638977, | |
| "learning_rate": 2.6175312381477442e-05, | |
| "loss": 0.6994, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 0.5056099891662598, | |
| "learning_rate": 2.148445343837755e-05, | |
| "loss": 0.7171, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.39329010248184204, | |
| "learning_rate": 1.69176392810087e-05, | |
| "loss": 0.7364, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": 0.5568200349807739, | |
| "learning_rate": 1.2636008291040618e-05, | |
| "loss": 0.7352, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "grad_norm": 0.714911937713623, | |
| "learning_rate": 8.790636265485334e-06, | |
| "loss": 0.4738, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 0.5729328989982605, | |
| "learning_rate": 5.51720576197794e-06, | |
| "loss": 0.5162, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 0.6667868494987488, | |
| "learning_rate": 2.931218588927315e-06, | |
| "loss": 0.4586, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.7199999999999998, | |
| "grad_norm": 0.49541157484054565, | |
| "learning_rate": 1.1239203660860648e-06, | |
| "loss": 0.5178, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "grad_norm": 0.5764051079750061, | |
| "learning_rate": 1.5908095594207583e-07, | |
| "loss": 0.4586, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.976, | |
| "step": 186, | |
| "total_flos": 1.5945119821725696e+16, | |
| "train_loss": 0.7450424432754517, | |
| "train_runtime": 1935.7993, | |
| "train_samples_per_second": 0.775, | |
| "train_steps_per_second": 0.096 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 186, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5945119821725696e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |