| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005599991040014336, | |
| "eval_steps": 200000, | |
| "global_step": 3500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001599997440004096, | |
| "grad_norm": 84.32501983642578, | |
| "learning_rate": 3.103950336794611e-08, | |
| "loss": 10.8792, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0003199994880008192, | |
| "grad_norm": 60.63747024536133, | |
| "learning_rate": 6.303899137613798e-08, | |
| "loss": 10.9284, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.00047999923200122877, | |
| "grad_norm": 55.71075439453125, | |
| "learning_rate": 9.503847938432986e-08, | |
| "loss": 10.6466, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.0006399989760016384, | |
| "grad_norm": 57.63307189941406, | |
| "learning_rate": 1.2703796739252173e-07, | |
| "loss": 10.841, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.000799998720002048, | |
| "grad_norm": 89.1032485961914, | |
| "learning_rate": 1.590374554007136e-07, | |
| "loss": 10.8094, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.0009599984640024575, | |
| "grad_norm": 57.2479362487793, | |
| "learning_rate": 1.9103694340890547e-07, | |
| "loss": 10.4323, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.0011199982080028672, | |
| "grad_norm": 51.17530059814453, | |
| "learning_rate": 2.2303643141709733e-07, | |
| "loss": 10.3032, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.0012799979520032767, | |
| "grad_norm": 60.76409912109375, | |
| "learning_rate": 2.550359194252892e-07, | |
| "loss": 10.4006, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.0014399976960036865, | |
| "grad_norm": 67.00859069824219, | |
| "learning_rate": 2.870354074334811e-07, | |
| "loss": 10.4743, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.001599997440004096, | |
| "grad_norm": 68.4343032836914, | |
| "learning_rate": 3.19034895441673e-07, | |
| "loss": 10.2334, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.0017599971840045055, | |
| "grad_norm": 48.704105377197266, | |
| "learning_rate": 3.510343834498648e-07, | |
| "loss": 10.0135, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.001919996928004915, | |
| "grad_norm": 45.30134963989258, | |
| "learning_rate": 3.830338714580567e-07, | |
| "loss": 9.7874, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.002079996672005325, | |
| "grad_norm": 84.56024169921875, | |
| "learning_rate": 4.150333594662486e-07, | |
| "loss": 9.7419, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.0022399964160057344, | |
| "grad_norm": 45.73213195800781, | |
| "learning_rate": 4.470328474744404e-07, | |
| "loss": 9.7412, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.002399996160006144, | |
| "grad_norm": 50.21996307373047, | |
| "learning_rate": 4.790323354826324e-07, | |
| "loss": 9.4585, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.0025599959040065534, | |
| "grad_norm": 59.475799560546875, | |
| "learning_rate": 5.110318234908241e-07, | |
| "loss": 9.5339, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.002719995648006963, | |
| "grad_norm": 82.53620910644531, | |
| "learning_rate": 5.43031311499016e-07, | |
| "loss": 9.4345, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.002879995392007373, | |
| "grad_norm": 39.44235610961914, | |
| "learning_rate": 5.750307995072079e-07, | |
| "loss": 9.1733, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.0030399951360077825, | |
| "grad_norm": 37.58698654174805, | |
| "learning_rate": 6.070302875153998e-07, | |
| "loss": 8.9952, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.003199994880008192, | |
| "grad_norm": 40.35204315185547, | |
| "learning_rate": 6.390297755235917e-07, | |
| "loss": 8.9669, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.0033599946240086016, | |
| "grad_norm": 57.84451675415039, | |
| "learning_rate": 6.707092686517017e-07, | |
| "loss": 8.8152, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.003519994368009011, | |
| "grad_norm": 40.126953125, | |
| "learning_rate": 7.027087566598935e-07, | |
| "loss": 8.7936, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.0036799941120094206, | |
| "grad_norm": 35.435707092285156, | |
| "learning_rate": 7.347082446680854e-07, | |
| "loss": 8.6771, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.00383999385600983, | |
| "grad_norm": 42.3509635925293, | |
| "learning_rate": 7.667077326762773e-07, | |
| "loss": 8.4648, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.00399999360001024, | |
| "grad_norm": 33.58556365966797, | |
| "learning_rate": 7.987072206844691e-07, | |
| "loss": 8.5764, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.00415999334401065, | |
| "grad_norm": 34.014678955078125, | |
| "learning_rate": 8.30706708692661e-07, | |
| "loss": 8.4587, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.004319993088011059, | |
| "grad_norm": 36.43831253051758, | |
| "learning_rate": 8.627061967008528e-07, | |
| "loss": 8.2966, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.004479992832011469, | |
| "grad_norm": 31.411684036254883, | |
| "learning_rate": 8.947056847090448e-07, | |
| "loss": 8.2329, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.004639992576011879, | |
| "grad_norm": 47.570125579833984, | |
| "learning_rate": 9.267051727172366e-07, | |
| "loss": 8.1415, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.004799992320012288, | |
| "grad_norm": 30.771928787231445, | |
| "learning_rate": 9.587046607254284e-07, | |
| "loss": 8.0404, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.004959992064012698, | |
| "grad_norm": 26.92803955078125, | |
| "learning_rate": 9.907041487336204e-07, | |
| "loss": 7.9698, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.005119991808013107, | |
| "grad_norm": 31.121917724609375, | |
| "learning_rate": 1.0227036367418122e-06, | |
| "loss": 7.9205, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.005279991552013517, | |
| "grad_norm": 33.991416931152344, | |
| "learning_rate": 1.054703124750004e-06, | |
| "loss": 7.8314, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.005439991296013926, | |
| "grad_norm": 31.278030395507812, | |
| "learning_rate": 1.086702612758196e-06, | |
| "loss": 7.8369, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.005599991040014336, | |
| "grad_norm": 28.116140365600586, | |
| "learning_rate": 1.1187021007663878e-06, | |
| "loss": 7.6403, | |
| "step": 3500 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 625001, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |