boris commited on
Commit
6098712
1 Parent(s): a996fb3

New model from https://wandb.ai/wandb/huggingtweets/runs/ozw5h8lm

Browse files

Files changed (5) hide show
  1. README.md +7 -7
  2. config.json +3 -2
  3. pytorch_model.bin +2 -2
  4. tokenizer.json +0 -0
  5. training_args.bin +2 -2
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  language: en
3
- thumbnail: https://www.huggingtweets.com/cnn/1629573785382/predictions.png
4
  tags:
5
  - huggingtweets
6
  widget:
@@ -43,19 +43,19 @@ The model was trained on tweets from CNN.
43
  | Data | CNN |
44
  | --- | --- |
45
  | Tweets downloaded | 3250 |
46
- | Retweets | 144 |
47
- | Short tweets | 18 |
48
- | Tweets kept | 3088 |
49
 
50
- [Explore the data](https://wandb.ai/wandb/huggingtweets/runs/3w3wwhg0/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 @cnn's tweets.
55
 
56
- Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/2y59172n) for full transparency and reproducibility.
57
 
58
- At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/2y59172n/artifacts) is logged and versioned.
59
 
60
  ## How to use
61
 
1
  ---
2
  language: en
3
+ thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
4
  tags:
5
  - huggingtweets
6
  widget:
43
  | Data | CNN |
44
  | --- | --- |
45
  | Tweets downloaded | 3250 |
46
+ | Retweets | 16 |
47
+ | Short tweets | 5 |
48
+ | Tweets kept | 3229 |
49
 
50
+ [Explore the data](https://wandb.ai/wandb/huggingtweets/runs/q0qwmbzx/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 @cnn's tweets.
55
 
56
+ Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/ozw5h8lm) for full transparency and reproducibility.
57
 
58
+ At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/ozw5h8lm/artifacts) is logged and versioned.
59
 
60
  ## How to use
61
 
config.json CHANGED
@@ -8,7 +8,6 @@
8
  "bos_token_id": 50256,
9
  "embd_pdrop": 0.1,
10
  "eos_token_id": 50256,
11
- "gradient_checkpointing": false,
12
  "initializer_range": 0.02,
13
  "layer_norm_epsilon": 1e-05,
14
  "model_type": "gpt2",
@@ -18,7 +17,9 @@
18
  "n_inner": null,
19
  "n_layer": 12,
20
  "n_positions": 1024,
 
21
  "resid_pdrop": 0.1,
 
22
  "scale_attn_weights": true,
23
  "summary_activation": null,
24
  "summary_first_dropout": 0.1,
@@ -36,7 +37,7 @@
36
  }
37
  },
38
  "torch_dtype": "float32",
39
- "transformers_version": "4.9.2",
40
  "use_cache": true,
41
  "vocab_size": 50257
42
  }
8
  "bos_token_id": 50256,
9
  "embd_pdrop": 0.1,
10
  "eos_token_id": 50256,
 
11
  "initializer_range": 0.02,
12
  "layer_norm_epsilon": 1e-05,
13
  "model_type": "gpt2",
17
  "n_inner": null,
18
  "n_layer": 12,
19
  "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
  "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
  "scale_attn_weights": true,
24
  "summary_activation": null,
25
  "summary_first_dropout": 0.1,
37
  }
38
  },
39
  "torch_dtype": "float32",
40
+ "transformers_version": "4.17.0",
41
  "use_cache": true,
42
  "vocab_size": 50257
43
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:220352e4735db73437737f657719f2b678a830584bee93571a6b34de9820b967
3
- size 510403817
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae3d42c2c9cc8f144a84f130f7dfd62d9554aeda061a77e9b73e249643a7319b
3
+ size 510404393
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f139ab85f8c6915b3cf54ca42dd8bdff5f6a6c27694b8b2af4ac88559d70b94
3
- size 2671
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1274365d4ad369f567283b54c707ffcadc8c3979b97adc08da235e4d8e081fe
3
+ size 2991