| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 11, |
| "global_step": 58, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.017241379310344827, |
| "grad_norm": 0.21293413639068604, |
| "learning_rate": 0.0, |
| "loss": 1.57470703125, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.034482758620689655, |
| "grad_norm": 0.2269705981016159, |
| "learning_rate": 1.6666666666666667e-06, |
| "loss": 1.6982421875, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.05172413793103448, |
| "grad_norm": 0.2178458869457245, |
| "learning_rate": 3.3333333333333333e-06, |
| "loss": 1.34033203125, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.06896551724137931, |
| "grad_norm": 0.21527980268001556, |
| "learning_rate": 5e-06, |
| "loss": 1.51416015625, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.08620689655172414, |
| "grad_norm": 0.21911631524562836, |
| "learning_rate": 6.666666666666667e-06, |
| "loss": 1.59765625, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.10344827586206896, |
| "grad_norm": 0.1833397001028061, |
| "learning_rate": 8.333333333333334e-06, |
| "loss": 1.54833984375, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.1206896551724138, |
| "grad_norm": 0.20413196086883545, |
| "learning_rate": 1e-05, |
| "loss": 1.45361328125, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.13793103448275862, |
| "grad_norm": 0.19401277601718903, |
| "learning_rate": 9.991789994004929e-06, |
| "loss": 1.41455078125, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.15517241379310345, |
| "grad_norm": 0.23864445090293884, |
| "learning_rate": 9.967189933441243e-06, |
| "loss": 1.4365234375, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.1724137931034483, |
| "grad_norm": 0.2296784520149231, |
| "learning_rate": 9.926289581262147e-06, |
| "loss": 1.35986328125, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.1896551724137931, |
| "grad_norm": 0.24175795912742615, |
| "learning_rate": 9.869238178417235e-06, |
| "loss": 1.5634765625, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.20689655172413793, |
| "grad_norm": 0.20265139639377594, |
| "learning_rate": 9.796243899288455e-06, |
| "loss": 1.52880859375, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.22413793103448276, |
| "grad_norm": 0.23336376249790192, |
| "learning_rate": 9.707573092084368e-06, |
| "loss": 1.689453125, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.2413793103448276, |
| "grad_norm": 0.2111799418926239, |
| "learning_rate": 9.603549306964408e-06, |
| "loss": 1.61328125, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.2413793103448276, |
| "eval_loss": 1.4794921875, |
| "eval_runtime": 2.5217, |
| "eval_samples_per_second": 1.586, |
| "eval_steps_per_second": 0.397, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.25862068965517243, |
| "grad_norm": 0.21442772448062897, |
| "learning_rate": 9.484552115439445e-06, |
| "loss": 1.39990234375, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.27586206896551724, |
| "grad_norm": 0.21152661740779877, |
| "learning_rate": 9.351015725356515e-06, |
| "loss": 1.42919921875, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.29310344827586204, |
| "grad_norm": 0.21132130920886993, |
| "learning_rate": 9.203427396521454e-06, |
| "loss": 1.5087890625, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.3103448275862069, |
| "grad_norm": 0.22954435646533966, |
| "learning_rate": 9.042325662740726e-06, |
| "loss": 1.46826171875, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.3275862068965517, |
| "grad_norm": 0.23091132938861847, |
| "learning_rate": 8.868298366769956e-06, |
| "loss": 1.6494140625, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.3448275862068966, |
| "grad_norm": 0.27502211928367615, |
| "learning_rate": 8.681980515339464e-06, |
| "loss": 1.5244140625, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.3620689655172414, |
| "grad_norm": 0.20342087745666504, |
| "learning_rate": 8.484051962083579e-06, |
| "loss": 1.42333984375, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.3793103448275862, |
| "grad_norm": 0.21416571736335754, |
| "learning_rate": 8.275234926828446e-06, |
| "loss": 1.396484375, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.39655172413793105, |
| "grad_norm": 0.21919746696949005, |
| "learning_rate": 8.056291360290202e-06, |
| "loss": 1.42626953125, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.41379310344827586, |
| "grad_norm": 0.2595324218273163, |
| "learning_rate": 7.828020163799455e-06, |
| "loss": 1.7578125, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.43103448275862066, |
| "grad_norm": 0.2378513365983963, |
| "learning_rate": 7.5912542741969585e-06, |
| "loss": 1.453125, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.43103448275862066, |
| "eval_loss": 1.455078125, |
| "eval_runtime": 2.5283, |
| "eval_samples_per_second": 1.582, |
| "eval_steps_per_second": 0.396, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.4482758620689655, |
| "grad_norm": 0.2067023515701294, |
| "learning_rate": 7.346857624537407e-06, |
| "loss": 1.52197265625, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.46551724137931033, |
| "grad_norm": 0.1973377913236618, |
| "learning_rate": 7.095721991691411e-06, |
| "loss": 1.3515625, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.4827586206896552, |
| "grad_norm": 0.2518433928489685, |
| "learning_rate": 6.838763742348414e-06, |
| "loss": 1.6005859375, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.24979768693447113, |
| "learning_rate": 6.576920489294011e-06, |
| "loss": 1.748046875, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.5172413793103449, |
| "grad_norm": 0.21077397465705872, |
| "learning_rate": 6.311147670162576e-06, |
| "loss": 1.2763671875, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.5344827586206896, |
| "grad_norm": 0.23148714005947113, |
| "learning_rate": 6.042415061148954e-06, |
| "loss": 1.5751953125, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.5517241379310345, |
| "grad_norm": 0.21228323876857758, |
| "learning_rate": 5.771703238400288e-06, |
| "loss": 1.53271484375, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.5689655172413793, |
| "grad_norm": 0.197456955909729, |
| "learning_rate": 5.500000000000001e-06, |
| "loss": 1.246337890625, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.5862068965517241, |
| "grad_norm": 0.20909880101680756, |
| "learning_rate": 5.228296761599713e-06, |
| "loss": 1.29736328125, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.603448275862069, |
| "grad_norm": 0.20181578397750854, |
| "learning_rate": 4.957584938851048e-06, |
| "loss": 1.521484375, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.6206896551724138, |
| "grad_norm": 0.2005235105752945, |
| "learning_rate": 4.6888523298374245e-06, |
| "loss": 1.2978515625, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.6206896551724138, |
| "eval_loss": 1.435546875, |
| "eval_runtime": 2.5169, |
| "eval_samples_per_second": 1.589, |
| "eval_steps_per_second": 0.397, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.6379310344827587, |
| "grad_norm": 0.21248990297317505, |
| "learning_rate": 4.423079510705992e-06, |
| "loss": 1.6171875, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.6551724137931034, |
| "grad_norm": 0.22428344190120697, |
| "learning_rate": 4.1612362576515875e-06, |
| "loss": 1.5224609375, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.6724137931034483, |
| "grad_norm": 0.2146124243736267, |
| "learning_rate": 3.904278008308589e-06, |
| "loss": 1.2802734375, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.6896551724137931, |
| "grad_norm": 0.19008564949035645, |
| "learning_rate": 3.653142375462596e-06, |
| "loss": 1.40625, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.7068965517241379, |
| "grad_norm": 0.18319071829319, |
| "learning_rate": 3.408745725803042e-06, |
| "loss": 1.484375, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.7241379310344828, |
| "grad_norm": 0.21213003993034363, |
| "learning_rate": 3.1719798362005444e-06, |
| "loss": 1.52490234375, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.7413793103448276, |
| "grad_norm": 0.21247462928295135, |
| "learning_rate": 2.9437086397097996e-06, |
| "loss": 1.4072265625, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.7586206896551724, |
| "grad_norm": 0.22428198158740997, |
| "learning_rate": 2.7247650731715563e-06, |
| "loss": 1.412109375, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.7758620689655172, |
| "grad_norm": 0.18434979021549225, |
| "learning_rate": 2.515948037916423e-06, |
| "loss": 1.41943359375, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.7931034482758621, |
| "grad_norm": 0.22083927690982819, |
| "learning_rate": 2.3180194846605367e-06, |
| "loss": 1.50927734375, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.8103448275862069, |
| "grad_norm": 0.21267378330230713, |
| "learning_rate": 2.131701633230045e-06, |
| "loss": 1.55126953125, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.8103448275862069, |
| "eval_loss": 1.421875, |
| "eval_runtime": 2.527, |
| "eval_samples_per_second": 1.583, |
| "eval_steps_per_second": 0.396, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.8275862068965517, |
| "grad_norm": 0.18734264373779297, |
| "learning_rate": 1.957674337259275e-06, |
| "loss": 1.30615234375, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.8448275862068966, |
| "grad_norm": 0.18868029117584229, |
| "learning_rate": 1.7965726034785466e-06, |
| "loss": 1.3740234375, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.8620689655172413, |
| "grad_norm": 0.19361327588558197, |
| "learning_rate": 1.648984274643487e-06, |
| "loss": 1.40380859375, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.8793103448275862, |
| "grad_norm": 0.1973700374364853, |
| "learning_rate": 1.515447884560556e-06, |
| "loss": 1.3046875, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.896551724137931, |
| "grad_norm": 0.2214573472738266, |
| "learning_rate": 1.3964506930355947e-06, |
| "loss": 1.58349609375, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.9137931034482759, |
| "grad_norm": 0.2411319464445114, |
| "learning_rate": 1.292426907915634e-06, |
| "loss": 1.6142578125, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.9310344827586207, |
| "grad_norm": 0.24840229749679565, |
| "learning_rate": 1.203756100711545e-06, |
| "loss": 1.728515625, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.9482758620689655, |
| "grad_norm": 0.20567460358142853, |
| "learning_rate": 1.130761821582766e-06, |
| "loss": 1.4443359375, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.9655172413793104, |
| "grad_norm": 0.1932135969400406, |
| "learning_rate": 1.0737104187378543e-06, |
| "loss": 1.4521484375, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.9827586206896551, |
| "grad_norm": 0.2393965870141983, |
| "learning_rate": 1.0328100665587573e-06, |
| "loss": 1.59716796875, |
| "step": 57 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.19470740854740143, |
| "learning_rate": 1.0082100059950713e-06, |
| "loss": 1.38720703125, |
| "step": 58 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.4189453125, |
| "eval_runtime": 2.523, |
| "eval_samples_per_second": 1.585, |
| "eval_steps_per_second": 0.396, |
| "step": 58 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 58, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 0, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.0371028860744499e+18, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
