| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.857689380645752, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.6957, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.8586467504501343, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 0.7235, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.4279438853263855, | |
| "learning_rate": 0.0002, | |
| "loss": 0.665, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.4085511863231659, | |
| "learning_rate": 0.00019977668786231534, | |
| "loss": 0.625, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.5382882356643677, | |
| "learning_rate": 0.000199107748815478, | |
| "loss": 0.6429, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.4320605993270874, | |
| "learning_rate": 0.0001979961705036587, | |
| "loss": 0.6354, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.3691844940185547, | |
| "learning_rate": 0.00019644691750543767, | |
| "loss": 0.6049, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.33010587096214294, | |
| "learning_rate": 0.0001944669091607919, | |
| "loss": 0.626, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.3566480576992035, | |
| "learning_rate": 0.00019206498866764288, | |
| "loss": 0.6424, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.3397829532623291, | |
| "learning_rate": 0.00018925188358598813, | |
| "loss": 0.6424, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.32853958010673523, | |
| "learning_rate": 0.00018604015792601396, | |
| "loss": 0.5838, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.32366353273391724, | |
| "learning_rate": 0.00018244415603417603, | |
| "loss": 0.6135, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.30376800894737244, | |
| "learning_rate": 0.0001784799385278661, | |
| "loss": 0.6362, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.28993257880210876, | |
| "learning_rate": 0.00017416521056479577, | |
| "loss": 0.5976, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.2954501807689667, | |
| "learning_rate": 0.00016951924276746425, | |
| "loss": 0.6179, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.2875906825065613, | |
| "learning_rate": 0.00016456278515588024, | |
| "loss": 0.6087, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.2935881018638611, | |
| "learning_rate": 0.00015931797447293552, | |
| "loss": 0.5936, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.2834060490131378, | |
| "learning_rate": 0.00015380823531633729, | |
| "loss": 0.601, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.2658578157424927, | |
| "learning_rate": 0.00014805817551866838, | |
| "loss": 0.5869, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.2771172523498535, | |
| "learning_rate": 0.0001420934762428335, | |
| "loss": 0.5686, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.27595141530036926, | |
| "learning_rate": 0.00013594077728375128, | |
| "loss": 0.6035, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.29558807611465454, | |
| "learning_rate": 0.00012962755808856342, | |
| "loss": 0.6189, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.29303988814353943, | |
| "learning_rate": 0.00012318201502675285, | |
| "loss": 0.6322, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.2829428017139435, | |
| "learning_rate": 0.00011663293545831302, | |
| "loss": 0.6079, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.28396308422088623, | |
| "learning_rate": 0.00011000956916240985, | |
| "loss": 0.5784, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.2766873836517334, | |
| "learning_rate": 0.00010334149770076747, | |
| "loss": 0.5971, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.270207017660141, | |
| "learning_rate": 9.665850229923258e-05, | |
| "loss": 0.6075, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.2784218192100525, | |
| "learning_rate": 8.999043083759017e-05, | |
| "loss": 0.5554, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.2829810678958893, | |
| "learning_rate": 8.336706454168701e-05, | |
| "loss": 0.5924, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.2684907913208008, | |
| "learning_rate": 7.681798497324716e-05, | |
| "loss": 0.5428, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.25939464569091797, | |
| "learning_rate": 7.037244191143661e-05, | |
| "loss": 0.5397, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.276192843914032, | |
| "learning_rate": 6.405922271624874e-05, | |
| "loss": 0.5992, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.2892877757549286, | |
| "learning_rate": 5.790652375716652e-05, | |
| "loss": 0.5993, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.25708481669425964, | |
| "learning_rate": 5.1941824481331626e-05, | |
| "loss": 0.5647, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.2700226306915283, | |
| "learning_rate": 4.6191764683662744e-05, | |
| "loss": 0.5424, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.2804276943206787, | |
| "learning_rate": 4.0682025527064486e-05, | |
| "loss": 0.5685, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.2692375183105469, | |
| "learning_rate": 3.543721484411976e-05, | |
| "loss": 0.5512, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.2597506046295166, | |
| "learning_rate": 3.0480757232535772e-05, | |
| "loss": 0.5535, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.2588387727737427, | |
| "learning_rate": 2.5834789435204243e-05, | |
| "loss": 0.5755, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.26815125346183777, | |
| "learning_rate": 2.1520061472133902e-05, | |
| "loss": 0.5859, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.2645345628261566, | |
| "learning_rate": 1.7555843965823992e-05, | |
| "loss": 0.5528, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.25494199991226196, | |
| "learning_rate": 1.3959842073986085e-05, | |
| "loss": 0.5274, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.26076003909111023, | |
| "learning_rate": 1.0748116414011888e-05, | |
| "loss": 0.5554, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.25466349720954895, | |
| "learning_rate": 7.935011332357112e-06, | |
| "loss": 0.5516, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.252687007188797, | |
| "learning_rate": 5.533090839208133e-06, | |
| "loss": 0.562, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.26723793148994446, | |
| "learning_rate": 3.5530824945623542e-06, | |
| "loss": 0.5599, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.27464812994003296, | |
| "learning_rate": 2.003829496341325e-06, | |
| "loss": 0.5998, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.26102861762046814, | |
| "learning_rate": 8.922511845219971e-07, | |
| "loss": 0.5513, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.25358739495277405, | |
| "learning_rate": 2.2331213768468363e-07, | |
| "loss": 0.5438, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.2604013681411743, | |
| "learning_rate": 0.0, | |
| "loss": 0.5642, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.058333143205478e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |