Tristan Thrush commited on
Commit
a29c6c1
1 Parent(s): a83ffa7

Training in progress, step 10000

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "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
+ "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,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.24.0",
37
+ "use_cache": true,
38
+ "vocab_size": 50265
39
+ }
logs/1669690626.5638368/events.out.tfevents.1669690626.tristan-olm-training-a100-80.3514.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:063cd2618e0560e74a658e9e728d224c80c0c4430f0bb25f14d1389eaa87d01f
3
+ size 5483
logs/1669690713.5668015/events.out.tfevents.1669690713.tristan-olm-training-a100-80.3864.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8c75904c542d678e69b1b3152671f3d6f5f20a22b1c42228fda9e4358f31d0a
3
+ size 5483
logs/1669690775.4381375/events.out.tfevents.1669690775.tristan-olm-training-a100-80.4182.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce6b004f22283ef19d37d530067c73dd42b3c78a0b18f7eac6894013564eef79
3
+ size 5483
logs/1669690846.2385244/events.out.tfevents.1669690846.tristan-olm-training-a100-80.4497.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba77a41ec3d95d0f7ae709185c585a36796a01e5fe72ab25a709a9f8b033020f
3
+ size 5483
logs/events.out.tfevents.1669690626.tristan-olm-training-a100-80.3514.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d93be7dd055936310b9c113725c89793140db7b1394fd97731ca3df99928fe9c
3
+ size 3963
logs/events.out.tfevents.1669690713.tristan-olm-training-a100-80.3864.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4567a102c7c983ee96196b890de7fa00131391d833a39103cad7098b18376a5
3
+ size 3963
logs/events.out.tfevents.1669690775.tristan-olm-training-a100-80.4182.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4ffb7c6f3534c619c4c7c3b21079dc98e2a6ec97e0ecee24b08ab72b76e02ab
3
+ size 3963
logs/events.out.tfevents.1669690846.tristan-olm-training-a100-80.4497.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3805d4f6bbefc660a623209d6a26c535e05648a99c45276b0d150abf9ee97c62
3
+ size 19659
merges.txt ADDED
The diff for this file is too large to render. See raw diff
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b30034b2b5bb3d1ef882e6aff61c711022519d2528a0c1261e8b8d22fbe78ff
3
+ size 510422589
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "mask_token": {
8
+ "__type": "AddedToken",
9
+ "content": "<mask>",
10
+ "lstrip": true,
11
+ "normalized": false,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "model_max_length": 512,
16
+ "name_or_path": "Tristan/olm-tokenizer",
17
+ "pad_token": "<pad>",
18
+ "sep_token": "</s>",
19
+ "special_tokens_map_file": null,
20
+ "tokenizer_class": "RobertaTokenizer",
21
+ "trim_offsets": true,
22
+ "unk_token": "<unk>"
23
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9d0cdb3b235c7a0e9743cb83848a4b0f8ec9330017adbf701401b8e68486ae7
3
+ size 3387
vocab.json ADDED
The diff for this file is too large to render. See raw diff