| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.7151370679380215, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009535160905840286, | |
| "grad_norm": 22.616830825805664, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 10.7012, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009535160905840286, | |
| "eval_loss": 9.564970016479492, | |
| "eval_runtime": 54.4321, | |
| "eval_samples_per_second": 1.635, | |
| "eval_steps_per_second": 0.827, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01907032181168057, | |
| "grad_norm": 20.275375366210938, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 9.9498, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.028605482717520857, | |
| "grad_norm": 23.843503952026367, | |
| "learning_rate": 0.0001, | |
| "loss": 9.8482, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03814064362336114, | |
| "grad_norm": 17.373727798461914, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 6.8627, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04767580452920143, | |
| "grad_norm": 16.935632705688477, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 5.3765, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.057210965435041714, | |
| "grad_norm": 25.84366226196289, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 6.6007, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.066746126340882, | |
| "grad_norm": 39.4841423034668, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 6.0231, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07628128724672228, | |
| "grad_norm": 24.768882751464844, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 2.7102, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08581644815256258, | |
| "grad_norm": 29.693031311035156, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.6618, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09535160905840286, | |
| "grad_norm": 14.000877380371094, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 0.9057, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10488676996424315, | |
| "grad_norm": 5.596749305725098, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.3843, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.11442193087008343, | |
| "grad_norm": 4.840229511260986, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.4124, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.12395709177592372, | |
| "grad_norm": 3.7698850631713867, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 0.3085, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.133492252681764, | |
| "grad_norm": 1.7670843601226807, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 0.2888, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1430274135876043, | |
| "grad_norm": 0.5820183753967285, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.2256, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.15256257449344457, | |
| "grad_norm": 3.2924885749816895, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 0.4244, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.16209773539928488, | |
| "grad_norm": 1.984984278678894, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 0.3216, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.17163289630512515, | |
| "grad_norm": 1.1172698736190796, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.3188, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.18116805721096543, | |
| "grad_norm": 1.5274360179901123, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.3054, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1907032181168057, | |
| "grad_norm": 1.9571841955184937, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 0.3021, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.20023837902264602, | |
| "grad_norm": 1.2252756357192993, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.2382, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2097735399284863, | |
| "grad_norm": 1.0066477060317993, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 0.3221, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.21930870083432658, | |
| "grad_norm": 0.6950803995132446, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.2824, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.22884386174016685, | |
| "grad_norm": 1.1107197999954224, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.361, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.23837902264600716, | |
| "grad_norm": 0.676360547542572, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 0.2431, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.23837902264600716, | |
| "eval_loss": 0.266483336687088, | |
| "eval_runtime": 54.8592, | |
| "eval_samples_per_second": 1.622, | |
| "eval_steps_per_second": 0.82, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24791418355184744, | |
| "grad_norm": 0.4809877872467041, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 0.2921, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.25744934445768775, | |
| "grad_norm": 1.3561242818832397, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.1493, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.266984505363528, | |
| "grad_norm": 1.378612756729126, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 0.1205, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2765196662693683, | |
| "grad_norm": 1.3110326528549194, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 0.09, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2860548271752086, | |
| "grad_norm": 0.8067518472671509, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.035, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.29558998808104886, | |
| "grad_norm": 30.427331924438477, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 1.3727, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.30512514898688914, | |
| "grad_norm": 30.505556106567383, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 2.8594, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3146603098927294, | |
| "grad_norm": 26.016315460205078, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.531, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.32419547079856975, | |
| "grad_norm": 14.183924674987793, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 1.1554, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.33373063170441003, | |
| "grad_norm": 1.8867197036743164, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.2323, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3432657926102503, | |
| "grad_norm": 1.2031322717666626, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.2414, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3528009535160906, | |
| "grad_norm": 1.523146390914917, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 0.2678, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.36233611442193087, | |
| "grad_norm": 1.5239652395248413, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 0.2312, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.37187127532777114, | |
| "grad_norm": 1.0078612565994263, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1885, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3814064362336114, | |
| "grad_norm": 4.037468433380127, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 0.4962, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3909415971394517, | |
| "grad_norm": 2.556730031967163, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 0.4065, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.40047675804529204, | |
| "grad_norm": 1.4753957986831665, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.3817, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.4100119189511323, | |
| "grad_norm": 1.1868329048156738, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.2182, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.4195470798569726, | |
| "grad_norm": 0.9121273159980774, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 0.2606, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.42908224076281287, | |
| "grad_norm": 0.551138162612915, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.2798, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.43861740166865315, | |
| "grad_norm": 0.5170517563819885, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 0.2307, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.44815256257449343, | |
| "grad_norm": 0.3968268036842346, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 0.2303, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.4576877234803337, | |
| "grad_norm": 0.3745101988315582, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.2629, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.46722288438617404, | |
| "grad_norm": 0.7609822750091553, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 0.2946, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4767580452920143, | |
| "grad_norm": 0.4893784523010254, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 0.2266, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4767580452920143, | |
| "eval_loss": 0.2717249393463135, | |
| "eval_runtime": 54.8636, | |
| "eval_samples_per_second": 1.622, | |
| "eval_steps_per_second": 0.82, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4862932061978546, | |
| "grad_norm": 0.6945714354515076, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.2567, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.4958283671036949, | |
| "grad_norm": 0.6655871272087097, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 0.1773, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.5053635280095352, | |
| "grad_norm": 2.4930078983306885, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 0.1157, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.5148986889153755, | |
| "grad_norm": 1.8733148574829102, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0834, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.5244338498212158, | |
| "grad_norm": 1.6207678318023682, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 0.072, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.533969010727056, | |
| "grad_norm": 2.021498441696167, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 0.2196, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.5435041716328963, | |
| "grad_norm": 8.16150188446045, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.9258, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.5530393325387366, | |
| "grad_norm": 15.361802101135254, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 1.1991, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.5625744934445769, | |
| "grad_norm": 15.315176010131836, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.2264, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.5721096543504172, | |
| "grad_norm": 14.774981498718262, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.2034, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5816448152562574, | |
| "grad_norm": 4.136609077453613, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 0.4474, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.5911799761620977, | |
| "grad_norm": 0.9078148007392883, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 0.2365, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.600715137067938, | |
| "grad_norm": 1.588295340538025, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.3393, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.6102502979737783, | |
| "grad_norm": 0.6780855059623718, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 0.2498, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.6197854588796186, | |
| "grad_norm": 0.553501307964325, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 0.2031, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.6293206197854588, | |
| "grad_norm": 0.3157319724559784, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2239, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.6388557806912991, | |
| "grad_norm": 0.7763720750808716, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.3028, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.6483909415971395, | |
| "grad_norm": 0.7925229072570801, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 0.2561, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.6579261025029798, | |
| "grad_norm": 0.41560518741607666, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.1974, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.6674612634088201, | |
| "grad_norm": 1.2434768676757812, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 0.3121, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6769964243146603, | |
| "grad_norm": 0.5525261759757996, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 0.201, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.6865315852205006, | |
| "grad_norm": 1.1765050888061523, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.3335, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.6960667461263409, | |
| "grad_norm": 0.3499181568622589, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 0.2423, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.7056019070321812, | |
| "grad_norm": 0.6464172601699829, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 0.1805, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.7151370679380215, | |
| "grad_norm": 0.9107186198234558, | |
| "learning_rate": 0.0, | |
| "loss": 0.3255, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.7151370679380215, | |
| "eval_loss": 0.2709729075431824, | |
| "eval_runtime": 54.2298, | |
| "eval_samples_per_second": 1.641, | |
| "eval_steps_per_second": 0.83, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.647483930279936e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |