lvwerra_distilbert-imdb
lvwerra · View on Hugging Face ↗
Model card
The complete upstream card, rendered from this payload's README.md — the same hash-verified bytes the torrent distributes. Images and off-site links are removed; the original card on Hugging Face carries them.
license: apache-2.0 tags:
- generated_from_trainer datasets:
- imdb metrics:
- accuracy model-index:
- name: distilbert-imdb
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: imdb
type: imdb
args: plain_text
metrics:
- name: Accuracy type: accuracy value: 0.928
- task:
name: Text Classification
type: text-classification
dataset:
name: imdb
type: imdb
args: plain_text
metrics:
distilbert-imdb
This model is a fine-tuned version of distilbert-base-uncased on the imdb dataset (training notebook is here). It achieves the following results on the evaluation set:
- Loss: 0.1903
- Accuracy: 0.928
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2195 | 1.0 | 1563 | 0.1903 | 0.928 |
Framework versions
- Transformers 4.15.0
- Pytorch 1.10.0+cu111
- Datasets 1.17.0
- Tokenizers 0.10.3
Magnet link
Opens the swarm directly in your torrent client — no file download needed. Copy-paste works too:
magnet:?xt=urn:btih:10344ae6863711fe57f307ffa9698d189107b506&dn=lvwerra_distilbert-imdbOpen magnet in torrent client · infohash 10344ae6863711fe57f307ffa9698d189107b506
Files & hashes
| Path | Size | sha1 | sha256 |
|---|---|---|---|
| README.md | 1.6 KB (1,685 B) | aa38d83d891fb3b87d04ed120b02b3752d1a75b5 | 9a440314bf40f0789dcea395f841fd88668a4db2ec59738cf937e6d631a61160 |
| config.json | 735 B (735 B) | 81562f1a7542eedebf12f7425aa77395abf21120 | 60b10704f12149b4001611a16b388d88b65d6b2f0566f55b5503d7185c9848ad |
| distilbert-imdb-training.ipynb | 6.3 KB (6,462 B) | 302f538d82ad93c3e4b5dcc26e4c8218c770277c | e053bb80d6755d6139926b7c6c23da5e45e92328edfafb5485a92f6eebca0bf4 |
| pytorch_model.bin | 255.5 MB (267,860,081 B) | 07f97cce6cd13286e94d5a28674720bce41b6b86 | 2ede11721eca562deedaf262b9ef2f504342ec76720e142f41fed7f062577035 |
| runs/Dec30_16-56-30_3603c37d6fc6/1640883891.1614847/events.out.tfevents.1640883891.3603c37d6fc6.75.1 | 4.6 KB (4,719 B) | 9a2870ef3dfb23edc74e662623addda3ae35cdf9 | a5828c9712eeff98c7a9fc4e28a8972cbed5efda0f3f53407c615a11ef3266ae |
| runs/Dec30_16-56-30_3603c37d6fc6/events.out.tfevents.1640883891.3603c37d6fc6.75.0 | 3.1 KB (3,148 B) | 5078113190b4c218dbc2557d624319ea35a1345b | 3748dfd52722add80a990cb076ac7f5443eb3be26100c6f678e33d593b8ed410 |
| runs/Dec30_17-07-51_3603c37d6fc6/1640884114.6640563/events.out.tfevents.1640884114.3603c37d6fc6.75.3 | 4.6 KB (4,725 B) | e914d90956415f5a954fc3d3e81ec6ea3cc2249a | 359761f26cd8267aa7523c747a5e68214abc511f7fd54f6cdef4d5008abe28d2 |
| runs/Dec30_17-07-51_3603c37d6fc6/1640884728.1701791/events.out.tfevents.1640884728.3603c37d6fc6.75.4 | 4.6 KB (4,725 B) | 43d98c8e642fc841e4f3461861a703246e417b95 | cf81463fb3b182b6bd62de92e7c75c1c5d7a6c9528c869e00fe3443672f88c7f |
| runs/Dec30_17-07-51_3603c37d6fc6/events.out.tfevents.1640884114.3603c37d6fc6.75.2 | 6.2 KB (6,360 B) | 720a40ba750428f9c6509895b0325276d0adafcd | 35112ddd1b9055861ee50ff374913501a006a37eaa14ee37b514bfc8706c53c6 |
| runs/Dec30_17-18-53_3603c37d6fc6/1640884742.6121824/events.out.tfevents.1640884742.3603c37d6fc6.75.6 | 4.6 KB (4,722 B) | 200cbbe63d9356a8412616e02da8fc71721054d8 | 82b8ec666b46f91f186989a2cf3a1ee636327ea42a811b2c769a9297d9a56814 |
| runs/Dec30_17-18-53_3603c37d6fc6/events.out.tfevents.1640884742.3603c37d6fc6.75.5 | 4.2 KB (4,349 B) | 072a643e085399a0ed44d6d8427cf41335e20ef3 | ae7d69ce92f6cae169cb738ebe8881bc095e7747b34c914134b8b95ea258523c |
| special_tokens_map.json | 112 B (112 B) | e7b0375001f109a6b8873d756ad4f7bbb15fbaa5 | 303df45a03609e4ead04bc3dc1536d0ab19b5358db685b6f3da123d05ec200e3 |
| tokenizer.json | 455.2 KB (466,132 B) | f0d8ac1487175807ad7b02455ee4744aae51f288 | 99e552efd3b68340ef1b1106ea152526659a9c525992f008fe4c182a5a587234 |
| tokenizer_config.json | 333 B (333 B) | 4036a93f3f40a3f79923bb26f5e9a13e0b2d1687 | 19061b90828c2f97596b3b41f9d3b961cd51619d282aba2856dcb77ac4202a52 |
| training_args.bin | 2.9 KB (2,927 B) | a8fd83f01e23269cd5ee97d0612720a94b485ce6 | a78ec6374b76a0152998650386f046a58e63000b66f7fdfbe249fd32c35b8a7a |
| vocab.txt | 226.1 KB (231,508 B) | fb140275c155a9c7c5a3b3e0e77a9e839594a938 | 07eced375cec144d27c900241f3e339478dec958f92fddbc551f295c992038a3 |
Cite this release
- Canonical URL
- https://aiseedbank.org/models/lvwerra_distilbert-imdb/
- Slug
- lvwerra_distilbert-imdb
- Infohash
- 10344ae6863711fe57f307ffa9698d189107b506
- License
- apache-2.0
- Signing key fingerprint
- 85a3b32c3712427b
Every file carries a locally computed sha256 — verify a download against the signed sums: lvwerra_distilbert-imdb.SHA256SUMS (+ minisign signature).
Provenance
| Upstream repository | lvwerra/distilbert-imdb |
|---|---|
| Revision (pinned) | 0fc02cd68445b599a9cb2da2368050e7fb31d29a |
| Fetched at | 2026-09-04T01:41:14Z |
| License at fetch | apache-2.0 |
| Snapshot tool | huggingface · seedbank 0.1.0 |
Trackers
- udp://announce.aitorrent.org:6969/announce
- http://announce.aitorrent.org:7070/announce
- udp://announce2.aitorrent.org:6970/announce
- http://announce2.aitorrent.org:7071/announce
- udp://tracker.opentrackr.org:1337/announce
- udp://open.demonii.com:1337/announce
- udp://open.stealth.si:80/announce
- udp://exodus.desync.com:6969/announce
- udp://tracker.torrent.eu.org:451/announce
✓ verified · rehash-vs-hf-metadata at 2026-09-04T01:41:18Z
apache-2.0256.2 MB (268,602,723 bytes)transformerspytorchtensorboarddistilberttext-classificationgenerated_from_trainermodel-indextext-embeddings-inferenceendpoints_compatible