Instructions to use risolmayo/31f2c202-4cff-4d57-99bb-425f233050e8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use risolmayo/31f2c202-4cff-4d57-99bb-425f233050e8 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("HuggingFaceH4/zephyr-7b-beta") model = PeftModel.from_pretrained(base_model, "risolmayo/31f2c202-4cff-4d57-99bb-425f233050e8") - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_metric": 0.39435139298439026, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", | |
| "epoch": 0.3368421052631579, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016842105263157896, | |
| "grad_norm": 6.024294853210449, | |
| "learning_rate": 7e-06, | |
| "loss": 3.1518, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016842105263157896, | |
| "eval_loss": 1.1191571950912476, | |
| "eval_runtime": 111.3697, | |
| "eval_samples_per_second": 8.979, | |
| "eval_steps_per_second": 2.245, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003368421052631579, | |
| "grad_norm": 6.236141681671143, | |
| "learning_rate": 1.4e-05, | |
| "loss": 3.6872, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0050526315789473685, | |
| "grad_norm": 7.557410717010498, | |
| "learning_rate": 2.1e-05, | |
| "loss": 3.944, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006736842105263158, | |
| "grad_norm": 6.667514324188232, | |
| "learning_rate": 2.8e-05, | |
| "loss": 3.7891, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008421052631578947, | |
| "grad_norm": 4.870666027069092, | |
| "learning_rate": 3.5e-05, | |
| "loss": 3.5453, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010105263157894737, | |
| "grad_norm": 5.671273231506348, | |
| "learning_rate": 4.2e-05, | |
| "loss": 3.687, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011789473684210527, | |
| "grad_norm": 5.420773983001709, | |
| "learning_rate": 4.899999999999999e-05, | |
| "loss": 3.8273, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013473684210526317, | |
| "grad_norm": 5.291108131408691, | |
| "learning_rate": 5.6e-05, | |
| "loss": 3.9469, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015157894736842105, | |
| "grad_norm": 5.485774040222168, | |
| "learning_rate": 6.3e-05, | |
| "loss": 4.2506, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.016842105263157894, | |
| "grad_norm": 7.075007915496826, | |
| "learning_rate": 7e-05, | |
| "loss": 4.1862, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018526315789473686, | |
| "grad_norm": 7.397273540496826, | |
| "learning_rate": 6.999521567473641e-05, | |
| "loss": 4.2168, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.020210526315789474, | |
| "grad_norm": 7.659411907196045, | |
| "learning_rate": 6.998086400693241e-05, | |
| "loss": 3.9829, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.021894736842105262, | |
| "grad_norm": 6.499504566192627, | |
| "learning_rate": 6.995694892019065e-05, | |
| "loss": 4.2727, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.023578947368421053, | |
| "grad_norm": 8.075024604797363, | |
| "learning_rate": 6.99234769526571e-05, | |
| "loss": 4.2441, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02526315789473684, | |
| "grad_norm": 7.219364643096924, | |
| "learning_rate": 6.988045725523343e-05, | |
| "loss": 3.6529, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.026947368421052633, | |
| "grad_norm": 13.242128372192383, | |
| "learning_rate": 6.982790158907539e-05, | |
| "loss": 3.7233, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02863157894736842, | |
| "grad_norm": 22.818618774414062, | |
| "learning_rate": 6.976582432237733e-05, | |
| "loss": 2.9828, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03031578947368421, | |
| "grad_norm": 13.402886390686035, | |
| "learning_rate": 6.969424242644413e-05, | |
| "loss": 0.7668, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.032, | |
| "grad_norm": 11.43515396118164, | |
| "learning_rate": 6.961317547105138e-05, | |
| "loss": 0.3833, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03368421052631579, | |
| "grad_norm": 13.019227027893066, | |
| "learning_rate": 6.952264561909527e-05, | |
| "loss": 0.1557, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03536842105263158, | |
| "grad_norm": 6.411274433135986, | |
| "learning_rate": 6.942267762053337e-05, | |
| "loss": 0.0357, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03705263157894737, | |
| "grad_norm": 27.83994483947754, | |
| "learning_rate": 6.931329880561832e-05, | |
| "loss": 0.1393, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03873684210526316, | |
| "grad_norm": 2.4345204830169678, | |
| "learning_rate": 6.919453907742597e-05, | |
| "loss": 0.0286, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04042105263157895, | |
| "grad_norm": 31.517459869384766, | |
| "learning_rate": 6.90664309036802e-05, | |
| "loss": 0.3511, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.042105263157894736, | |
| "grad_norm": 0.5334464311599731, | |
| "learning_rate": 6.892900930787656e-05, | |
| "loss": 0.0039, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.043789473684210524, | |
| "grad_norm": 0.3200743496417999, | |
| "learning_rate": 6.87823118597072e-05, | |
| "loss": 0.0014, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.04547368421052632, | |
| "grad_norm": 4.356933116912842, | |
| "learning_rate": 6.862637866478969e-05, | |
| "loss": 0.0069, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.04715789473684211, | |
| "grad_norm": 3.2138633728027344, | |
| "learning_rate": 6.846125235370252e-05, | |
| "loss": 0.035, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.048842105263157895, | |
| "grad_norm": 0.0741715058684349, | |
| "learning_rate": 6.828697807033038e-05, | |
| "loss": 0.0003, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05052631578947368, | |
| "grad_norm": 0.47199904918670654, | |
| "learning_rate": 6.81036034595222e-05, | |
| "loss": 0.0007, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05221052631578947, | |
| "grad_norm": 0.0408998541533947, | |
| "learning_rate": 6.791117865406564e-05, | |
| "loss": 0.0001, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.053894736842105266, | |
| "grad_norm": 24.849538803100586, | |
| "learning_rate": 6.770975626098112e-05, | |
| "loss": 0.0947, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.055578947368421054, | |
| "grad_norm": 0.08601894229650497, | |
| "learning_rate": 6.749939134713974e-05, | |
| "loss": 0.0002, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.05726315789473684, | |
| "grad_norm": 1.5362071990966797, | |
| "learning_rate": 6.728014142420846e-05, | |
| "loss": 0.0017, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.05894736842105263, | |
| "grad_norm": 10.688153266906738, | |
| "learning_rate": 6.7052066432927e-05, | |
| "loss": 0.0053, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06063157894736842, | |
| "grad_norm": 141.94935607910156, | |
| "learning_rate": 6.681522872672069e-05, | |
| "loss": 1.1714, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06231578947368421, | |
| "grad_norm": 2.113950490951538, | |
| "learning_rate": 6.656969305465356e-05, | |
| "loss": 0.0022, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "grad_norm": 9.177931785583496, | |
| "learning_rate": 6.631552654372672e-05, | |
| "loss": 0.0096, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.06568421052631579, | |
| "grad_norm": 0.007726682350039482, | |
| "learning_rate": 6.60527986805264e-05, | |
| "loss": 0.0001, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06736842105263158, | |
| "grad_norm": 0.005540175829082727, | |
| "learning_rate": 6.578158129222711e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06905263157894737, | |
| "grad_norm": 0.04228057339787483, | |
| "learning_rate": 6.550194852695469e-05, | |
| "loss": 0.0001, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07073684210526315, | |
| "grad_norm": 149.91966247558594, | |
| "learning_rate": 6.521397683351509e-05, | |
| "loss": 1.6379, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.07242105263157894, | |
| "grad_norm": 22.759241104125977, | |
| "learning_rate": 6.491774494049386e-05, | |
| "loss": 5.1486, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.07410526315789474, | |
| "grad_norm": 31.00199317932129, | |
| "learning_rate": 6.461333383473272e-05, | |
| "loss": 4.2017, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07578947368421053, | |
| "grad_norm": 21.475034713745117, | |
| "learning_rate": 6.430082673918849e-05, | |
| "loss": 3.8613, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07747368421052632, | |
| "grad_norm": 34.067291259765625, | |
| "learning_rate": 6.398030909018069e-05, | |
| "loss": 5.0442, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.07915789473684211, | |
| "grad_norm": 25.33576011657715, | |
| "learning_rate": 6.365186851403423e-05, | |
| "loss": 3.5212, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0808421052631579, | |
| "grad_norm": 25.13298988342285, | |
| "learning_rate": 6.331559480312315e-05, | |
| "loss": 3.6162, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.08252631578947368, | |
| "grad_norm": 21.35511589050293, | |
| "learning_rate": 6.297157989132236e-05, | |
| "loss": 3.8031, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.08421052631578947, | |
| "grad_norm": 35.120750427246094, | |
| "learning_rate": 6.261991782887377e-05, | |
| "loss": 4.4614, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08421052631578947, | |
| "eval_loss": 0.7924072742462158, | |
| "eval_runtime": 112.6124, | |
| "eval_samples_per_second": 8.88, | |
| "eval_steps_per_second": 2.22, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08589473684210526, | |
| "grad_norm": 8.38847541809082, | |
| "learning_rate": 6.226070475667393e-05, | |
| "loss": 3.4838, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.08757894736842105, | |
| "grad_norm": 5.965296268463135, | |
| "learning_rate": 6.189403887999006e-05, | |
| "loss": 3.9466, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.08926315789473684, | |
| "grad_norm": 4.863672256469727, | |
| "learning_rate": 6.152002044161171e-05, | |
| "loss": 3.3858, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.09094736842105264, | |
| "grad_norm": 3.967648506164551, | |
| "learning_rate": 6.113875169444539e-05, | |
| "loss": 3.5997, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.09263157894736843, | |
| "grad_norm": 3.9109582901000977, | |
| "learning_rate": 6.0750336873559605e-05, | |
| "loss": 3.4546, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.09431578947368421, | |
| "grad_norm": 4.112473011016846, | |
| "learning_rate": 6.035488216768811e-05, | |
| "loss": 3.8372, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "grad_norm": 4.314053058624268, | |
| "learning_rate": 5.9952495690198894e-05, | |
| "loss": 3.7284, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.09768421052631579, | |
| "grad_norm": 4.413819789886475, | |
| "learning_rate": 5.954328744953709e-05, | |
| "loss": 4.0576, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.09936842105263158, | |
| "grad_norm": 4.593724250793457, | |
| "learning_rate": 5.91273693191498e-05, | |
| "loss": 3.6599, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.10105263157894737, | |
| "grad_norm": 5.130562782287598, | |
| "learning_rate": 5.870485500690094e-05, | |
| "loss": 3.8042, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.10273684210526315, | |
| "grad_norm": 4.8895978927612305, | |
| "learning_rate": 5.827586002398468e-05, | |
| "loss": 3.6673, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.10442105263157894, | |
| "grad_norm": 5.687342643737793, | |
| "learning_rate": 5.784050165334589e-05, | |
| "loss": 3.4877, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.10610526315789473, | |
| "grad_norm": 5.853930950164795, | |
| "learning_rate": 5.739889891761608e-05, | |
| "loss": 3.8737, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.10778947368421053, | |
| "grad_norm": 5.930052757263184, | |
| "learning_rate": 5.6951172546573794e-05, | |
| "loss": 3.6394, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.10947368421052632, | |
| "grad_norm": 7.453705787658691, | |
| "learning_rate": 5.6497444944138376e-05, | |
| "loss": 4.0279, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.11115789473684211, | |
| "grad_norm": 8.265393257141113, | |
| "learning_rate": 5.603784015490587e-05, | |
| "loss": 3.4707, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.1128421052631579, | |
| "grad_norm": 8.47661304473877, | |
| "learning_rate": 5.557248383023655e-05, | |
| "loss": 3.4433, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.11452631578947368, | |
| "grad_norm": 36.97196960449219, | |
| "learning_rate": 5.510150319390302e-05, | |
| "loss": 2.4884, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.11621052631578947, | |
| "grad_norm": 31.378150939941406, | |
| "learning_rate": 5.4625027007308546e-05, | |
| "loss": 0.8111, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.11789473684210526, | |
| "grad_norm": 4.121087551116943, | |
| "learning_rate": 5.414318553428494e-05, | |
| "loss": 0.1426, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.11957894736842105, | |
| "grad_norm": 1.8152331113815308, | |
| "learning_rate": 5.3656110505479776e-05, | |
| "loss": 0.0321, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.12126315789473684, | |
| "grad_norm": 0.4557514786720276, | |
| "learning_rate": 5.316393508234253e-05, | |
| "loss": 0.0082, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.12294736842105262, | |
| "grad_norm": 0.7588320374488831, | |
| "learning_rate": 5.266679382071953e-05, | |
| "loss": 0.0059, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.12463157894736843, | |
| "grad_norm": 6.640488147735596, | |
| "learning_rate": 5.216482263406778e-05, | |
