mledall commited on
Commit
b5aa10c
·
verified ·
1 Parent(s): 9033e0c

Training in progress, step 957

Browse files
config.json CHANGED
@@ -1,13 +1,12 @@
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": 0,
9
  "embd_pdrop": 0.1,
10
- "eos_token_id": 0,
11
  "initializer_range": 0.02,
12
  "layer_norm_epsilon": 1e-05,
13
  "model_type": "gpt2",
@@ -33,7 +32,7 @@
33
  }
34
  },
35
  "torch_dtype": "float32",
36
- "transformers_version": "4.49.0",
37
  "use_cache": true,
38
- "vocab_size": 50000
39
  }
 
1
  {
 
2
  "activation_function": "gelu_new",
3
  "architectures": [
4
  "GPT2LMHeadModel"
5
  ],
6
  "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
  "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
  "initializer_range": 0.02,
11
  "layer_norm_epsilon": 1e-05,
12
  "model_type": "gpt2",
 
32
  }
33
  },
34
  "torch_dtype": "float32",
35
+ "transformers_version": "4.50.2",
36
  "use_cache": true,
37
+ "vocab_size": 50257
38
  }
merges.txt CHANGED
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 sha256:23bda47fb43bd82d4c61e413155137494c0c107adbb62b2467749739f7f6368c
3
- size 496984704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03471a040c0b7b89db1148eb1a9bda887efa25cbcfba427c8762a4f2485e73a2
3
+ size 497774208
runs/Mar28_17-01-01_192-222-56-147/events.out.tfevents.1743181271.192-222-56-147.4378.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c110c4917e27d66711b5162b6649832a617cec68f6fcd87a6aaca5eb3435a1e7
3
+ size 5618
special_tokens_map.json CHANGED
@@ -1,24 +1,6 @@
1
  {
2
- "bos_token": {
3
- "content": "<|endoftext|>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "<|endoftext|>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
  "pad_token": "<|endoftext|>",
17
- "unk_token": {
18
- "content": "<|endoftext|>",
19
- "lstrip": false,
20
- "normalized": false,
21
- "rstrip": false,
22
- "single_word": false
23
- }
24
  }
 
1
  {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
 
 
 
 
 
 
 
 
 
 
 
 
4
  "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
 
 
 
 
 
 
6
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
  "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
- "0": {
5
  "content": "<|endoftext|>",
6
  "lstrip": false,
7
- "normalized": false,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
 
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
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5fdd30269c93fdf0fd3e81d11b745482aac662b3bdfe83ea347835ec32fc7ee4
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75adc7e5a17055a64f65ec32c06d9ee10b7d75264c4b59f97c14ebf181807c7d
3
  size 5304
vocab.json CHANGED
The diff for this file is too large to render. See raw diff