schreon commited on
Commit
69ef460
1 Parent(s): 78bda23

Training in progress, step 5000

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "schreon/gpt2large-lhm-02",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 1,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 2,
11
+ "initializer_range": 0.02,
12
+ "is_decoder": true,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 256,
16
+ "n_embd": 1280,
17
+ "n_head": 20,
18
+ "n_inner": null,
19
+ "n_layer": 36,
20
+ "n_positions": 1024,
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": "4.24.0",
38
+ "use_cache": true,
39
+ "vocab_size": 40000
40
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45cea4dd2fd085e1901a9f55c99acb0403532457f43fa0ddc7450277dfd41941
3
+ size 3081519165
runs/Feb16_14-16-13_tardis/1676553399.9318495/events.out.tfevents.1676553399.tardis.37413.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4813afd95e5a5403b73e25ff38ddc7237ff9f5e45d9567c9ca4b600cff7b1878
3
+ size 5500
runs/Feb16_14-16-13_tardis/events.out.tfevents.1676553399.tardis.37413.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52d8f551230382d801210d220890e79b22cbbfc0dab0069bd70de5dded857eed
3
+ size 4206
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<cls>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "pad_token": "</s>",
7
+ "sep_token": "<sep>",
8
+ "unk_token": "<unk>"
9
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "name_or_path": "/home/ma/s/schroederl/XNEXT/xnext/data/tokenizer_fast",
3
+ "special_tokens_map_file": "/home/ma/s/schroederl/XNEXT/xnext/data/tokenizer_fast/special_tokens_map.json",
4
+ "tokenizer_class": "PreTrainedTokenizerFast"
5
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38a64737ec0e316f1065ca780eeaaad557244a3c1ee644dce9e5da47b6bfb6ce
3
+ size 3451