Instructions to use jeqcho/mdcl_7b_to_3b-qwen25-3b-panda-random_10k-seed44 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jeqcho/mdcl_7b_to_3b-qwen25-3b-panda-random_10k-seed44 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("jeqcho/mdcl_7b_to_3b-qwen25-3b-panda-random_10k-seed44", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Studio
How to use jeqcho/mdcl_7b_to_3b-qwen25-3b-panda-random_10k-seed44 with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for jeqcho/mdcl_7b_to_3b-qwen25-3b-panda-random_10k-seed44 to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for jeqcho/mdcl_7b_to_3b-qwen25-3b-panda-random_10k-seed44 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for jeqcho/mdcl_7b_to_3b-qwen25-3b-panda-random_10k-seed44 to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="jeqcho/mdcl_7b_to_3b-qwen25-3b-panda-random_10k-seed44", max_seq_length=2048, )
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.8901098901098901, | |
| "eval_steps": 500, | |
| "global_step": 135, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006593406593406593, | |
| "grad_norm": 1.51781165599823, | |
| "learning_rate": 0.0, | |
| "loss": 2.6003, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013186813186813187, | |
| "grad_norm": 1.9261507987976074, | |
| "learning_rate": 4e-05, | |
| "loss": 2.9025, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01978021978021978, | |
| "grad_norm": 1.853804588317871, | |
| "learning_rate": 8e-05, | |
| "loss": 2.8561, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.026373626373626374, | |
| "grad_norm": 1.526839256286621, | |
| "learning_rate": 0.00012, | |
| "loss": 2.2888, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03296703296703297, | |
| "grad_norm": 2.0907649993896484, | |
| "learning_rate": 0.00016, | |
| "loss": 2.6181, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03956043956043956, | |
| "grad_norm": 2.8383708000183105, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5613, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.046153846153846156, | |
| "grad_norm": 3.0531911849975586, | |
| "learning_rate": 0.00019955654101995565, | |
| "loss": 1.8836, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05274725274725275, | |
| "grad_norm": 1.9199020862579346, | |
| "learning_rate": 0.00019911308203991133, | |
| "loss": 1.3011, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05934065934065934, | |
| "grad_norm": 0.8820964694023132, | |
| "learning_rate": 0.00019866962305986697, | |
| "loss": 1.2175, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06593406593406594, | |
| "grad_norm": 1.2959258556365967, | |
| "learning_rate": 0.00019822616407982261, | |
| "loss": 1.1792, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07252747252747253, | |
| "grad_norm": 1.0196328163146973, | |
| "learning_rate": 0.00019778270509977829, | |
| "loss": 1.4126, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07912087912087912, | |
| "grad_norm": 0.6727527976036072, | |
| "learning_rate": 0.00019733924611973393, | |
| "loss": 1.3123, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08571428571428572, | |
| "grad_norm": 0.6856306195259094, | |
| "learning_rate": 0.0001968957871396896, | |
| "loss": 1.1368, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09230769230769231, | |
| "grad_norm": 0.5775002241134644, | |
| "learning_rate": 0.00019645232815964525, | |
| "loss": 1.2559, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0989010989010989, | |
| "grad_norm": 0.5077104568481445, | |
| "learning_rate": 0.00019600886917960092, | |
| "loss": 1.0962, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1054945054945055, | |
| "grad_norm": 0.4343227446079254, | |
| "learning_rate": 0.00019556541019955653, | |
| "loss": 1.2124, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.11208791208791209, | |
| "grad_norm": 0.38887736201286316, | |
| "learning_rate": 0.0001951219512195122, | |
| "loss": 1.1039, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.11868131868131868, | |
| "grad_norm": 0.3728462755680084, | |
| "learning_rate": 0.00019467849223946785, | |
| "loss": 1.1092, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12527472527472527, | |
| "grad_norm": 0.4714427888393402, | |
| "learning_rate": 0.00019423503325942352, | |
| "loss": 1.0643, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.13186813186813187, | |
| "grad_norm": 0.37319809198379517, | |
| "learning_rate": 0.00019379157427937917, | |
| "loss": 0.8982, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13846153846153847, | |
| "grad_norm": 0.43793997168540955, | |
| "learning_rate": 0.00019334811529933484, | |
| "loss": 1.0853, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.14505494505494507, | |
| "grad_norm": 0.35266539454460144, | |
| "learning_rate": 0.00019290465631929045, | |
| "loss": 1.0757, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.15164835164835164, | |
| "grad_norm": 0.3485453128814697, | |
| "learning_rate": 0.00019246119733924613, | |
| "loss": 1.0654, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.15824175824175823, | |
| "grad_norm": 0.32909029722213745, | |
| "learning_rate": 0.00019201773835920177, | |
| "loss": 0.9124, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.16483516483516483, | |
| "grad_norm": 0.29112690687179565, | |
| "learning_rate": 0.00019157427937915744, | |
| "loss": 0.998, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.17142857142857143, | |
| "grad_norm": 0.34860149025917053, | |
| "learning_rate": 0.00019113082039911309, | |
| "loss": 0.9398, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.17802197802197803, | |
| "grad_norm": 0.3410319685935974, | |
| "learning_rate": 0.00019068736141906876, | |
| "loss": 1.085, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.18461538461538463, | |
| "grad_norm": 0.27022361755371094, | |
| "learning_rate": 0.0001902439024390244, | |
| "loss": 0.8182, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1912087912087912, | |
| "grad_norm": 0.39027002453804016, | |
| "learning_rate": 0.00018980044345898005, | |
| "loss": 1.0936, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.1978021978021978, | |
| "grad_norm": 0.3809190094470978, | |
| "learning_rate": 0.00018935698447893572, | |
| "loss": 0.9669, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2043956043956044, | |
| "grad_norm": 0.2618960738182068, | |
| "learning_rate": 0.00018891352549889136, | |
| "loss": 0.7325, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.210989010989011, | |
| "grad_norm": 0.31428655982017517, | |
| "learning_rate": 0.00018847006651884703, | |
| "loss": 0.8969, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2175824175824176, | |
| "grad_norm": 0.3208927512168884, | |
| "learning_rate": 0.00018802660753880268, | |
| "loss": 0.9837, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.22417582417582418, | |
| "grad_norm": 0.3479961156845093, | |
| "learning_rate": 0.00018758314855875832, | |
| "loss": 0.9492, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.23076923076923078, | |
| "grad_norm": 0.24484692513942719, | |
| "learning_rate": 0.00018713968957871397, | |
| "loss": 0.8931, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.23736263736263735, | |
| "grad_norm": 0.31913065910339355, | |
| "learning_rate": 0.00018669623059866964, | |
| "loss": 1.0286, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.24395604395604395, | |
| "grad_norm": 0.3971562087535858, | |
| "learning_rate": 0.00018625277161862528, | |
| "loss": 1.1215, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.25054945054945055, | |
| "grad_norm": 0.3638000190258026, | |
| "learning_rate": 0.00018580931263858095, | |
| "loss": 0.9333, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2571428571428571, | |
| "grad_norm": 0.34042876958847046, | |
| "learning_rate": 0.0001853658536585366, | |
| "loss": 1.1182, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.26373626373626374, | |
| "grad_norm": 0.35048097372055054, | |
| "learning_rate": 0.00018492239467849224, | |
| "loss": 1.0188, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2703296703296703, | |
| "grad_norm": 0.3047362267971039, | |
| "learning_rate": 0.0001844789356984479, | |
| "loss": 1.1008, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.27692307692307694, | |
| "grad_norm": 0.24302105605602264, | |
| "learning_rate": 0.00018403547671840356, | |
| "loss": 0.8789, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2835164835164835, | |
| "grad_norm": 0.32716572284698486, | |
| "learning_rate": 0.0001835920177383592, | |
| "loss": 0.8929, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.29010989010989013, | |
| "grad_norm": 0.24855059385299683, | |
| "learning_rate": 0.00018314855875831487, | |
| "loss": 0.7146, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2967032967032967, | |
| "grad_norm": 0.2590542137622833, | |
| "learning_rate": 0.00018270509977827052, | |
| "loss": 0.9198, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3032967032967033, | |
| "grad_norm": 0.32804593443870544, | |
| "learning_rate": 0.00018226164079822616, | |
| "loss": 0.895, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3098901098901099, | |
| "grad_norm": 0.3551070988178253, | |
| "learning_rate": 0.00018181818181818183, | |
| "loss": 0.9866, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.31648351648351647, | |
| "grad_norm": 0.2825017273426056, | |
| "learning_rate": 0.00018137472283813748, | |
| "loss": 0.8555, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3230769230769231, | |
| "grad_norm": 0.2646731436252594, | |
| "learning_rate": 0.00018093126385809312, | |
| "loss": 0.9711, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.32967032967032966, | |
| "grad_norm": 0.33243000507354736, | |
| "learning_rate": 0.0001804878048780488, | |
| "loss": 0.9449, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3362637362637363, | |
| "grad_norm": 0.385030061006546, | |
| "learning_rate": 0.00018004434589800444, | |
| "loss": 0.9101, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.34285714285714286, | |
| "grad_norm": 0.31159284710884094, | |
| "learning_rate": 0.00017960088691796008, | |
| "loss": 0.8401, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.34945054945054943, | |
| "grad_norm": 0.2921944558620453, | |
| "learning_rate": 0.00017915742793791575, | |
| "loss": 1.0733, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.35604395604395606, | |
| "grad_norm": 0.2874985337257385, | |
| "learning_rate": 0.0001787139689578714, | |
| "loss": 0.8802, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.3626373626373626, | |
| "grad_norm": 0.31257903575897217, | |
| "learning_rate": 0.00017827050997782707, | |
| "loss": 1.1215, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.36923076923076925, | |
| "grad_norm": 0.2742151916027069, | |
| "learning_rate": 0.00017782705099778271, | |
| "loss": 0.9605, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.3758241758241758, | |
| "grad_norm": 0.32726484537124634, | |
| "learning_rate": 0.00017738359201773839, | |
| "loss": 1.0408, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.3824175824175824, | |
| "grad_norm": 0.3544639050960541, | |
| "learning_rate": 0.000176940133037694, | |
| "loss": 1.0483, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.389010989010989, | |
| "grad_norm": 0.3291817009449005, | |
| "learning_rate": 0.00017649667405764967, | |
| "loss": 1.0099, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.3956043956043956, | |
| "grad_norm": 0.2948567271232605, | |
| "learning_rate": 0.00017605321507760532, | |
| "loss": 0.7214, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4021978021978022, | |
| "grad_norm": 0.3465343713760376, | |
| "learning_rate": 0.000175609756097561, | |
| "loss": 0.8914, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.4087912087912088, | |
| "grad_norm": 0.294916033744812, | |
| "learning_rate": 0.00017516629711751663, | |
| "loss": 0.9002, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.4153846153846154, | |
| "grad_norm": 0.2645125687122345, | |
| "learning_rate": 0.0001747228381374723, | |
| "loss": 0.9807, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.421978021978022, | |
| "grad_norm": 0.26566192507743835, | |
| "learning_rate": 0.00017427937915742792, | |
| "loss": 1.0263, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": 0.3932898938655853, | |
| "learning_rate": 0.0001738359201773836, | |
| "loss": 0.9964, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.4351648351648352, | |
| "grad_norm": 0.3968732953071594, | |
| "learning_rate": 0.00017339246119733924, | |
| "loss": 0.905, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.44175824175824174, | |
| "grad_norm": 0.2582176923751831, | |
| "learning_rate": 0.0001729490022172949, | |
| "loss": 0.762, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.44835164835164837, | |
| "grad_norm": 0.3497701585292816, | |
| "learning_rate": 0.00017250554323725056, | |
| "loss": 1.2204, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.45494505494505494, | |
| "grad_norm": 0.21835869550704956, | |
| "learning_rate": 0.00017206208425720623, | |
| "loss": 0.8432, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.46153846153846156, | |
| "grad_norm": 0.4241009056568146, | |
| "learning_rate": 0.00017161862527716187, | |
| "loss": 1.1661, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.46813186813186813, | |
| "grad_norm": 0.29903969168663025, | |
| "learning_rate": 0.00017117516629711752, | |
| "loss": 0.9637, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.4747252747252747, | |
| "grad_norm": 0.32923105359077454, | |
| "learning_rate": 0.0001707317073170732, | |
| "loss": 0.9613, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.48131868131868133, | |
| "grad_norm": 0.33389630913734436, | |
| "learning_rate": 0.00017028824833702883, | |
| "loss": 0.8119, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.4879120879120879, | |
| "grad_norm": 0.2928239703178406, | |
| "learning_rate": 0.0001698447893569845, | |
| "loss": 1.1114, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.4945054945054945, | |
| "grad_norm": 0.4275268316268921, | |
| "learning_rate": 0.00016940133037694015, | |
| "loss": 1.0924, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5010989010989011, | |
| "grad_norm": 0.252409964799881, | |
| "learning_rate": 0.00016895787139689582, | |
| "loss": 0.9047, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.5076923076923077, | |
| "grad_norm": 0.27643951773643494, | |
| "learning_rate": 0.00016851441241685144, | |
| "loss": 0.9516, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.5142857142857142, | |
| "grad_norm": 0.31490686535835266, | |
| "learning_rate": 0.0001680709534368071, | |
| "loss": 0.9629, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.5208791208791209, | |
| "grad_norm": 0.28956061601638794, | |
| "learning_rate": 0.00016762749445676275, | |
| "loss": 1.073, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.5274725274725275, | |
| "grad_norm": 0.39840641617774963, | |
| "learning_rate": 0.00016718403547671842, | |
| "loss": 1.0587, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5340659340659341, | |
| "grad_norm": 0.3193679749965668, | |
| "learning_rate": 0.00016674057649667407, | |
| "loss": 0.9033, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.5406593406593406, | |
| "grad_norm": 0.29296162724494934, | |
| "learning_rate": 0.00016629711751662974, | |
| "loss": 0.9926, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.5472527472527473, | |
| "grad_norm": 0.25819483399391174, | |
| "learning_rate": 0.00016585365853658536, | |
| "loss": 0.9406, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.5538461538461539, | |
| "grad_norm": 0.3168943226337433, | |
| "learning_rate": 0.00016541019955654103, | |
| "loss": 0.8069, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.5604395604395604, | |
| "grad_norm": 0.30880314111709595, | |
| "learning_rate": 0.00016496674057649667, | |
| "loss": 0.872, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.567032967032967, | |
| "grad_norm": 0.3081277310848236, | |
| "learning_rate": 0.00016452328159645234, | |
| "loss": 1.0051, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.5736263736263736, | |
| "grad_norm": 0.41150379180908203, | |
| "learning_rate": 0.000164079822616408, | |
| "loss": 0.9577, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.5802197802197803, | |
| "grad_norm": 0.3497859239578247, | |
| "learning_rate": 0.00016363636363636366, | |
| "loss": 0.9117, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.5868131868131868, | |
| "grad_norm": 0.24770864844322205, | |
| "learning_rate": 0.0001631929046563193, | |
| "loss": 0.8452, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.5934065934065934, | |
| "grad_norm": 0.2897774875164032, | |
| "learning_rate": 0.00016274944567627495, | |
| "loss": 0.9269, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.2963946759700775, | |
| "learning_rate": 0.0001623059866962306, | |
| "loss": 0.883, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.6065934065934065, | |
| "grad_norm": 0.35474881529808044, | |
| "learning_rate": 0.00016186252771618626, | |
| "loss": 1.0333, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.6131868131868132, | |
| "grad_norm": 0.3128604292869568, | |
| "learning_rate": 0.0001614190687361419, | |
| "loss": 0.8813, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.6197802197802198, | |
| "grad_norm": 0.3175148069858551, | |
| "learning_rate": 0.00016097560975609758, | |
| "loss": 0.9218, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.6263736263736264, | |
| "grad_norm": 0.30592796206474304, | |
| "learning_rate": 0.00016053215077605322, | |
| "loss": 1.0093, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.6329670329670329, | |
| "grad_norm": 0.30979204177856445, | |
| "learning_rate": 0.00016008869179600887, | |
| "loss": 1.1087, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.6395604395604395, | |
| "grad_norm": 0.3170197010040283, | |
| "learning_rate": 0.00015964523281596454, | |
| "loss": 1.0377, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.6461538461538462, | |
| "grad_norm": 0.34211069345474243, | |
| "learning_rate": 0.00015920177383592018, | |
| "loss": 1.1252, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.6527472527472528, | |
| "grad_norm": 0.34838294982910156, | |
| "learning_rate": 0.00015875831485587586, | |
| "loss": 0.9858, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.6593406593406593, | |
| "grad_norm": 0.3975377082824707, | |
| "learning_rate": 0.0001583148558758315, | |
| "loss": 1.041, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6659340659340659, | |
| "grad_norm": 0.33024221658706665, | |
| "learning_rate": 0.00015787139689578714, | |
| "loss": 0.9925, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.6725274725274726, | |
| "grad_norm": 0.3557412922382355, | |
| "learning_rate": 0.0001574279379157428, | |
| "loss": 1.077, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.6791208791208792, | |
| "grad_norm": 0.3489350378513336, | |
| "learning_rate": 0.00015698447893569846, | |
| "loss": 1.1104, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.6857142857142857, | |
| "grad_norm": 0.3904794454574585, | |
| "learning_rate": 0.0001565410199556541, | |
| "loss": 0.816, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.6923076923076923, | |
| "grad_norm": 0.28544628620147705, | |
| "learning_rate": 0.00015609756097560978, | |
| "loss": 0.8572, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.6989010989010989, | |
| "grad_norm": 0.2343568354845047, | |
| "learning_rate": 0.00015565410199556542, | |
| "loss": 0.8888, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.7054945054945055, | |
| "grad_norm": 0.25775396823883057, | |
| "learning_rate": 0.00015521064301552106, | |
| "loss": 0.7646, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.7120879120879121, | |
| "grad_norm": 0.32354897260665894, | |
| "learning_rate": 0.0001547671840354767, | |
| "loss": 0.8485, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.7186813186813187, | |
| "grad_norm": 0.2608407735824585, | |
| "learning_rate": 0.00015432372505543238, | |
| "loss": 0.8236, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.7252747252747253, | |
| "grad_norm": 0.2987760603427887, | |
| "learning_rate": 0.00015388026607538802, | |
| "loss": 0.9411, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.7318681318681318, | |
| "grad_norm": 0.3875117599964142, | |
| "learning_rate": 0.0001534368070953437, | |
| "loss": 0.8312, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.7384615384615385, | |
| "grad_norm": 0.3331878185272217, | |
| "learning_rate": 0.00015299334811529934, | |
| "loss": 0.94, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.7450549450549451, | |
| "grad_norm": 0.36396199464797974, | |
| "learning_rate": 0.00015254988913525498, | |
| "loss": 0.8921, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.7516483516483516, | |
| "grad_norm": 0.2830229103565216, | |
| "learning_rate": 0.00015210643015521066, | |
| "loss": 0.9608, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.7582417582417582, | |
| "grad_norm": 0.27632445096969604, | |
| "learning_rate": 0.0001516629711751663, | |
| "loss": 0.9802, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.7648351648351648, | |
| "grad_norm": 0.3065943717956543, | |
| "learning_rate": 0.00015121951219512197, | |
| "loss": 0.9039, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.7714285714285715, | |
| "grad_norm": 0.27498388290405273, | |
| "learning_rate": 0.00015077605321507762, | |
| "loss": 0.6538, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.778021978021978, | |
| "grad_norm": 0.29651233553886414, | |
| "learning_rate": 0.0001503325942350333, | |
| "loss": 0.7523, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.7846153846153846, | |
| "grad_norm": 0.34246179461479187, | |
| "learning_rate": 0.0001498891352549889, | |
| "loss": 0.9063, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.7912087912087912, | |
| "grad_norm": 0.2942260801792145, | |
| "learning_rate": 0.00014944567627494458, | |
| "loss": 0.9174, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7978021978021979, | |
| "grad_norm": 0.35497164726257324, | |
| "learning_rate": 0.00014900221729490022, | |
| "loss": 1.061, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.8043956043956044, | |
| "grad_norm": 0.31248870491981506, | |
| "learning_rate": 0.0001485587583148559, | |
| "loss": 0.5611, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.810989010989011, | |
| "grad_norm": 0.3703018128871918, | |
| "learning_rate": 0.00014811529933481154, | |
| "loss": 0.994, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.8175824175824176, | |
| "grad_norm": 0.30003687739372253, | |
| "learning_rate": 0.0001476718403547672, | |
| "loss": 1.0005, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.8241758241758241, | |
| "grad_norm": 0.3337390720844269, | |
| "learning_rate": 0.00014722838137472282, | |
| "loss": 0.9926, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.8307692307692308, | |
| "grad_norm": 0.3595570921897888, | |
| "learning_rate": 0.0001467849223946785, | |
| "loss": 0.9224, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.8373626373626374, | |
| "grad_norm": 0.32574501633644104, | |
| "learning_rate": 0.00014634146341463414, | |
| "loss": 0.925, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.843956043956044, | |
| "grad_norm": 0.3348236382007599, | |
| "learning_rate": 0.0001458980044345898, | |
| "loss": 1.0227, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.8505494505494505, | |
| "grad_norm": 0.4262445569038391, | |
| "learning_rate": 0.00014545454545454546, | |
| "loss": 1.1669, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 0.2437465935945511, | |
| "learning_rate": 0.00014501108647450113, | |
| "loss": 0.9765, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.8637362637362638, | |
| "grad_norm": 0.2993992865085602, | |
| "learning_rate": 0.00014456762749445675, | |
| "loss": 0.9402, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.8703296703296703, | |
| "grad_norm": 0.31676241755485535, | |
| "learning_rate": 0.00014412416851441242, | |
| "loss": 0.7698, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.8769230769230769, | |
| "grad_norm": 0.3266180753707886, | |
| "learning_rate": 0.00014368070953436806, | |
| "loss": 0.9382, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.8835164835164835, | |
| "grad_norm": 0.5359867811203003, | |
| "learning_rate": 0.00014323725055432373, | |
| "loss": 1.1008, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.8901098901098901, | |
| "grad_norm": 0.3537139892578125, | |
| "learning_rate": 0.00014279379157427938, | |
| "loss": 1.0479, | |
| "step": 135 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 456, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 15, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.2213320240562176e+16, | |
| "train_batch_size": 22, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |