bigmorning commited on
Commit
25c2725
1 Parent(s): 8df1ae2
Files changed (3) hide show
  1. README.md +112 -0
  2. config.json +45 -0
  3. tf_model.h5 +3 -0
README.md ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_keras_callback
5
+ model-index:
6
+ - name: distilgpt_oscarth_0060
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information Keras had access to. You should
11
+ probably proofread and complete it, then remove this comment. -->
12
+
13
+ # distilgpt_oscarth_0060
14
+
15
+ This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Train Loss: 2.8883
18
+ - Validation Loss: 2.7784
19
+ - Epoch: 59
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
39
+ - training_precision: float32
40
+
41
+ ### Training results
42
+
43
+ | Train Loss | Validation Loss | Epoch |
44
+ |:----------:|:---------------:|:-----:|
45
+ | 5.6021 | 4.5759 | 0 |
46
+ | 4.4536 | 4.1235 | 1 |
47
+ | 4.1386 | 3.9013 | 2 |
48
+ | 3.9546 | 3.7563 | 3 |
49
+ | 3.8255 | 3.6477 | 4 |
50
+ | 3.7271 | 3.5617 | 5 |
51
+ | 3.6488 | 3.4936 | 6 |
52
+ | 3.5844 | 3.4379 | 7 |
53
+ | 3.5301 | 3.3891 | 8 |
54
+ | 3.4833 | 3.3448 | 9 |
55
+ | 3.4427 | 3.3098 | 10 |
56
+ | 3.4068 | 3.2750 | 11 |
57
+ | 3.3749 | 3.2425 | 12 |
58
+ | 3.3462 | 3.2211 | 13 |
59
+ | 3.3202 | 3.1941 | 14 |
60
+ | 3.2964 | 3.1720 | 15 |
61
+ | 3.2749 | 3.1512 | 16 |
62
+ | 3.2548 | 3.1322 | 17 |
63
+ | 3.2363 | 3.1141 | 18 |
64
+ | 3.2188 | 3.0982 | 19 |
65
+ | 3.2025 | 3.0818 | 20 |
66
+ | 3.1871 | 3.0678 | 21 |
67
+ | 3.1724 | 3.0533 | 22 |
68
+ | 3.1583 | 3.0376 | 23 |
69
+ | 3.1446 | 3.0256 | 24 |
70
+ | 3.1318 | 3.0122 | 25 |
71
+ | 3.1195 | 3.0016 | 26 |
72
+ | 3.1079 | 2.9901 | 27 |
73
+ | 3.0968 | 2.9826 | 28 |
74
+ | 3.0863 | 2.9711 | 29 |
75
+ | 3.0761 | 2.9593 | 30 |
76
+ | 3.0665 | 2.9514 | 31 |
77
+ | 3.0572 | 2.9432 | 32 |
78
+ | 3.0483 | 2.9347 | 33 |
79
+ | 3.0396 | 2.9250 | 34 |
80
+ | 3.0313 | 2.9160 | 35 |
81
+ | 3.0232 | 2.9095 | 36 |
82
+ | 3.0153 | 2.9028 | 37 |
83
+ | 3.0078 | 2.8949 | 38 |
84
+ | 3.0004 | 2.8864 | 39 |
85
+ | 2.9932 | 2.8799 | 40 |
86
+ | 2.9864 | 2.8722 | 41 |
87
+ | 2.9797 | 2.8657 | 42 |
88
+ | 2.9731 | 2.8605 | 43 |
89
+ | 2.9668 | 2.8544 | 44 |
90
+ | 2.9606 | 2.8481 | 45 |
91
+ | 2.9545 | 2.8421 | 46 |
92
+ | 2.9487 | 2.8368 | 47 |
93
+ | 2.9429 | 2.8288 | 48 |
94
+ | 2.9374 | 2.8257 | 49 |
95
+ | 2.9319 | 2.8204 | 50 |
96
+ | 2.9266 | 2.8152 | 51 |
97
+ | 2.9215 | 2.8093 | 52 |
98
+ | 2.9164 | 2.8054 | 53 |
99
+ | 2.9114 | 2.7998 | 54 |
100
+ | 2.9066 | 2.7980 | 55 |
101
+ | 2.9019 | 2.7913 | 56 |
102
+ | 2.8972 | 2.7865 | 57 |
103
+ | 2.8927 | 2.7816 | 58 |
104
+ | 2.8883 | 2.7784 | 59 |
105
+
106
+
107
+ ### Framework versions
108
+
109
+ - Transformers 4.20.1
110
+ - TensorFlow 2.8.2
111
+ - Datasets 2.3.2
112
+ - Tokenizers 0.12.1
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 50256,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "LABEL_0": 0
18
+ },
19
+ "layer_norm_epsilon": 1e-05,
20
+ "model_type": "gpt2",
21
+ "n_ctx": 1024,
22
+ "n_embd": 768,
23
+ "n_head": 12,
24
+ "n_inner": null,
25
+ "n_layer": 6,
26
+ "n_positions": 1024,
27
+ "reorder_and_upcast_attn": false,
28
+ "resid_pdrop": 0.1,
29
+ "scale_attn_by_inverse_layer_idx": false,
30
+ "scale_attn_weights": true,
31
+ "summary_activation": null,
32
+ "summary_first_dropout": 0.1,
33
+ "summary_proj_to_labels": true,
34
+ "summary_type": "cls_index",
35
+ "summary_use_proj": true,
36
+ "task_specific_params": {
37
+ "text-generation": {
38
+ "do_sample": true,
39
+ "max_length": 50
40
+ }
41
+ },
42
+ "transformers_version": "4.20.1",
43
+ "use_cache": true,
44
+ "vocab_size": 27672
45
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03f1b952c9f26e6b5c83dbf6d1efc1d541fde80e5a98888c12f73e59623cb67b
3
+ size 343376392