boris commited on
Commit
c7ce451
1 Parent(s): d0ac70f

New model from https://wandb.ai/wandb/huggingtweets/runs/1gjmi5b8

Browse files
README.md CHANGED
@@ -42,20 +42,20 @@ The model was trained on tweets from Alexandria Ocasio-Cortez.
42
 
43
  | Data | Alexandria Ocasio-Cortez |
44
  | --- | --- |
45
- | Tweets downloaded | 3246 |
46
- | Retweets | 1206 |
47
- | Short tweets | 137 |
48
- | Tweets kept | 1903 |
49
 
50
- [Explore the data](https://wandb.ai/wandb/huggingtweets/runs/2ephbfgv/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 @aoc's tweets.
55
 
56
- Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/1n5unoap) for full transparency and reproducibility.
57
 
58
- At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/1n5unoap/artifacts) is logged and versioned.
59
 
60
  ## How to use
61
 
 
42
 
43
  | Data | Alexandria Ocasio-Cortez |
44
  | --- | --- |
45
+ | Tweets downloaded | 3221 |
46
+ | Retweets | 1253 |
47
+ | Short tweets | 126 |
48
+ | Tweets kept | 1842 |
49
 
50
+ [Explore the data](https://wandb.ai/wandb/huggingtweets/runs/3i05suuv/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 @aoc's tweets.
55
 
56
+ Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/1gjmi5b8) for full transparency and reproducibility.
57
 
58
+ At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/1gjmi5b8/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,
@@ -35,7 +36,8 @@
35
  "top_p": 0.95
36
  }
37
  },
38
- "transformers_version": "4.6.1",
 
39
  "use_cache": true,
40
  "vocab_size": 50257
41
  }
 
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,
 
36
  "top_p": 0.95
37
  }
38
  },
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.20.1",
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 sha256:9bd5449a9b52d03e3909ab6fec3425e47ddb938f5ab67a4a8f43b328103554bd
3
- size 510408315
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e410137781a3fb4416d7b65d76fb40d77d65a4c02ac6adddc89a5859d03ee5f
3
+ size 510396521
special_tokens_map.json CHANGED
@@ -1 +1,5 @@
1
- {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1 +1,10 @@
1
- {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2"}
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1024,
6
+ "name_or_path": "gpt2",
7
+ "special_tokens_map_file": null,
8
+ "tokenizer_class": "GPT2Tokenizer",
9
+ "unk_token": "<|endoftext|>"
10
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8975b79004c44304ff905bf2d90a957983eb48ae4c1c63cdf50b261ad1db563
3
- size 2415
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d68355eb2bd3c332d800ec9827a39e8c55cd156546ecf75b67eceff51540dc8
3
+ size 3311