Text Classification
PEFT
Safetensors
rag-gym
retrieval-augmented-generation
agent
lora
process-supervision
reward-model
Instructions to use RAG-Gym/Direct-MedQA-PRM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use RAG-Gym/Direct-MedQA-PRM with PEFT:
from peft import PeftModel from transformers import AutoModelForSequenceClassification base_model = AutoModelForSequenceClassification.from_pretrained("meta-llama/Meta-Llama-3.1-8B-Instruct") model = PeftModel.from_pretrained(base_model, "RAG-Gym/Direct-MedQA-PRM") - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9980430528375733, | |
| "eval_steps": 500, | |
| "global_step": 255, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003913894324853229, | |
| "grad_norm": 81.35062408447266, | |
| "learning_rate": 9.960784313725492e-06, | |
| "loss": 0.9609, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007827788649706457, | |
| "grad_norm": 52.11482238769531, | |
| "learning_rate": 9.921568627450981e-06, | |
| "loss": 0.8496, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.011741682974559686, | |
| "grad_norm": 26.55351448059082, | |
| "learning_rate": 9.882352941176472e-06, | |
| "loss": 0.6934, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.015655577299412915, | |
| "grad_norm": 55.15858840942383, | |
| "learning_rate": 9.843137254901962e-06, | |
| "loss": 0.7539, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.019569471624266144, | |
| "grad_norm": 43.13751220703125, | |
| "learning_rate": 9.803921568627451e-06, | |
| "loss": 0.7188, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.023483365949119372, | |
| "grad_norm": 32.82776641845703, | |
| "learning_rate": 9.764705882352942e-06, | |
| "loss": 0.7344, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0273972602739726, | |
| "grad_norm": 32.37958908081055, | |
| "learning_rate": 9.725490196078432e-06, | |
| "loss": 0.7695, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03131115459882583, | |
| "grad_norm": 23.465608596801758, | |
| "learning_rate": 9.686274509803923e-06, | |
| "loss": 0.6152, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03522504892367906, | |
| "grad_norm": 23.890037536621094, | |
| "learning_rate": 9.647058823529412e-06, | |
| "loss": 0.7305, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03913894324853229, | |
| "grad_norm": 29.455656051635742, | |
| "learning_rate": 9.607843137254903e-06, | |
| "loss": 0.6875, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.043052837573385516, | |
| "grad_norm": 30.304548263549805, | |
| "learning_rate": 9.568627450980393e-06, | |
| "loss": 0.6426, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.046966731898238745, | |
| "grad_norm": 28.69137191772461, | |
| "learning_rate": 9.529411764705882e-06, | |
| "loss": 0.7051, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.050880626223091974, | |
| "grad_norm": 21.705123901367188, | |
| "learning_rate": 9.490196078431373e-06, | |
| "loss": 0.7051, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0547945205479452, | |
| "grad_norm": 30.71137046813965, | |
| "learning_rate": 9.450980392156863e-06, | |
| "loss": 0.8711, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05870841487279843, | |
| "grad_norm": 21.21854019165039, | |
| "learning_rate": 9.411764705882354e-06, | |
| "loss": 0.6465, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06262230919765166, | |
| "grad_norm": 20.575902938842773, | |
| "learning_rate": 9.372549019607843e-06, | |
| "loss": 0.6816, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06653620352250489, | |
| "grad_norm": 26.486536026000977, | |
| "learning_rate": 9.333333333333334e-06, | |
| "loss": 0.6484, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07045009784735812, | |
| "grad_norm": 20.01655387878418, | |
| "learning_rate": 9.294117647058824e-06, | |
| "loss": 0.6621, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07436399217221135, | |
| "grad_norm": 27.65776252746582, | |
| "learning_rate": 9.254901960784315e-06, | |
| "loss": 0.791, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.07827788649706457, | |
| "grad_norm": 22.50664520263672, | |
| "learning_rate": 9.215686274509804e-06, | |
| "loss": 0.7734, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0821917808219178, | |
| "grad_norm": 22.885677337646484, | |
| "learning_rate": 9.176470588235294e-06, | |
| "loss": 0.7812, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08610567514677103, | |
| "grad_norm": 20.37392234802246, | |
| "learning_rate": 9.137254901960785e-06, | |
| "loss": 0.7363, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.09001956947162426, | |
| "grad_norm": 19.406883239746094, | |
| "learning_rate": 9.098039215686276e-06, | |
| "loss": 0.5781, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.09393346379647749, | |
| "grad_norm": 24.332717895507812, | |
| "learning_rate": 9.058823529411765e-06, | |
| "loss": 0.666, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09784735812133072, | |
| "grad_norm": 20.917455673217773, | |
| "learning_rate": 9.019607843137256e-06, | |
| "loss": 0.6504, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10176125244618395, | |
| "grad_norm": 19.47399139404297, | |
| "learning_rate": 8.980392156862746e-06, | |
| "loss": 0.7285, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.10567514677103718, | |
| "grad_norm": 28.136478424072266, | |
| "learning_rate": 8.941176470588237e-06, | |
| "loss": 0.7402, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1095890410958904, | |
| "grad_norm": 18.095579147338867, | |
| "learning_rate": 8.901960784313726e-06, | |
| "loss": 0.6562, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.11350293542074363, | |
| "grad_norm": 18.166412353515625, | |
| "learning_rate": 8.862745098039216e-06, | |
| "loss": 0.6758, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.11741682974559686, | |
| "grad_norm": 22.67608070373535, | |
| "learning_rate": 8.823529411764707e-06, | |
| "loss": 0.6309, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12133072407045009, | |
| "grad_norm": 21.273290634155273, | |
| "learning_rate": 8.784313725490196e-06, | |
| "loss": 0.7637, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.12524461839530332, | |
| "grad_norm": 19.978851318359375, | |
| "learning_rate": 8.745098039215687e-06, | |
| "loss": 0.7432, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.12915851272015655, | |
| "grad_norm": 33.78230667114258, | |
| "learning_rate": 8.705882352941177e-06, | |
| "loss": 1.1113, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.13307240704500978, | |
| "grad_norm": 20.23151969909668, | |
| "learning_rate": 8.666666666666668e-06, | |
| "loss": 0.6758, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.136986301369863, | |
| "grad_norm": 18.375417709350586, | |
| "learning_rate": 8.627450980392157e-06, | |
| "loss": 0.5703, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.14090019569471623, | |
| "grad_norm": 21.369112014770508, | |
| "learning_rate": 8.588235294117647e-06, | |
| "loss": 0.6816, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.14481409001956946, | |
| "grad_norm": 16.71885108947754, | |
| "learning_rate": 8.549019607843138e-06, | |
| "loss": 0.5215, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.1487279843444227, | |
| "grad_norm": 18.679346084594727, | |
| "learning_rate": 8.509803921568627e-06, | |
| "loss": 0.6426, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.15264187866927592, | |
| "grad_norm": 21.49001121520996, | |
| "learning_rate": 8.470588235294118e-06, | |
| "loss": 0.6055, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.15655577299412915, | |
| "grad_norm": 23.428495407104492, | |
| "learning_rate": 8.43137254901961e-06, | |
| "loss": 0.834, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16046966731898238, | |
| "grad_norm": 21.168067932128906, | |
| "learning_rate": 8.392156862745099e-06, | |
| "loss": 0.7236, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.1643835616438356, | |
| "grad_norm": 19.88214111328125, | |
| "learning_rate": 8.35294117647059e-06, | |
| "loss": 0.5801, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.16829745596868884, | |
| "grad_norm": 21.480422973632812, | |
| "learning_rate": 8.31372549019608e-06, | |
| "loss": 0.8047, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.17221135029354206, | |
| "grad_norm": 27.3992977142334, | |
| "learning_rate": 8.274509803921569e-06, | |
| "loss": 0.8438, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1761252446183953, | |
| "grad_norm": 17.163576126098633, | |
| "learning_rate": 8.23529411764706e-06, | |
| "loss": 0.6729, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.18003913894324852, | |
| "grad_norm": 27.425546646118164, | |
| "learning_rate": 8.19607843137255e-06, | |
| "loss": 0.8125, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.18395303326810175, | |
| "grad_norm": 17.309377670288086, | |
| "learning_rate": 8.15686274509804e-06, | |
| "loss": 0.6055, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.18786692759295498, | |
| "grad_norm": 20.072425842285156, | |
| "learning_rate": 8.11764705882353e-06, | |
| "loss": 0.6406, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1917808219178082, | |
| "grad_norm": 29.32526206970215, | |
| "learning_rate": 8.07843137254902e-06, | |
| "loss": 0.8418, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.19569471624266144, | |
| "grad_norm": 19.27393913269043, | |
| "learning_rate": 8.03921568627451e-06, | |
| "loss": 0.6699, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.19960861056751467, | |
| "grad_norm": 20.099166870117188, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.7422, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.2035225048923679, | |
| "grad_norm": 20.619558334350586, | |
| "learning_rate": 7.96078431372549e-06, | |
| "loss": 0.7559, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.20743639921722112, | |
| "grad_norm": 16.634538650512695, | |
| "learning_rate": 7.92156862745098e-06, | |
| "loss": 0.6113, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.21135029354207435, | |
| "grad_norm": 20.62796974182129, | |
| "learning_rate": 7.882352941176471e-06, | |
| "loss": 0.7227, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.21526418786692758, | |
| "grad_norm": 18.67365074157715, | |
| "learning_rate": 7.84313725490196e-06, | |
| "loss": 0.7285, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.2191780821917808, | |
| "grad_norm": 19.195316314697266, | |
| "learning_rate": 7.803921568627452e-06, | |
| "loss": 0.499, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.22309197651663404, | |
| "grad_norm": 19.645790100097656, | |
| "learning_rate": 7.764705882352941e-06, | |
| "loss": 0.7344, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.22700587084148727, | |
| "grad_norm": 17.333480834960938, | |
| "learning_rate": 7.725490196078432e-06, | |
| "loss": 0.6602, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.2309197651663405, | |
| "grad_norm": 17.400426864624023, | |
| "learning_rate": 7.686274509803923e-06, | |
| "loss": 0.6582, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.23483365949119372, | |
| "grad_norm": 16.94071388244629, | |
| "learning_rate": 7.647058823529411e-06, | |
| "loss": 0.6172, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.23874755381604695, | |
| "grad_norm": 20.580204010009766, | |
| "learning_rate": 7.607843137254902e-06, | |
| "loss": 0.6348, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.24266144814090018, | |
| "grad_norm": 18.06707191467285, | |
| "learning_rate": 7.5686274509803925e-06, | |
| "loss": 0.752, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.2465753424657534, | |
| "grad_norm": 21.974361419677734, | |
| "learning_rate": 7.529411764705883e-06, | |
| "loss": 0.6934, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.25048923679060664, | |
| "grad_norm": 18.627838134765625, | |
| "learning_rate": 7.490196078431373e-06, | |
| "loss": 0.666, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.25440313111545987, | |
| "grad_norm": 24.03013038635254, | |
| "learning_rate": 7.450980392156863e-06, | |
| "loss": 0.75, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.2583170254403131, | |
| "grad_norm": 21.04698944091797, | |
| "learning_rate": 7.4117647058823535e-06, | |
| "loss": 0.791, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.2622309197651663, | |
| "grad_norm": 20.169849395751953, | |
| "learning_rate": 7.372549019607845e-06, | |
| "loss": 0.7324, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.26614481409001955, | |
| "grad_norm": 17.215654373168945, | |
| "learning_rate": 7.333333333333333e-06, | |
| "loss": 0.5703, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.2700587084148728, | |
| "grad_norm": 17.34694480895996, | |
| "learning_rate": 7.294117647058823e-06, | |
| "loss": 0.6758, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.273972602739726, | |
| "grad_norm": 18.656417846679688, | |
| "learning_rate": 7.2549019607843145e-06, | |
| "loss": 0.6602, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.27788649706457924, | |
| "grad_norm": 17.223094940185547, | |
| "learning_rate": 7.215686274509805e-06, | |
| "loss": 0.6504, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.28180039138943247, | |
| "grad_norm": 20.023418426513672, | |
| "learning_rate": 7.176470588235295e-06, | |
| "loss": 0.7637, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 19.665098190307617, | |
| "learning_rate": 7.137254901960785e-06, | |
| "loss": 0.7031, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.2896281800391389, | |
| "grad_norm": 16.643753051757812, | |
| "learning_rate": 7.0980392156862755e-06, | |
| "loss": 0.5801, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.29354207436399216, | |
| "grad_norm": 17.616483688354492, | |
| "learning_rate": 7.058823529411766e-06, | |
| "loss": 0.584, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.2974559686888454, | |
| "grad_norm": 18.30911636352539, | |
| "learning_rate": 7.019607843137255e-06, | |
| "loss": 0.7578, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.3013698630136986, | |
| "grad_norm": 23.798246383666992, | |
| "learning_rate": 6.9803921568627454e-06, | |
| "loss": 0.6758, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.30528375733855184, | |
| "grad_norm": 25.015972137451172, | |
| "learning_rate": 6.941176470588236e-06, | |
| "loss": 0.7266, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.30919765166340507, | |
| "grad_norm": 16.107532501220703, | |
| "learning_rate": 6.901960784313726e-06, | |
| "loss": 0.6035, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.3131115459882583, | |
| "grad_norm": 27.97053337097168, | |
| "learning_rate": 6.862745098039216e-06, | |
| "loss": 0.8535, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.31702544031311153, | |
| "grad_norm": 20.14472198486328, | |
| "learning_rate": 6.8235294117647065e-06, | |
| "loss": 0.7461, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.32093933463796476, | |
| "grad_norm": 17.23094367980957, | |
| "learning_rate": 6.784313725490197e-06, | |
| "loss": 0.6113, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.324853228962818, | |
| "grad_norm": 21.04646873474121, | |
| "learning_rate": 6.745098039215687e-06, | |
| "loss": 0.7305, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.3287671232876712, | |
| "grad_norm": 19.706920623779297, | |
| "learning_rate": 6.705882352941176e-06, | |
| "loss": 0.7207, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.33268101761252444, | |
| "grad_norm": 20.11699867248535, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.7207, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.33659491193737767, | |
| "grad_norm": 20.971492767333984, | |
| "learning_rate": 6.627450980392157e-06, | |
| "loss": 0.7441, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.3405088062622309, | |
| "grad_norm": 19.476722717285156, | |
| "learning_rate": 6.588235294117647e-06, | |
| "loss": 0.7188, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.34442270058708413, | |
| "grad_norm": 20.52178382873535, | |
| "learning_rate": 6.549019607843137e-06, | |
| "loss": 0.6719, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.34833659491193736, | |
| "grad_norm": 21.943870544433594, | |
| "learning_rate": 6.5098039215686285e-06, | |
| "loss": 0.7422, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.3522504892367906, | |
| "grad_norm": 19.915830612182617, | |
| "learning_rate": 6.470588235294119e-06, | |
| "loss": 0.627, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3561643835616438, | |
| "grad_norm": 20.40972137451172, | |
| "learning_rate": 6.431372549019609e-06, | |
| "loss": 0.6328, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.36007827788649704, | |
| "grad_norm": 36.07078552246094, | |
| "learning_rate": 6.3921568627450984e-06, | |
| "loss": 1.043, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.3639921722113503, | |
| "grad_norm": 20.237627029418945, | |
| "learning_rate": 6.352941176470589e-06, | |
| "loss": 0.6426, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.3679060665362035, | |
| "grad_norm": 17.273475646972656, | |
| "learning_rate": 6.313725490196079e-06, | |
| "loss": 0.4648, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.37181996086105673, | |
| "grad_norm": 22.85821533203125, | |
| "learning_rate": 6.274509803921569e-06, | |
| "loss": 0.8203, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.37573385518590996, | |
| "grad_norm": 30.95992660522461, | |
| "learning_rate": 6.2352941176470595e-06, | |
| "loss": 0.7773, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.3796477495107632, | |
| "grad_norm": 24.51490592956543, | |
| "learning_rate": 6.19607843137255e-06, | |
| "loss": 0.7188, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.3835616438356164, | |
| "grad_norm": 19.44826889038086, | |
| "learning_rate": 6.15686274509804e-06, | |
| "loss": 0.6318, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.38747553816046965, | |
| "grad_norm": 26.77659034729004, | |
| "learning_rate": 6.11764705882353e-06, | |
| "loss": 0.7363, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.3913894324853229, | |
| "grad_norm": 24.762977600097656, | |
| "learning_rate": 6.07843137254902e-06, | |
| "loss": 0.7041, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3953033268101761, | |
| "grad_norm": 20.80742835998535, | |
| "learning_rate": 6.03921568627451e-06, | |
| "loss": 0.6133, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.39921722113502933, | |
| "grad_norm": 20.675134658813477, | |
| "learning_rate": 6e-06, | |
| "loss": 0.666, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.40313111545988256, | |
| "grad_norm": 21.61725616455078, | |
| "learning_rate": 5.96078431372549e-06, | |
| "loss": 0.6465, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.4070450097847358, | |
| "grad_norm": 20.770998001098633, | |
| "learning_rate": 5.921568627450981e-06, | |
| "loss": 0.748, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.410958904109589, | |
| "grad_norm": 19.81855010986328, | |
| "learning_rate": 5.882352941176471e-06, | |
| "loss": 0.6328, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.41487279843444225, | |
| "grad_norm": 19.529430389404297, | |
| "learning_rate": 5.843137254901961e-06, | |
| "loss": 0.6367, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.4187866927592955, | |
| "grad_norm": 21.23464012145996, | |
| "learning_rate": 5.803921568627452e-06, | |
| "loss": 0.6914, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.4227005870841487, | |
| "grad_norm": 42.98903274536133, | |
| "learning_rate": 5.764705882352941e-06, | |
| "loss": 0.9609, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.42661448140900193, | |
| "grad_norm": 18.04936408996582, | |
| "learning_rate": 5.725490196078431e-06, | |
| "loss": 0.5, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.43052837573385516, | |
| "grad_norm": 30.827211380004883, | |
| "learning_rate": 5.686274509803922e-06, | |
| "loss": 0.8564, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.4344422700587084, | |
| "grad_norm": 30.2517032623291, | |
| "learning_rate": 5.6470588235294125e-06, | |
| "loss": 0.6953, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.4383561643835616, | |
| "grad_norm": 22.330467224121094, | |
| "learning_rate": 5.607843137254903e-06, | |
| "loss": 0.6133, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.44227005870841485, | |
| "grad_norm": 23.358022689819336, | |
| "learning_rate": 5.568627450980393e-06, | |
| "loss": 0.7617, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.4461839530332681, | |
| "grad_norm": 27.15355682373047, | |
| "learning_rate": 5.529411764705883e-06, | |
| "loss": 0.6064, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.4500978473581213, | |
| "grad_norm": 20.863426208496094, | |
| "learning_rate": 5.4901960784313735e-06, | |
| "loss": 0.4629, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.45401174168297453, | |
| "grad_norm": 24.13099479675293, | |
| "learning_rate": 5.450980392156863e-06, | |
| "loss": 0.7461, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.45792563600782776, | |
| "grad_norm": 21.187448501586914, | |
| "learning_rate": 5.411764705882353e-06, | |
| "loss": 0.7383, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.461839530332681, | |
| "grad_norm": 27.121164321899414, | |
| "learning_rate": 5.372549019607843e-06, | |
| "loss": 0.7891, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.4657534246575342, | |
| "grad_norm": 20.777185440063477, | |
| "learning_rate": 5.333333333333334e-06, | |
| "loss": 0.5225, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.46966731898238745, | |
| "grad_norm": 26.442543029785156, | |
| "learning_rate": 5.294117647058824e-06, | |
| "loss": 0.8965, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.4735812133072407, | |
| "grad_norm": 16.87776756286621, | |
| "learning_rate": 5.254901960784314e-06, | |
| "loss": 0.3662, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.4774951076320939, | |
| "grad_norm": 22.01878547668457, | |
| "learning_rate": 5.2156862745098044e-06, | |
| "loss": 0.5732, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.48140900195694714, | |
| "grad_norm": 18.766368865966797, | |
| "learning_rate": 5.176470588235295e-06, | |
| "loss": 0.4912, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.48532289628180036, | |
| "grad_norm": 18.304288864135742, | |
| "learning_rate": 5.137254901960784e-06, | |
| "loss": 0.5469, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.4892367906066536, | |
| "grad_norm": 27.0838565826416, | |
| "learning_rate": 5.098039215686274e-06, | |
| "loss": 0.8457, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.4931506849315068, | |
| "grad_norm": 17.831584930419922, | |
| "learning_rate": 5.058823529411765e-06, | |
| "loss": 0.4189, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.49706457925636005, | |
| "grad_norm": 25.150676727294922, | |
| "learning_rate": 5.019607843137255e-06, | |
| "loss": 0.5967, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.5009784735812133, | |
| "grad_norm": 29.916927337646484, | |
| "learning_rate": 4.980392156862746e-06, | |
| "loss": 0.9102, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.5048923679060665, | |
| "grad_norm": 22.988473892211914, | |
| "learning_rate": 4.941176470588236e-06, | |
| "loss": 0.543, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.5088062622309197, | |
| "grad_norm": 28.76955223083496, | |
| "learning_rate": 4.901960784313726e-06, | |
| "loss": 0.8105, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.512720156555773, | |
| "grad_norm": 29.070444107055664, | |
| "learning_rate": 4.862745098039216e-06, | |
| "loss": 0.5308, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.5166340508806262, | |
| "grad_norm": 41.238914489746094, | |
| "learning_rate": 4.823529411764706e-06, | |
| "loss": 0.998, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.5205479452054794, | |
| "grad_norm": 21.324832916259766, | |
| "learning_rate": 4.784313725490196e-06, | |
| "loss": 0.5146, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.5244618395303327, | |
| "grad_norm": 23.553356170654297, | |
| "learning_rate": 4.745098039215687e-06, | |
| "loss": 0.502, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.5283757338551859, | |
| "grad_norm": 33.09126663208008, | |
| "learning_rate": 4.705882352941177e-06, | |
| "loss": 0.9336, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.5322896281800391, | |
| "grad_norm": 32.21029281616211, | |
| "learning_rate": 4.666666666666667e-06, | |
| "loss": 0.7549, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.5362035225048923, | |
| "grad_norm": 29.427898406982422, | |
| "learning_rate": 4.627450980392157e-06, | |
| "loss": 0.4893, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.5401174168297456, | |
| "grad_norm": 23.003868103027344, | |
| "learning_rate": 4.588235294117647e-06, | |
| "loss": 0.5938, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.5440313111545988, | |
| "grad_norm": 36.66391372680664, | |
| "learning_rate": 4.549019607843138e-06, | |
| "loss": 1.0078, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.547945205479452, | |
| "grad_norm": 24.132999420166016, | |
| "learning_rate": 4.509803921568628e-06, | |
| "loss": 0.5479, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5518590998043053, | |
| "grad_norm": 26.13268280029297, | |
| "learning_rate": 4.4705882352941184e-06, | |
| "loss": 0.5039, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.5557729941291585, | |
| "grad_norm": 36.02132034301758, | |
| "learning_rate": 4.431372549019608e-06, | |
| "loss": 0.916, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.5596868884540117, | |
| "grad_norm": 24.24317741394043, | |
| "learning_rate": 4.392156862745098e-06, | |
| "loss": 0.417, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.5636007827788649, | |
| "grad_norm": 30.09670066833496, | |
| "learning_rate": 4.352941176470588e-06, | |
| "loss": 0.6914, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.5675146771037182, | |
| "grad_norm": 31.203584671020508, | |
| "learning_rate": 4.313725490196079e-06, | |
| "loss": 0.6328, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 25.28211212158203, | |
| "learning_rate": 4.274509803921569e-06, | |
| "loss": 0.6133, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.5753424657534246, | |
| "grad_norm": 37.595375061035156, | |
| "learning_rate": 4.235294117647059e-06, | |
| "loss": 0.8926, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.5792563600782779, | |
| "grad_norm": 32.950469970703125, | |
| "learning_rate": 4.196078431372549e-06, | |
| "loss": 0.8105, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.5831702544031311, | |
| "grad_norm": 27.790950775146484, | |
| "learning_rate": 4.15686274509804e-06, | |
| "loss": 0.7188, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.5870841487279843, | |
| "grad_norm": 25.586286544799805, | |
| "learning_rate": 4.11764705882353e-06, | |
| "loss": 0.4209, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5909980430528375, | |
| "grad_norm": 28.530052185058594, | |
| "learning_rate": 4.07843137254902e-06, | |
| "loss": 0.624, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.5949119373776908, | |
| "grad_norm": 24.636592864990234, | |
| "learning_rate": 4.03921568627451e-06, | |
| "loss": 0.499, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.598825831702544, | |
| "grad_norm": 26.40654754638672, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.3857, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.6027397260273972, | |
| "grad_norm": 34.652889251708984, | |
| "learning_rate": 3.96078431372549e-06, | |
| "loss": 0.7246, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.6066536203522505, | |
| "grad_norm": 47.83692169189453, | |
| "learning_rate": 3.92156862745098e-06, | |
| "loss": 1.0156, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.6105675146771037, | |
| "grad_norm": 28.949697494506836, | |
| "learning_rate": 3.882352941176471e-06, | |
| "loss": 0.5156, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.6144814090019569, | |
| "grad_norm": 22.209552764892578, | |
| "learning_rate": 3.843137254901962e-06, | |
| "loss": 0.3306, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.6183953033268101, | |
| "grad_norm": 35.80719757080078, | |
| "learning_rate": 3.803921568627451e-06, | |
| "loss": 0.9258, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.6223091976516634, | |
| "grad_norm": 21.83152198791504, | |
| "learning_rate": 3.7647058823529414e-06, | |
| "loss": 0.3984, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.6262230919765166, | |
| "grad_norm": 37.10114669799805, | |
| "learning_rate": 3.7254901960784316e-06, | |
| "loss": 0.5264, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6301369863013698, | |
| "grad_norm": 35.30165100097656, | |
| "learning_rate": 3.6862745098039223e-06, | |
| "loss": 0.8574, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.6340508806262231, | |
| "grad_norm": 48.411617279052734, | |
| "learning_rate": 3.6470588235294117e-06, | |
| "loss": 0.9551, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.6379647749510763, | |
| "grad_norm": 35.921085357666016, | |
| "learning_rate": 3.6078431372549024e-06, | |
| "loss": 0.5713, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.6418786692759295, | |
| "grad_norm": 34.80085372924805, | |
| "learning_rate": 3.5686274509803926e-06, | |
| "loss": 0.5977, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.6457925636007827, | |
| "grad_norm": 34.023563385009766, | |
| "learning_rate": 3.529411764705883e-06, | |
| "loss": 0.4863, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.649706457925636, | |
| "grad_norm": 23.1094970703125, | |
| "learning_rate": 3.4901960784313727e-06, | |
| "loss": 0.3701, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.6536203522504892, | |
| "grad_norm": 34.026580810546875, | |
| "learning_rate": 3.450980392156863e-06, | |
| "loss": 0.5391, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.6575342465753424, | |
| "grad_norm": 47.0769157409668, | |
| "learning_rate": 3.4117647058823532e-06, | |
| "loss": 0.9609, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.6614481409001957, | |
| "grad_norm": 32.36403274536133, | |
| "learning_rate": 3.3725490196078435e-06, | |
| "loss": 0.3496, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.6653620352250489, | |
| "grad_norm": 51.04401779174805, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.877, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.6692759295499021, | |
| "grad_norm": 33.55438995361328, | |
| "learning_rate": 3.2941176470588236e-06, | |
| "loss": 0.6279, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.6731898238747553, | |
| "grad_norm": 48.1519889831543, | |
| "learning_rate": 3.2549019607843143e-06, | |
| "loss": 0.6377, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.6771037181996086, | |
| "grad_norm": 32.186336517333984, | |
| "learning_rate": 3.2156862745098045e-06, | |
| "loss": 0.6621, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.6810176125244618, | |
| "grad_norm": 27.279178619384766, | |
| "learning_rate": 3.1764705882352943e-06, | |
| "loss": 0.5645, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.684931506849315, | |
| "grad_norm": 60.810707092285156, | |
| "learning_rate": 3.1372549019607846e-06, | |
| "loss": 1.082, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.6888454011741683, | |
| "grad_norm": 44.514869689941406, | |
| "learning_rate": 3.098039215686275e-06, | |
| "loss": 0.5156, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.6927592954990215, | |
| "grad_norm": 46.69163131713867, | |
| "learning_rate": 3.058823529411765e-06, | |
| "loss": 0.5449, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.6966731898238747, | |
| "grad_norm": 32.7429313659668, | |
| "learning_rate": 3.019607843137255e-06, | |
| "loss": 0.3965, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.700587084148728, | |
| "grad_norm": 40.568519592285156, | |
| "learning_rate": 2.980392156862745e-06, | |
| "loss": 0.5269, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.7045009784735812, | |
| "grad_norm": 42.448726654052734, | |
| "learning_rate": 2.9411764705882355e-06, | |
| "loss": 0.6172, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.7084148727984344, | |
| "grad_norm": 22.704015731811523, | |
| "learning_rate": 2.901960784313726e-06, | |
| "loss": 0.4219, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.7123287671232876, | |
| "grad_norm": 35.70201110839844, | |
| "learning_rate": 2.8627450980392155e-06, | |
| "loss": 0.3955, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.7162426614481409, | |
| "grad_norm": 44.086280822753906, | |
| "learning_rate": 2.8235294117647062e-06, | |
| "loss": 0.8623, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.7201565557729941, | |
| "grad_norm": 100.1460189819336, | |
| "learning_rate": 2.7843137254901965e-06, | |
| "loss": 1.7773, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.7240704500978473, | |
| "grad_norm": 49.51592254638672, | |
| "learning_rate": 2.7450980392156867e-06, | |
| "loss": 0.9736, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.7279843444227005, | |
| "grad_norm": 41.7654914855957, | |
| "learning_rate": 2.7058823529411766e-06, | |
| "loss": 0.9316, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.7318982387475538, | |
| "grad_norm": 49.708526611328125, | |
| "learning_rate": 2.666666666666667e-06, | |
| "loss": 0.7969, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.735812133072407, | |
| "grad_norm": 73.48169708251953, | |
| "learning_rate": 2.627450980392157e-06, | |
| "loss": 1.1836, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.7397260273972602, | |
| "grad_norm": 34.95996856689453, | |
| "learning_rate": 2.5882352941176473e-06, | |
| "loss": 0.3926, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.7436399217221135, | |
| "grad_norm": 29.19251251220703, | |
| "learning_rate": 2.549019607843137e-06, | |
| "loss": 0.4092, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.7475538160469667, | |
| "grad_norm": 38.58152770996094, | |
| "learning_rate": 2.5098039215686274e-06, | |
| "loss": 0.7246, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.7514677103718199, | |
| "grad_norm": 23.995059967041016, | |
| "learning_rate": 2.470588235294118e-06, | |
| "loss": 0.5684, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.7553816046966731, | |
| "grad_norm": 69.17566680908203, | |
| "learning_rate": 2.431372549019608e-06, | |
| "loss": 1.0156, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.7592954990215264, | |
| "grad_norm": 33.91133117675781, | |
| "learning_rate": 2.392156862745098e-06, | |
| "loss": 0.4043, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.7632093933463796, | |
| "grad_norm": 53.28361511230469, | |
| "learning_rate": 2.3529411764705885e-06, | |
| "loss": 1.0801, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.7671232876712328, | |
| "grad_norm": 74.28852081298828, | |
| "learning_rate": 2.3137254901960787e-06, | |
| "loss": 0.9609, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.7710371819960861, | |
| "grad_norm": 30.927936553955078, | |
| "learning_rate": 2.274509803921569e-06, | |
| "loss": 0.4595, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.7749510763209393, | |
| "grad_norm": 39.658348083496094, | |
| "learning_rate": 2.2352941176470592e-06, | |
| "loss": 0.7539, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.7788649706457925, | |
| "grad_norm": 36.83723068237305, | |
| "learning_rate": 2.196078431372549e-06, | |
| "loss": 0.7422, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.7827788649706457, | |
| "grad_norm": 31.887121200561523, | |
| "learning_rate": 2.1568627450980393e-06, | |
| "loss": 0.6953, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.786692759295499, | |
| "grad_norm": 37.30141067504883, | |
| "learning_rate": 2.1176470588235296e-06, | |
| "loss": 0.4375, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.7906066536203522, | |
| "grad_norm": 49.28624725341797, | |
| "learning_rate": 2.07843137254902e-06, | |
| "loss": 1.0371, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.7945205479452054, | |
| "grad_norm": 50.49917984008789, | |
| "learning_rate": 2.03921568627451e-06, | |
| "loss": 0.3906, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.7984344422700587, | |
| "grad_norm": 32.133949279785156, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.5186, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.8023483365949119, | |
| "grad_norm": 34.72405242919922, | |
| "learning_rate": 1.96078431372549e-06, | |
| "loss": 0.4971, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.8062622309197651, | |
| "grad_norm": 22.606107711791992, | |
| "learning_rate": 1.921568627450981e-06, | |
| "loss": 0.2954, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.8101761252446184, | |
| "grad_norm": 36.00542449951172, | |
| "learning_rate": 1.8823529411764707e-06, | |
| "loss": 0.4756, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.8140900195694716, | |
| "grad_norm": 36.495155334472656, | |
| "learning_rate": 1.8431372549019611e-06, | |
| "loss": 0.752, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.8180039138943248, | |
| "grad_norm": 40.29722595214844, | |
| "learning_rate": 1.8039215686274512e-06, | |
| "loss": 0.7129, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.821917808219178, | |
| "grad_norm": 27.014453887939453, | |
| "learning_rate": 1.7647058823529414e-06, | |
| "loss": 0.4629, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.8258317025440313, | |
| "grad_norm": 52.40525436401367, | |
| "learning_rate": 1.7254901960784315e-06, | |
| "loss": 0.6465, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.8297455968688845, | |
| "grad_norm": 58.047672271728516, | |
| "learning_rate": 1.6862745098039217e-06, | |
| "loss": 0.6484, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.8336594911937377, | |
| "grad_norm": 45.495880126953125, | |
| "learning_rate": 1.6470588235294118e-06, | |
| "loss": 0.627, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.837573385518591, | |
| "grad_norm": 69.82907104492188, | |
| "learning_rate": 1.6078431372549023e-06, | |
| "loss": 0.6094, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.8414872798434442, | |
| "grad_norm": 40.72998046875, | |
| "learning_rate": 1.5686274509803923e-06, | |
| "loss": 0.4688, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.8454011741682974, | |
| "grad_norm": 40.783119201660156, | |
| "learning_rate": 1.5294117647058826e-06, | |
| "loss": 0.6045, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.8493150684931506, | |
| "grad_norm": 50.536048889160156, | |
| "learning_rate": 1.4901960784313726e-06, | |
| "loss": 0.668, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.8532289628180039, | |
| "grad_norm": 26.48868179321289, | |
| "learning_rate": 1.450980392156863e-06, | |
| "loss": 0.3135, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 92.84970092773438, | |
| "learning_rate": 1.4117647058823531e-06, | |
| "loss": 0.7402, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.8610567514677103, | |
| "grad_norm": 52.71649169921875, | |
| "learning_rate": 1.3725490196078434e-06, | |
| "loss": 0.7832, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.8649706457925636, | |
| "grad_norm": 49.83753967285156, | |
| "learning_rate": 1.3333333333333334e-06, | |
| "loss": 0.668, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.8688845401174168, | |
| "grad_norm": 31.568586349487305, | |
| "learning_rate": 1.2941176470588237e-06, | |
| "loss": 0.3599, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.87279843444227, | |
| "grad_norm": 49.77619934082031, | |
| "learning_rate": 1.2549019607843137e-06, | |
| "loss": 0.7168, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.8767123287671232, | |
| "grad_norm": 85.63893127441406, | |
| "learning_rate": 1.215686274509804e-06, | |
| "loss": 1.0234, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.8806262230919765, | |
| "grad_norm": 37.95510482788086, | |
| "learning_rate": 1.1764705882352942e-06, | |
| "loss": 0.5215, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.8845401174168297, | |
| "grad_norm": 68.19884490966797, | |
| "learning_rate": 1.1372549019607845e-06, | |
| "loss": 0.8105, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.8884540117416829, | |
| "grad_norm": 50.0982666015625, | |
| "learning_rate": 1.0980392156862745e-06, | |
| "loss": 0.79, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.8923679060665362, | |
| "grad_norm": 101.46347045898438, | |
| "learning_rate": 1.0588235294117648e-06, | |
| "loss": 1.0586, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.8962818003913894, | |
| "grad_norm": 80.32396697998047, | |
| "learning_rate": 1.019607843137255e-06, | |
| "loss": 0.6367, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.9001956947162426, | |
| "grad_norm": 44.84475326538086, | |
| "learning_rate": 9.80392156862745e-07, | |
| "loss": 0.7969, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.9041095890410958, | |
| "grad_norm": 48.397239685058594, | |
| "learning_rate": 9.411764705882353e-07, | |
| "loss": 0.6562, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.9080234833659491, | |
| "grad_norm": 54.06624984741211, | |
| "learning_rate": 9.019607843137256e-07, | |
| "loss": 0.7578, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.9119373776908023, | |
| "grad_norm": 74.30240631103516, | |
| "learning_rate": 8.627450980392157e-07, | |
| "loss": 0.7861, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.9158512720156555, | |
| "grad_norm": 105.15657043457031, | |
| "learning_rate": 8.235294117647059e-07, | |
| "loss": 0.7014, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.9197651663405088, | |
| "grad_norm": 51.52583694458008, | |
| "learning_rate": 7.843137254901962e-07, | |
| "loss": 0.752, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.923679060665362, | |
| "grad_norm": 30.393779754638672, | |
| "learning_rate": 7.450980392156863e-07, | |
| "loss": 0.2056, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.9275929549902152, | |
| "grad_norm": 28.403417587280273, | |
| "learning_rate": 7.058823529411766e-07, | |
| "loss": 0.1951, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.9315068493150684, | |
| "grad_norm": 51.4306640625, | |
| "learning_rate": 6.666666666666667e-07, | |
| "loss": 0.5312, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.9354207436399217, | |
| "grad_norm": 41.486446380615234, | |
| "learning_rate": 6.274509803921569e-07, | |
| "loss": 0.2686, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.9393346379647749, | |
| "grad_norm": 35.38566970825195, | |
| "learning_rate": 5.882352941176471e-07, | |
| "loss": 0.3149, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.9432485322896281, | |
| "grad_norm": 50.63884735107422, | |
| "learning_rate": 5.490196078431373e-07, | |
| "loss": 0.5977, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.9471624266144814, | |
| "grad_norm": 48.22124481201172, | |
| "learning_rate": 5.098039215686275e-07, | |
| "loss": 0.7041, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.9510763209393346, | |
| "grad_norm": 65.34977722167969, | |
| "learning_rate": 4.7058823529411767e-07, | |
| "loss": 1.0, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.9549902152641878, | |
| "grad_norm": 47.49263000488281, | |
| "learning_rate": 4.3137254901960787e-07, | |
| "loss": 0.5352, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.958904109589041, | |
| "grad_norm": 48.74634552001953, | |
| "learning_rate": 3.921568627450981e-07, | |
| "loss": 0.5166, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.9628180039138943, | |
| "grad_norm": 43.316322326660156, | |
| "learning_rate": 3.529411764705883e-07, | |
| "loss": 0.6279, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.9667318982387475, | |
| "grad_norm": 29.874509811401367, | |
| "learning_rate": 3.1372549019607843e-07, | |
| "loss": 0.1953, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.9706457925636007, | |
| "grad_norm": 107.00479888916016, | |
| "learning_rate": 2.7450980392156863e-07, | |
| "loss": 0.9375, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.974559686888454, | |
| "grad_norm": 80.3258285522461, | |
| "learning_rate": 2.3529411764705883e-07, | |
| "loss": 1.0977, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.9784735812133072, | |
| "grad_norm": 48.2215690612793, | |
| "learning_rate": 1.9607843137254904e-07, | |
| "loss": 0.7598, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.9823874755381604, | |
| "grad_norm": 47.73377227783203, | |
| "learning_rate": 1.5686274509803921e-07, | |
| "loss": 0.7207, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.9863013698630136, | |
| "grad_norm": 42.210811614990234, | |
| "learning_rate": 1.1764705882352942e-07, | |
| "loss": 0.5166, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.9902152641878669, | |
| "grad_norm": 46.40138244628906, | |
| "learning_rate": 7.843137254901961e-08, | |
| "loss": 0.5781, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.9941291585127201, | |
| "grad_norm": 54.96934127807617, | |
| "learning_rate": 3.9215686274509804e-08, | |
| "loss": 0.4463, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.9980430528375733, | |
| "grad_norm": 26.624391555786133, | |
| "learning_rate": 0.0, | |
| "loss": 0.4082, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.9980430528375733, | |
| "eval_accuracy": 0.6229508196721312, | |
| "eval_loss": 0.6867475509643555, | |
| "eval_runtime": 6.0663, | |
| "eval_samples_per_second": 10.056, | |
| "eval_steps_per_second": 10.056, | |
| "step": 255 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 255, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |