| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 22, |
| "global_step": 66, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.045454545454545456, |
| "grad_norm": 13.541594505310059, |
| "learning_rate": 1e-05, |
| "loss": 1.687255859375, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.09090909090909091, |
| "grad_norm": 270.9620056152344, |
| "learning_rate": 9.994336695915041e-06, |
| "loss": 4.320972442626953, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.13636363636363635, |
| "grad_norm": 8.045546531677246, |
| "learning_rate": 9.977359612865424e-06, |
| "loss": 0.990966796875, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.18181818181818182, |
| "grad_norm": 4.051703453063965, |
| "learning_rate": 9.949107209404664e-06, |
| "loss": 1.09613037109375, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.22727272727272727, |
| "grad_norm": 2.503697633743286, |
| "learning_rate": 9.909643486313533e-06, |
| "loss": 1.016815185546875, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.2727272727272727, |
| "grad_norm": 3.1819581985473633, |
| "learning_rate": 9.859057841617709e-06, |
| "loss": 0.91766357421875, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.3181818181818182, |
| "grad_norm": 1.810927391052246, |
| "learning_rate": 9.797464868072489e-06, |
| "loss": 0.9587249755859375, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.36363636363636365, |
| "grad_norm": 1.6619356870651245, |
| "learning_rate": 9.725004093573343e-06, |
| "loss": 0.80902099609375, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.4090909090909091, |
| "grad_norm": 2.2837491035461426, |
| "learning_rate": 9.641839665080363e-06, |
| "loss": 0.8079757690429688, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.45454545454545453, |
| "grad_norm": 3.019440174102783, |
| "learning_rate": 9.548159976772593e-06, |
| "loss": 0.8288116455078125, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 1.1921716928482056, |
| "learning_rate": 9.444177243274619e-06, |
| "loss": 0.6759376525878906, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.5454545454545454, |
| "grad_norm": 2.224130153656006, |
| "learning_rate": 9.330127018922195e-06, |
| "loss": 0.54034423828125, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5909090909090909, |
| "grad_norm": 1.386547327041626, |
| "learning_rate": 9.206267664155906e-06, |
| "loss": 0.49675750732421875, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.6363636363636364, |
| "grad_norm": 1.4452524185180664, |
| "learning_rate": 9.07287976025168e-06, |
| "loss": 0.4326019287109375, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.6818181818181818, |
| "grad_norm": 2.8639578819274902, |
| "learning_rate": 8.930265473713939e-06, |
| "loss": 0.587005615234375, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.7272727272727273, |
| "grad_norm": 1.1509618759155273, |
| "learning_rate": 8.778747871771293e-06, |
| "loss": 0.49512481689453125, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.7727272727272727, |
| "grad_norm": 1.06486177444458, |
| "learning_rate": 8.61867019052535e-06, |
| "loss": 0.6640739440917969, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.8181818181818182, |
| "grad_norm": 0.9991989731788635, |
| "learning_rate": 8.450395057410561e-06, |
| "loss": 0.437957763671875, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.8636363636363636, |
| "grad_norm": 0.7819029092788696, |
| "learning_rate": 8.274303669726427e-06, |
| "loss": 0.5671710968017578, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.9090909090909091, |
| "grad_norm": 0.8972281813621521, |
| "learning_rate": 8.090794931103026e-06, |
| "loss": 0.3094291687011719, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.9545454545454546, |
| "grad_norm": 0.8230551481246948, |
| "learning_rate": 7.900284547855992e-06, |
| "loss": 0.42014312744140625, |
| "step": 21 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.9112458229064941, |
| "learning_rate": 7.703204087277989e-06, |
| "loss": 0.3252525329589844, |
| "step": 22 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.59442138671875, |
| "eval_runtime": 13.685, |
| "eval_samples_per_second": 0.365, |
| "eval_steps_per_second": 0.073, |
| "step": 22 |
| }, |
| { |
| "checkpoint_runtime": 130.4115 |
| }, |
| { |
| "epoch": 1.0454545454545454, |
| "grad_norm": 1.6123707294464111, |
| "learning_rate": 7.500000000000001e-06, |
| "loss": 0.5166397094726562, |
| "step": 23 |
| }, |
| { |
| "epoch": 1.0909090909090908, |
| "grad_norm": 1.3553637266159058, |
| "learning_rate": 7.291132608637053e-06, |
| "loss": 0.3297233581542969, |
| "step": 24 |
| }, |
| { |
| "epoch": 1.1363636363636362, |
| "grad_norm": 1.3093994855880737, |
| "learning_rate": 7.0770750650094335e-06, |
| "loss": 0.49069786071777344, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.1818181818181819, |
| "grad_norm": 0.996208667755127, |
| "learning_rate": 6.858312278301638e-06, |
| "loss": 0.2602996826171875, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.2272727272727273, |
| "grad_norm": 0.8691992163658142, |
| "learning_rate": 6.635339816587109e-06, |
| "loss": 0.09621810913085938, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.2727272727272727, |
| "grad_norm": 0.73832106590271, |
| "learning_rate": 6.408662784207149e-06, |
| "loss": 0.2693767547607422, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.3181818181818181, |
| "grad_norm": 0.9352995753288269, |
| "learning_rate": 6.178794677547138e-06, |
| "loss": 0.2981605529785156, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.3636363636363638, |
| "grad_norm": 0.6079849004745483, |
| "learning_rate": 5.946256221802052e-06, |
| "loss": 0.26114463806152344, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.4090909090909092, |
| "grad_norm": 1.1613916158676147, |
| "learning_rate": 5.711574191366427e-06, |
| "loss": 0.3663311004638672, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.4545454545454546, |
| "grad_norm": 1.0265836715698242, |
| "learning_rate": 5.475280216520913e-06, |
| "loss": 0.13217544555664062, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.5, |
| "grad_norm": 0.9267441630363464, |
| "learning_rate": 5.237909579118713e-06, |
| "loss": 0.3060760498046875, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.5454545454545454, |
| "grad_norm": 0.6758596301078796, |
| "learning_rate": 5e-06, |
| "loss": 0.053920745849609375, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.5909090909090908, |
| "grad_norm": 0.6371091604232788, |
| "learning_rate": 4.762090420881289e-06, |
| "loss": 0.11317062377929688, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.6363636363636362, |
| "grad_norm": 0.6892620325088501, |
| "learning_rate": 4.524719783479088e-06, |
| "loss": 0.1634387969970703, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.6818181818181817, |
| "grad_norm": 1.267598032951355, |
| "learning_rate": 4.2884258086335755e-06, |
| "loss": 0.1157989501953125, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.7272727272727273, |
| "grad_norm": 0.618965208530426, |
| "learning_rate": 4.053743778197951e-06, |
| "loss": 0.2590446472167969, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.7727272727272727, |
| "grad_norm": 0.8626583814620972, |
| "learning_rate": 3.821205322452863e-06, |
| "loss": 0.4122934341430664, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.8181818181818183, |
| "grad_norm": 0.5675498843193054, |
| "learning_rate": 3.5913372157928515e-06, |
| "loss": 0.18222999572753906, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.8636363636363638, |
| "grad_norm": 1.346577525138855, |
| "learning_rate": 3.3646601834128924e-06, |
| "loss": 0.36645030975341797, |
| "step": 41 |
| }, |
| { |
| "epoch": 1.9090909090909092, |
| "grad_norm": 0.5783951282501221, |
| "learning_rate": 3.141687721698363e-06, |
| "loss": 0.19093704223632812, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.9545454545454546, |
| "grad_norm": 0.7677918672561646, |
| "learning_rate": 2.9229249349905686e-06, |
| "loss": 0.24652671813964844, |
| "step": 43 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.6522639393806458, |
| "learning_rate": 2.708867391362948e-06, |
| "loss": 0.13533401489257812, |
| "step": 44 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.59344482421875, |
| "eval_runtime": 4.3126, |
| "eval_samples_per_second": 1.159, |
| "eval_steps_per_second": 0.232, |
| "step": 44 |
| }, |
| { |
| "checkpoint_runtime": 134.2782 |
| }, |
| { |
| "epoch": 2.0454545454545454, |
| "grad_norm": 1.315116286277771, |
| "learning_rate": 2.5000000000000015e-06, |
| "loss": 0.2724342346191406, |
| "step": 45 |
| }, |
| { |
| "epoch": 2.090909090909091, |
| "grad_norm": 0.5187699198722839, |
| "learning_rate": 2.296795912722014e-06, |
| "loss": 0.18209326267242432, |
| "step": 46 |
| }, |
| { |
| "epoch": 2.1363636363636362, |
| "grad_norm": 0.9916004538536072, |
| "learning_rate": 2.09971545214401e-06, |
| "loss": 0.2614755630493164, |
| "step": 47 |
| }, |
| { |
| "epoch": 2.1818181818181817, |
| "grad_norm": 0.5112076997756958, |
| "learning_rate": 1.9092050688969736e-06, |
| "loss": 0.1507863998413086, |
| "step": 48 |
| }, |
| { |
| "epoch": 2.227272727272727, |
| "grad_norm": 0.3336804211139679, |
| "learning_rate": 1.7256963302735752e-06, |
| "loss": 0.024288177490234375, |
| "step": 49 |
| }, |
| { |
| "epoch": 2.2727272727272725, |
| "grad_norm": 0.40631377696990967, |
| "learning_rate": 1.549604942589441e-06, |
| "loss": 0.19109153747558594, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.3181818181818183, |
| "grad_norm": 0.8899633288383484, |
| "learning_rate": 1.3813298094746491e-06, |
| "loss": 0.17161941528320312, |
| "step": 51 |
| }, |
| { |
| "epoch": 2.3636363636363638, |
| "grad_norm": 0.5578643679618835, |
| "learning_rate": 1.2212521282287093e-06, |
| "loss": 0.17924213409423828, |
| "step": 52 |
| }, |
| { |
| "epoch": 2.409090909090909, |
| "grad_norm": 1.057443618774414, |
| "learning_rate": 1.0697345262860638e-06, |
| "loss": 0.21059799194335938, |
| "step": 53 |
| }, |
| { |
| "epoch": 2.4545454545454546, |
| "grad_norm": 0.6124624609947205, |
| "learning_rate": 9.271202397483214e-07, |
| "loss": 0.050838470458984375, |
| "step": 54 |
| }, |
| { |
| "epoch": 2.5, |
| "grad_norm": 0.5138548016548157, |
| "learning_rate": 7.937323358440935e-07, |
| "loss": 0.22317028045654297, |
| "step": 55 |
| }, |
| { |
| "epoch": 2.5454545454545454, |
| "grad_norm": 0.5870931148529053, |
| "learning_rate": 6.698729810778065e-07, |
| "loss": 0.02097320556640625, |
| "step": 56 |
| }, |
| { |
| "epoch": 2.590909090909091, |
| "grad_norm": 0.47857600450515747, |
| "learning_rate": 5.558227567253832e-07, |
| "loss": 0.056339263916015625, |
| "step": 57 |
| }, |
| { |
| "epoch": 2.6363636363636362, |
| "grad_norm": 0.4128285050392151, |
| "learning_rate": 4.5184002322740784e-07, |
| "loss": 0.10932445526123047, |
| "step": 58 |
| }, |
| { |
| "epoch": 2.6818181818181817, |
| "grad_norm": 0.9088109135627747, |
| "learning_rate": 3.581603349196372e-07, |
| "loss": 0.04517364501953125, |
| "step": 59 |
| }, |
| { |
| "epoch": 2.7272727272727275, |
| "grad_norm": 0.5057564973831177, |
| "learning_rate": 2.7499590642665773e-07, |
| "loss": 0.19766902923583984, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.7727272727272725, |
| "grad_norm": 0.792408287525177, |
| "learning_rate": 2.0253513192751374e-07, |
| "loss": 0.33954524993896484, |
| "step": 61 |
| }, |
| { |
| "epoch": 2.8181818181818183, |
| "grad_norm": 0.47474050521850586, |
| "learning_rate": 1.4094215838229176e-07, |
| "loss": 0.12943077087402344, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.8636363636363638, |
| "grad_norm": 0.9088992476463318, |
| "learning_rate": 9.035651368646647e-08, |
| "loss": 0.3276538848876953, |
| "step": 63 |
| }, |
| { |
| "epoch": 2.909090909090909, |
| "grad_norm": 0.4451668858528137, |
| "learning_rate": 5.089279059533658e-08, |
| "loss": 0.1589193344116211, |
| "step": 64 |
| }, |
| { |
| "epoch": 2.9545454545454546, |
| "grad_norm": 0.6257097721099854, |
| "learning_rate": 2.264038713457706e-08, |
| "loss": 0.2027444839477539, |
| "step": 65 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.4987045228481293, |
| "learning_rate": 5.6633040849601865e-09, |
| "loss": 0.09051704406738281, |
| "step": 66 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.61431884765625, |
| "eval_runtime": 4.3337, |
| "eval_samples_per_second": 1.154, |
| "eval_steps_per_second": 0.231, |
| "step": 66 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 66, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 22, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 8.409622391826678e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