| "loss": 0.0578, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.12631578947368421, | |
| "grad_norm": 1.1129047870635986, | |
| "learning_rate": 5.1658158756297576e-05, | |
| "loss": 0.0882, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.128, | |
| "grad_norm": 4.541646957397461, | |
| "learning_rate": 5.114694070425407e-05, | |
| "loss": 0.0046, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.1296842105263158, | |
| "grad_norm": 0.05839858204126358, | |
| "learning_rate": 5.063130823984823e-05, | |
| "loss": 0.0005, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.13136842105263158, | |
| "grad_norm": 121.34305572509766, | |
| "learning_rate": 5.011140233184724e-05, | |
| "loss": 0.6478, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.13305263157894737, | |
| "grad_norm": 0.017042573541402817, | |
| "learning_rate": 4.958736511733516e-05, | |
| "loss": 0.0002, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.13473684210526315, | |
| "grad_norm": 0.45838016271591187, | |
| "learning_rate": 4.905933986285393e-05, | |
| "loss": 0.0012, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.13642105263157894, | |
| "grad_norm": 0.12328316271305084, | |
| "learning_rate": 4.8527470925235824e-05, | |
| "loss": 0.0005, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.13810526315789473, | |
| "grad_norm": 5.341918468475342, | |
| "learning_rate": 4.799190371213772e-05, | |
| "loss": 0.0099, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.13978947368421052, | |
| "grad_norm": 1.8465338945388794, | |
| "learning_rate": 4.745278464228808e-05, | |
| "loss": 0.214, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.1414736842105263, | |
| "grad_norm": 0.053226958960294724, | |
| "learning_rate": 4.69102611054575e-05, | |
| "loss": 0.0001, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.1431578947368421, | |
| "grad_norm": 0.020978201180696487, | |
| "learning_rate": 4.6364481422163926e-05, | |
| "loss": 0.0001, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.14484210526315788, | |
| "grad_norm": 15.91220760345459, | |
| "learning_rate": 4.581559480312316e-05, | |
| "loss": 0.0311, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.14652631578947367, | |
| "grad_norm": 0.0033549582585692406, | |
| "learning_rate": 4.526375130845627e-05, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.1482105263157895, | |
| "grad_norm": 3.0451927185058594, | |
| "learning_rate": 4.4709101806664554e-05, | |
| "loss": 0.2818, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.14989473684210528, | |
| "grad_norm": 2.114051342010498, | |
| "learning_rate": 4.4151797933383685e-05, | |
| "loss": 0.056, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.15157894736842106, | |
| "grad_norm": 7.292730808258057, | |
| "learning_rate": 4.359199204992797e-05, | |
| "loss": 0.0047, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.15326315789473685, | |
| "grad_norm": 0.010774493217468262, | |
| "learning_rate": 4.30298372016363e-05, | |
| "loss": 0.0001, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.15494736842105264, | |
| "grad_norm": 0.009904594160616398, | |
| "learning_rate": 4.246548707603114e-05, | |
| "loss": 0.0001, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.15663157894736843, | |
| "grad_norm": 10.971230506896973, | |
| "learning_rate": 4.1899095960801805e-05, | |
| "loss": 3.7023, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.15831578947368422, | |
| "grad_norm": 11.993653297424316, | |
| "learning_rate": 4.133081870162385e-05, | |
| "loss": 3.2664, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 14.521844863891602, | |
| "learning_rate": 4.076081065982569e-05, | |
| "loss": 3.733, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.1616842105263158, | |
| "grad_norm": 15.639982223510742, | |
| "learning_rate": 4.018922766991447e-05, | |
| "loss": 3.1755, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.16336842105263158, | |
| "grad_norm": 14.03834056854248, | |
| "learning_rate": 3.961622599697241e-05, | |
| "loss": 3.3718, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.16505263157894737, | |
| "grad_norm": 19.315185546875, | |
| "learning_rate": 3.9041962293935516e-05, | |
| "loss": 3.6855, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.16673684210526316, | |
| "grad_norm": 18.49924087524414, | |
| "learning_rate": 3.84665935587662e-05, | |
| "loss": 2.8886, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.16842105263157894, | |
| "grad_norm": 19.87647247314453, | |
| "learning_rate": 3.7890277091531636e-05, | |
| "loss": 2.7829, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16842105263157894, | |
| "eval_loss": 0.43836522102355957, | |
| "eval_runtime": 112.5255, | |
| "eval_samples_per_second": 8.887, | |
| "eval_steps_per_second": 2.222, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.17010526315789473, | |
| "grad_norm": 4.052360534667969, | |
| "learning_rate": 3.7313170451399475e-05, | |
| "loss": 3.6542, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.17178947368421052, | |
| "grad_norm": 3.763493537902832, | |
| "learning_rate": 3.673543141356278e-05, | |
| "loss": 3.6541, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.1734736842105263, | |
| "grad_norm": 3.3259809017181396, | |
| "learning_rate": 3.6157217926105783e-05, | |
| "loss": 3.1932, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.1751578947368421, | |
| "grad_norm": 3.5312576293945312, | |
| "learning_rate": 3.557868806682255e-05, | |
| "loss": 3.4563, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.17684210526315788, | |
| "grad_norm": 3.349715232849121, | |
| "learning_rate": 3.5e-05, | |
| "loss": 3.343, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.17852631578947367, | |
| "grad_norm": 3.2899487018585205, | |
| "learning_rate": 3.442131193317745e-05, | |
| "loss": 3.4426, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.18021052631578946, | |
| "grad_norm": 3.7904226779937744, | |
| "learning_rate": 3.384278207389421e-05, | |
| "loss": 3.2929, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.18189473684210528, | |
| "grad_norm": 3.846342086791992, | |
| "learning_rate": 3.3264568586437216e-05, | |
| "loss": 2.8453, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.18357894736842106, | |
| "grad_norm": 4.319014072418213, | |
| "learning_rate": 3.268682954860052e-05, | |
| "loss": 3.4215, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.18526315789473685, | |
| "grad_norm": 4.5721659660339355, | |
| "learning_rate": 3.210972290846837e-05, | |
| "loss": 3.217, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.18694736842105264, | |
| "grad_norm": 5.326986312866211, | |
| "learning_rate": 3.15334064412338e-05, | |
| "loss": 3.5518, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.18863157894736843, | |
| "grad_norm": 5.925167083740234, | |
| "learning_rate": 3.0958037706064485e-05, | |
| "loss": 3.2563, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.19031578947368422, | |
| "grad_norm": 5.811061859130859, | |
| "learning_rate": 3.038377400302758e-05, | |
| "loss": 3.4556, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.192, | |
| "grad_norm": 8.005414009094238, | |
| "learning_rate": 2.9810772330085524e-05, | |
| "loss": 3.4495, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.1936842105263158, | |
| "grad_norm": 8.293067932128906, | |
| "learning_rate": 2.9239189340174306e-05, | |
| "loss": 3.3465, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.19536842105263158, | |
| "grad_norm": 10.697053909301758, | |
| "learning_rate": 2.8669181298376163e-05, | |
| "loss": 3.3562, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.19705263157894737, | |
| "grad_norm": 7.104681015014648, | |
| "learning_rate": 2.8100904039198193e-05, | |
| "loss": 0.0802, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.19873684210526316, | |
| "grad_norm": 0.23395206034183502, | |
| "learning_rate": 2.7534512923968863e-05, | |
| "loss": 0.0015, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.20042105263157894, | |
| "grad_norm": 0.02725689671933651, | |
| "learning_rate": 2.6970162798363695e-05, | |
| "loss": 0.0003, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.20210526315789473, | |
| "grad_norm": 0.014771652407944202, | |
| "learning_rate": 2.640800795007203e-05, | |
| "loss": 0.0002, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.20378947368421052, | |
| "grad_norm": 0.011932775378227234, | |
| "learning_rate": 2.5848202066616305e-05, | |
| "loss": 0.0001, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.2054736842105263, | |
| "grad_norm": 0.011874247342348099, | |
| "learning_rate": 2.5290898193335446e-05, | |
| "loss": 0.0001, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.2071578947368421, | |
| "grad_norm": 0.031760357320308685, | |
| "learning_rate": 2.4736248691543736e-05, | |
| "loss": 0.0001, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.20884210526315788, | |
| "grad_norm": 1.686309576034546, | |
| "learning_rate": 2.4184405196876842e-05, | |
| "loss": 0.0003, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 0.012486536987125874, | |
| "learning_rate": 2.363551857783608e-05, | |
| "loss": 0.0002, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.21221052631578946, | |
| "grad_norm": 0.008614882826805115, | |
| "learning_rate": 2.308973889454249e-05, | |
| "loss": 0.0001, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.21389473684210528, | |
| "grad_norm": 0.009931172244250774, | |
| "learning_rate": 2.2547215357711918e-05, | |
| "loss": 0.0001, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.21557894736842106, | |
| "grad_norm": 0.008893569000065327, | |
| "learning_rate": 2.2008096287862266e-05, | |
| "loss": 0.0001, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.21726315789473685, | |
| "grad_norm": 9.234477043151855, | |
| "learning_rate": 2.1472529074764177e-05, | |
| "loss": 0.0103, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.21894736842105264, | |
| "grad_norm": 0.008060800842940807, | |
| "learning_rate": 2.0940660137146074e-05, | |
| "loss": 0.0001, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.22063157894736843, | |
| "grad_norm": 0.008976759389042854, | |
| "learning_rate": 2.041263488266484e-05, | |
| "loss": 0.0001, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.22231578947368422, | |
| "grad_norm": 0.007290771696716547, | |
| "learning_rate": 1.988859766815275e-05, | |
| "loss": 0.0001, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.224, | |
| "grad_norm": 0.007480121683329344, | |
| "learning_rate": 1.9368691760151773e-05, | |
| "loss": 0.0001, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.2256842105263158, | |
| "grad_norm": 0.006769363768398762, | |
| "learning_rate": 1.885305929574593e-05, | |
| "loss": 0.0001, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.22736842105263158, | |
| "grad_norm": 0.00597826112061739, | |
| "learning_rate": 1.8341841243702424e-05, | |
| "loss": 0.0001, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.22905263157894737, | |
| "grad_norm": 0.005812656134366989, | |
| "learning_rate": 1.7835177365932225e-05, | |
| "loss": 0.0001, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.23073684210526316, | |
| "grad_norm": 0.005943721160292625, | |
| "learning_rate": 1.7333206179280478e-05, | |
| "loss": 0.0001, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.23242105263157894, | |
| "grad_norm": 0.0051173800602555275, | |
| "learning_rate": 1.6836064917657478e-05, | |
| "loss": 0.0001, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.23410526315789473, | |
| "grad_norm": 0.004846564959734678, | |
| "learning_rate": 1.6343889494520224e-05, | |
| "loss": 0.0001, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.23578947368421052, | |
| "grad_norm": 0.005883246660232544, | |
| "learning_rate": 1.5856814465715064e-05, | |
| "loss": 0.0001, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.2374736842105263, | |
| "grad_norm": 0.004718493670225143, | |
| "learning_rate": 1.5374972992691458e-05, | |
| "loss": 0.0001, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.2391578947368421, | |
| "grad_norm": 5.402604579925537, | |
| "learning_rate": 1.4898496806096974e-05, | |
| "loss": 1.1714, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.24084210526315789, | |
| "grad_norm": 10.396501541137695, | |
| "learning_rate": 1.4427516169763444e-05, | |
| "loss": 3.7748, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.24252631578947367, | |
| "grad_norm": 12.204318046569824, | |
| "learning_rate": 1.396215984509412e-05, | |
| "loss": 2.449, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.24421052631578946, | |
| "grad_norm": 13.88398551940918, | |
| "learning_rate": 1.3502555055861625e-05, | |
| "loss": 3.0316, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.24589473684210525, | |
| "grad_norm": 15.177433013916016, | |
| "learning_rate": 1.3048827453426203e-05, | |
| "loss": 2.7415, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.24757894736842107, | |
| "grad_norm": 13.086450576782227, | |
| "learning_rate": 1.2601101082383917e-05, | |
| "loss": 2.6946, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.24926315789473685, | |
| "grad_norm": 18.535987854003906, | |
| "learning_rate": 1.2159498346654094e-05, | |
| "loss": 2.5944, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.25094736842105264, | |
| "grad_norm": 16.978410720825195, | |
| "learning_rate": 1.1724139976015306e-05, | |
| "loss": 1.724, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.25263157894736843, | |
| "grad_norm": 25.89999008178711, | |
| "learning_rate": 1.1295144993099068e-05, | |
| "loss": 2.9555, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.25263157894736843, | |
| "eval_loss": 0.40092983841896057, | |
| "eval_runtime": 112.4794, | |
| "eval_samples_per_second": 8.891, | |
| "eval_steps_per_second": 2.223, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.2543157894736842, | |
| "grad_norm": 2.652461290359497, | |
| "learning_rate": 1.0872630680850196e-05, | |
| "loss": 3.0062, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.256, | |
| "grad_norm": 2.8873250484466553, | |
| "learning_rate": 1.0456712550462898e-05, | |
| "loss": 3.4078, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.2576842105263158, | |
| "grad_norm": 3.0040674209594727, | |
| "learning_rate": 1.0047504309801104e-05, | |
| "loss": 3.1916, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.2593684210526316, | |
| "grad_norm": 2.793316602706909, | |
| "learning_rate": 9.645117832311886e-06, | |
| "loss": 3.4096, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.26105263157894737, | |
| "grad_norm": 3.250425338745117, | |
| "learning_rate": 9.249663126440394e-06, | |
| "loss": 3.3077, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.26273684210526316, | |
| "grad_norm": 3.3044142723083496, | |
| "learning_rate": 8.861248305554624e-06, | |
| "loss": 3.6225, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.26442105263157895, | |
| "grad_norm": 3.566394567489624, | |
| "learning_rate": 8.47997955838829e-06, | |
| "loss": 3.6262, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.26610526315789473, | |
| "grad_norm": 3.730665683746338, | |
| "learning_rate": 8.10596112000994e-06, | |
| "loss": 3.437, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.2677894736842105, | |
| "grad_norm": 4.241246223449707, | |
| "learning_rate": 7.739295243326067e-06, | |
| "loss": 3.5003, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.2694736842105263, | |
| "grad_norm": 4.298994541168213, | |
| "learning_rate": 7.380082171126228e-06, | |
| "loss": 3.5357, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.2711578947368421, | |
| "grad_norm": 5.053274154663086, | |
| "learning_rate": 7.028420108677635e-06, | |
| "loss": 3.605, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.2728421052631579, | |
| "grad_norm": 5.663376331329346, | |
| "learning_rate": 6.684405196876842e-06, | |
| "loss": 3.6048, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.2745263157894737, | |
| "grad_norm": 5.2607903480529785, | |
| "learning_rate": 6.3481314859657675e-06, | |
| "loss": 3.4462, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.27621052631578946, | |
| "grad_norm": 5.644373893737793, | |
| "learning_rate": 6.019690909819298e-06, | |
| "loss": 3.3231, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.27789473684210525, | |
| "grad_norm": 5.945282459259033, | |
| "learning_rate": 5.6991732608115e-06, | |
| "loss": 3.0284, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.27957894736842104, | |
| "grad_norm": 7.386387348175049, | |
| "learning_rate": 5.386666165267256e-06, | |
| "loss": 3.37, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.2812631578947368, | |
| "grad_norm": 8.950904846191406, | |
| "learning_rate": 5.08225505950613e-06, | |
| "loss": 3.4616, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.2829473684210526, | |
| "grad_norm": 9.204294204711914, | |
| "learning_rate": 4.786023166484913e-06, | |
| "loss": 1.0604, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.2846315789473684, | |
| "grad_norm": 0.005298123694956303, | |
| "learning_rate": 4.498051473045291e-06, | |
| "loss": 0.0, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.2863157894736842, | |
| "grad_norm": 1.4738227128982544, | |
| "learning_rate": 4.218418707772886e-06, | |
| "loss": 0.0011, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.288, | |
| "grad_norm": 0.003732364857569337, | |
| "learning_rate": 3.947201319473587e-06, | |
| "loss": 0.0001, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.28968421052631577, | |
| "grad_norm": 0.003882531775161624, | |
| "learning_rate": 3.684473456273278e-06, | |
| "loss": 0.0001, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.29136842105263155, | |
| "grad_norm": 0.003962241113185883, | |
| "learning_rate": 3.4303069453464383e-06, | |
| "loss": 0.0001, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.29305263157894734, | |
| "grad_norm": 0.003944694995880127, | |
| "learning_rate": 3.184771273279312e-06, | |
| "loss": 0.0001, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.29473684210526313, | |
| "grad_norm": 0.004233397077769041, | |
| "learning_rate": 2.947933567072987e-06, | |
| "loss": 0.0001, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.296421052631579, | |
| "grad_norm": 0.004388746805489063, | |
| "learning_rate": 2.719858575791534e-06, | |
| "loss": 0.0001, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.29810526315789476, | |
| "grad_norm": 1.8857475519180298, | |
| "learning_rate": 2.500608652860256e-06, | |
| "loss": 0.1626, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.29978947368421055, | |
| "grad_norm": 0.0037590626161545515, | |
| "learning_rate": 2.2902437390188737e-06, | |
| "loss": 0.0001, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.30147368421052634, | |
| "grad_norm": 0.004339190665632486, | |
| "learning_rate": 2.0888213459343587e-06, | |
| "loss": 0.0001, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.3031578947368421, | |
| "grad_norm": 0.5742155313491821, | |
| "learning_rate": 1.8963965404777875e-06, | |
| "loss": 0.0133, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.3048421052631579, | |
| "grad_norm": 0.003307727398350835, | |
| "learning_rate": 1.7130219296696263e-06, | |
| "loss": 0.0, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.3065263157894737, | |
| "grad_norm": 2.4448399543762207, | |
| "learning_rate": 1.5387476462974824e-06, | |
| "loss": 0.135, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.3082105263157895, | |
| "grad_norm": 0.004187013953924179, | |
| "learning_rate": 1.3736213352103147e-06, | |
| "loss": 0.0001, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.3098947368421053, | |
| "grad_norm": 3.6251096725463867, | |
| "learning_rate": 1.2176881402928002e-06, | |
| "loss": 0.1389, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.31157894736842107, | |
| "grad_norm": 0.004039019346237183, | |
| "learning_rate": 1.0709906921234367e-06, | |
| "loss": 0.0001, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.31326315789473685, | |
| "grad_norm": 0.0039500705897808075, | |
| "learning_rate": 9.33569096319799e-07, | |
| "loss": 0.0001, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.31494736842105264, | |
| "grad_norm": 0.003979185130447149, | |
| "learning_rate": 8.054609225740255e-07, | |
| "loss": 0.0001, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.31663157894736843, | |
| "grad_norm": 0.006327040959149599, | |
| "learning_rate": 6.867011943816724e-07, | |
| "loss": 0.0001, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.3183157894736842, | |
| "grad_norm": 1.6148942708969116, | |
| "learning_rate": 5.77322379466617e-07, | |
| "loss": 0.1009, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 1.6720211505889893, | |
| "learning_rate": 4.773543809047186e-07, | |
| "loss": 0.1362, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.3216842105263158, | |
| "grad_norm": 0.004089950583875179, | |
| "learning_rate": 3.868245289486027e-07, | |
| "loss": 0.0001, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.3233684210526316, | |
| "grad_norm": 9.69481086730957, | |
| "learning_rate": 3.0575757355586817e-07, | |
| "loss": 3.0134, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.32505263157894737, | |
| "grad_norm": 11.325800895690918, | |
| "learning_rate": 2.3417567762266497e-07, | |
| "loss": 3.2252, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.32673684210526316, | |
| "grad_norm": 12.9413423538208, | |
| "learning_rate": 1.7209841092460043e-07, | |
| "loss": 2.9453, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.32842105263157895, | |
| "grad_norm": 12.968132019042969, | |
| "learning_rate": 1.1954274476655534e-07, | |
| "loss": 2.6332, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.33010526315789473, | |
| "grad_norm": 15.115516662597656, | |
| "learning_rate": 7.652304734289127e-08, | |
| "loss": 2.2777, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.3317894736842105, | |
| "grad_norm": 20.15196418762207, | |
| "learning_rate": 4.30510798093342e-08, | |
| "loss": 3.5042, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.3334736842105263, | |
| "grad_norm": 19.404085159301758, | |
| "learning_rate": 1.9135993067588284e-08, | |
| "loss": 2.7561, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.3351578947368421, | |
| "grad_norm": 19.473817825317383, | |
| "learning_rate": 4.784325263584854e-09, | |
| "loss": 2.7526, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.3368421052631579, | |
| "grad_norm": 26.683012008666992, | |
| "learning_rate": 0.0, | |
| "loss": 2.8218, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3368421052631579, | |
| "eval_loss": 0.39435139298439026, | |
| "eval_runtime": 112.5272, | |
| "eval_samples_per_second": 8.887, | |
| "eval_steps_per_second": 2.222, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 4, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.8691510080202342e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |