zari commited on
Commit
c019cff
1 Parent(s): 0e2b427
Files changed (3) hide show
  1. README.md +61 -0
  2. config.json +46 -0
  3. pytorch_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ datasets:
4
+ - null
5
+ model_index:
6
+ - name: my-awesome-model
7
+ results:
8
+ - task:
9
+ name: Causal Language Modeling
10
+ type: text-generation
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # my-awesome-model
17
+
18
+ This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 3.4356
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 2e-05
40
+ - train_batch_size: 8
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 3.0
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:----:|:---------------:|
51
+ | No log | 1.0 | 91 | 3.4934 |
52
+ | No log | 2.0 | 182 | 3.4451 |
53
+ | No log | 3.0 | 273 | 3.4356 |
54
+
55
+
56
+ ### Framework versions
57
+
58
+ - Transformers 4.7.0
59
+ - Pytorch 1.9.0+cu102
60
+ - Datasets 1.8.0
61
+ - Tokenizers 0.10.3
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilgpt2",
3
+ "_num_labels": 1,
4
+ "activation_function": "gelu_new",
5
+ "architectures": [
6
+ "GPT2LMHeadModel"
7
+ ],
8
+ "attn_pdrop": 0.1,
9
+ "bos_token_id": 50256,
10
+ "do_sample": true,
11
+ "embd_pdrop": 0.1,
12
+ "eos_token_id": 50256,
13
+ "gradient_checkpointing": false,
14
+ "id2label": {
15
+ "0": "LABEL_0"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "label2id": {
19
+ "LABEL_0": 0
20
+ },
21
+ "layer_norm_epsilon": 1e-05,
22
+ "max_length": 50,
23
+ "model_type": "gpt2",
24
+ "n_ctx": 1024,
25
+ "n_embd": 768,
26
+ "n_head": 12,
27
+ "n_inner": null,
28
+ "n_layer": 6,
29
+ "n_positions": 1024,
30
+ "resid_pdrop": 0.1,
31
+ "scale_attn_weights": true,
32
+ "summary_activation": null,
33
+ "summary_first_dropout": 0.1,
34
+ "summary_proj_to_labels": true,
35
+ "summary_type": "cls_index",
36
+ "summary_use_proj": true,
37
+ "task_specific_params": {
38
+ "text-generation": {
39
+ "do_sample": true,
40
+ "max_length": 50
41
+ }
42
+ },
43
+ "transformers_version": "4.7.0",
44
+ "use_cache": true,
45
+ "vocab_size": 50257
46
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:132b8650677c9194c585feb65b0da8cfe476db6a878d4c6f4814cb042fc6ad8c
3
+ size 333972957