boris commited on
Commit
a1ed76e
1 Parent(s): accec01

New model from https://wandb.ai/wandb/huggingtweets/runs/p2md0wva

Browse files
Files changed (3) hide show
  1. README.md +6 -6
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -42,20 +42,20 @@ The model was trained on tweets from Pratham & Insha & Savio Martin ⚡️.
42
 
43
  | Data | Pratham | Insha | Savio Martin ⚡️ |
44
  | --- | --- | --- | --- |
45
- | Tweets downloaded | 3246 | 3249 | 3246 |
46
- | Retweets | 460 | 24 | 118 |
47
  | Short tweets | 317 | 457 | 201 |
48
- | Tweets kept | 2469 | 2768 | 2927 |
49
 
50
- [Explore the data](https://wandb.ai/wandb/huggingtweets/runs/26px96pn/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
51
 
52
  ## Training procedure
53
 
54
  The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @insharamin-prathkum-saviomartin7's tweets.
55
 
56
- Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/2i7imlo0) for full transparency and reproducibility.
57
 
58
- At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/2i7imlo0/artifacts) is logged and versioned.
59
 
60
  ## How to use
61
 
42
 
43
  | Data | Pratham | Insha | Savio Martin ⚡️ |
44
  | --- | --- | --- | --- |
45
+ | Tweets downloaded | 3246 | 3249 | 3249 |
46
+ | Retweets | 461 | 24 | 118 |
47
  | Short tweets | 317 | 457 | 201 |
48
+ | Tweets kept | 2468 | 2768 | 2930 |
49
 
50
+ [Explore the data](https://wandb.ai/wandb/huggingtweets/runs/o7jfvmhp/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
51
 
52
  ## Training procedure
53
 
54
  The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @insharamin-prathkum-saviomartin7's tweets.
55
 
56
+ Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/p2md0wva) for full transparency and reproducibility.
57
 
58
+ At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/p2md0wva/artifacts) is logged and versioned.
59
 
60
  ## How to use
61
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9fd01816edc1fbb37e4eb0548ebfa5d2c5bd9479c8511e4d7a14dc7ab26b0d9
3
  size 510403817
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19ff6e2792f1bfd96e310ee7b3bb2ffe74aae96af243c9f6892a2e167bb4c99c
3
  size 510403817
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26a2ed9090af3e12484f98f1c935e459b374458770c29e0e6165b94966caedf4
3
  size 2863
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c64e0280a5d13c9ef4724d047940820a7f1d6d1d85d88a0d3b58193c05a0a6b5
3
  size 2863