Hugging Face's logo

mllm-dev
/
gen_test_4

Text Generation
Transformers
TensorBoard
Safetensors
gpt2
text-generation-inference
Model card Files
xet
Metrics Community
mllm-dev commited on
Commit
334d4e6
·
verified ·
1 Parent(s): 85dd8db

Training in progress, epoch 1

Browse files
Files changed (19) hide show
  1. config.json +40 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. runs/Mar12_16-40-34_lambda-hyperplane01/events.out.tfevents.1710286841.lambda-hyperplane01.953443.0 +3 -0
  5. runs/Mar12_16-51-23_lambda-hyperplane01/events.out.tfevents.1710287490.lambda-hyperplane01.954031.0 +3 -0
  6. runs/Mar12_17-00-04_lambda-hyperplane01/events.out.tfevents.1710288011.lambda-hyperplane01.954505.0 +3 -0
  7. runs/Mar12_17-02-30_lambda-hyperplane01/events.out.tfevents.1710288157.lambda-hyperplane01.954734.0 +3 -0
  8. runs/Mar12_17-03-57_lambda-hyperplane01/events.out.tfevents.1710288244.lambda-hyperplane01.954898.0 +3 -0
  9. runs/Mar12_17-08-11_lambda-hyperplane01/events.out.tfevents.1710288498.lambda-hyperplane01.955167.0 +3 -0
  10. runs/Mar12_17-10-53_lambda-hyperplane01/events.out.tfevents.1710288660.lambda-hyperplane01.955390.0 +3 -0
  11. runs/Mar12_20-38-51_lambda-hyperplane03/events.out.tfevents.1710301138.lambda-hyperplane03.3249289.0 +3 -0
  12. runs/Mar12_21-02-00_lambda-hyperplane03/events.out.tfevents.1710302527.lambda-hyperplane03.3261148.0 +3 -0
  13. runs/Mar12_21-50-38_lambda-hyperplane03/events.out.tfevents.1710305445.lambda-hyperplane03.3274663.0 +3 -0
  14. runs/Mar12_22-12-09_lambda-hyperplane03/events.out.tfevents.1710306736.lambda-hyperplane03.3286236.0 +3 -0
  15. runs/Mar12_23-21-03_lambda-hyperplane04/events.out.tfevents.1710310870.lambda-hyperplane04.1144229.0 +3 -0
  16. special_tokens_map.json +24 -0
  17. tokenizer_config.json +22 -0
  18. training_args.bin +3 -0
  19. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai-community/gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
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",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "pad_token_id": 50256,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "task_specific_params": {
31
+ "text-generation": {
32
+ "do_sample": true,
33
+ "max_length": 50
34
+ }
35
+ },
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.38.2",
38
+ "use_cache": true,
39
+ "vocab_size": 50257
40
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51aaa3791f5841a581fff4099977eb7f75e673ba7b767b0a27ae6c2751ae67dd
3
+ size 497774208
runs/Mar12_16-40-34_lambda-hyperplane01/events.out.tfevents.1710286841.lambda-hyperplane01.953443.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:839a5e37fff0d3598f6c8238209a2cc9aea9a0d9fd1247e057261610e96665a6
3
+ size 6253
runs/Mar12_16-51-23_lambda-hyperplane01/events.out.tfevents.1710287490.lambda-hyperplane01.954031.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04331e5641a8072699ba27175c4e16137c44584fd6311d216c20ec27856ca0f8
3
+ size 6253
runs/Mar12_17-00-04_lambda-hyperplane01/events.out.tfevents.1710288011.lambda-hyperplane01.954505.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3319e74549b3e08ad505c651c399f995ae64631c5013900daa63cccbb8f5e36
3
+ size 4841
runs/Mar12_17-02-30_lambda-hyperplane01/events.out.tfevents.1710288157.lambda-hyperplane01.954734.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb3c1ad6c20e1be3f848ae42aa93a151151c25c3950231668d01b8cbe72522d0
3
+ size 4841
runs/Mar12_17-03-57_lambda-hyperplane01/events.out.tfevents.1710288244.lambda-hyperplane01.954898.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12b85890120c416bac798fbc15995722bdbc90616eb64414d9cdd7ebaa7d9d63
3
+ size 4841
runs/Mar12_17-08-11_lambda-hyperplane01/events.out.tfevents.1710288498.lambda-hyperplane01.955167.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94b4beaeae108403e642305e53e601e1aa4782b1ddd6cb38313d5cd63e8ecd86
3
+ size 4841
runs/Mar12_17-10-53_lambda-hyperplane01/events.out.tfevents.1710288660.lambda-hyperplane01.955390.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90d564b3f19b71e19905337119d07c8a348e5dff85625ab724671f6b85ec36df
3
+ size 6488
runs/Mar12_20-38-51_lambda-hyperplane03/events.out.tfevents.1710301138.lambda-hyperplane03.3249289.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:587b2fdb77fab58ac9fef542b4a1bcf52858091698ce902dd8a4cecc6be92481
3
+ size 6488
runs/Mar12_21-02-00_lambda-hyperplane03/events.out.tfevents.1710302527.lambda-hyperplane03.3261148.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16c25c896750afc8d0fabc4f3d9d1ed9e749065766e7031e36c97c9015869ad1
3
+ size 6488
runs/Mar12_21-50-38_lambda-hyperplane03/events.out.tfevents.1710305445.lambda-hyperplane03.3274663.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5214b2bef5309aad4669988cf14e4482e9f83f09c49d5247585ac52a7fe299f
3
+ size 6488
runs/Mar12_22-12-09_lambda-hyperplane03/events.out.tfevents.1710306736.lambda-hyperplane03.3286236.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e22d28fdd26e86bc1ff3f02cec946ba29f3bf174bbcf770e96de89aa1dd6444
3
+ size 8809
runs/Mar12_23-21-03_lambda-hyperplane04/events.out.tfevents.1710310870.lambda-hyperplane04.1144229.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfb3c05c9956bcdfbb98995957b9bb64dec22dafedf9c42f2069a5bf73740a1c
3
+ size 5743
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ }
13
+ },
14
+ "bos_token": "<|endoftext|>",
15
+ "clean_up_tokenization_spaces": true,
16
+ "eos_token": "<|endoftext|>",
17
+ "errors": "replace",
18
+ "model_max_length": 1024,
19
+ "pad_token": "<|endoftext|>",
20
+ "tokenizer_class": "GPT2Tokenizer",
21
+ "unk_token": "<|endoftext|>"
22
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06049c3a4d810ccb40116545b36ae9be71ca122cda2ae9a768209a855f9a605c
3
+ size 4539
vocab.json ADDED
The diff for this file is too large to render. See raw diff