Wonder-Griffin commited on
Commit
55a1e04
1 Parent(s): 1b1f209

Training in progress, step 500

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 50257
3
+ }
config.json CHANGED
@@ -1,54 +1,54 @@
1
- {
2
- "_name_or_path": "Wonder-Griffin/TraXLMistral",
3
- "activation_function": "gelu_new",
4
- "architectures": [
5
- "GPT2Model"
6
- ],
7
- "attn_pdrop": 0.1,
8
- "bos_token_id": 50256,
9
- "dropout": 0.1,
10
- "dynamic_routing": true,
11
- "embd_pdrop": 0.1,
12
- "eos_token_id": 50256,
13
- "ff_expansion_factor": 4,
14
- "id2label": {
15
- "0": "LABEL_0",
16
- "1": "LABEL_1",
17
- "2": "LABEL_2",
18
- "3": "LABEL_3",
19
- "4": "LABEL_4"
20
- },
21
- "initializer_range": 0.02,
22
- "label2id": {
23
- "LABEL_0": 0,
24
- "LABEL_1": 1,
25
- "LABEL_2": 2,
26
- "LABEL_3": 3,
27
- "LABEL_4": 4
28
- },
29
- "layer_norm_epsilon": 1e-05,
30
- "max_computation_steps": 5,
31
- "max_len": 256,
32
- "memory_size": 256,
33
- "model_type": "gpt2",
34
- "n_embd": 128,
35
- "n_head": 4,
36
- "n_inner": null,
37
- "n_layer": 4,
38
- "n_positions": 1024,
39
- "reorder_and_upcast_attn": false,
40
- "resid_pdrop": 0.1,
41
- "rnn_units": 128,
42
- "scale_attn_by_inverse_layer_idx": false,
43
- "scale_attn_weights": true,
44
- "sparse_attention": true,
45
- "summary_activation": null,
46
- "summary_first_dropout": 0.1,
47
- "summary_proj_to_labels": true,
48
- "summary_type": "cls_index",
49
- "summary_use_proj": true,
50
- "torch_dtype": "float32",
51
- "transformers_version": "4.44.1",
52
- "use_cache": true,
53
- "vocab_size": 60000
54
- }
 
1
+ {
2
+ "_name_or_path": "Wonder-Griffin/squadtrainTraXL",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "dropout": 0.1,
10
+ "dynamic_routing": true,
11
+ "embd_pdrop": 0.1,
12
+ "eos_token_id": 50256,
13
+ "ff_expansion_factor": 4,
14
+ "id2label": {
15
+ "0": "LABEL_0",
16
+ "1": "LABEL_1",
17
+ "2": "LABEL_2",
18
+ "3": "LABEL_3",
19
+ "4": "LABEL_4"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "label2id": {
23
+ "LABEL_0": 0,
24
+ "LABEL_1": 1,
25
+ "LABEL_2": 2,
26
+ "LABEL_3": 3,
27
+ "LABEL_4": 4
28
+ },
29
+ "layer_norm_epsilon": 1e-05,
30
+ "max_computation_steps": 5,
31
+ "max_len": 256,
32
+ "memory_size": 256,
33
+ "model_type": "gpt2",
34
+ "n_embd": 128,
35
+ "n_head": 4,
36
+ "n_inner": null,
37
+ "n_layer": 4,
38
+ "n_positions": 1024,
39
+ "reorder_and_upcast_attn": false,
40
+ "resid_pdrop": 0.1,
41
+ "rnn_units": 128,
42
+ "scale_attn_by_inverse_layer_idx": false,
43
+ "scale_attn_weights": true,
44
+ "sparse_attention": true,
45
+ "summary_activation": null,
46
+ "summary_first_dropout": 0.1,
47
+ "summary_proj_to_labels": true,
48
+ "summary_type": "cls_index",
49
+ "summary_use_proj": true,
50
+ "torch_dtype": "float32",
51
+ "transformers_version": "4.44.2",
52
+ "use_cache": true,
53
+ "vocab_size": 60000
54
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82270158702ecf9996287bdac337857c7c672f4c56f064294716860060af4f84
3
- size 34422080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6199d32d8e47d80d687a5a538ce2c2b9a525938f569c8f94529e5b383f60b216
3
+ size 34422704
special_tokens_map.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "unk_token": "<|endoftext|>"
12
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": "[PAD]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "bos_token": "<|endoftext|>",
22
+ "clean_up_tokenization_spaces": true,
23
+ "eos_token": "<|endoftext|>",
24
+ "model_max_length": 1024,
25
+ "pad_token": "[PAD]",
26
+ "tokenizer_class": "GPT2Tokenizer",
27
+ "unk_token": "<|endoftext|>"
28
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b964318d0e43bbcb33753b5a8681dc869f7ccbc931707b07a3b3b46cae789786
3
- size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0af5bbae6ba84b124abdb4be8844f3c19d31437d5bb7dbcf91c6773aef2591a2
3
+ size 5176
vocab.json ADDED
The diff for this file is too large to render. See raw diff