Hugging Face's logo

ccore
/
RDW3

TensorBoard
Safetensors
opt
Model card Files Metrics Community
ccore commited on
Commit
a208e2f
·
verified ·
1 Parent(s): 6f7fa2a

Training in progress, epoch 2

Browse files
Files changed (13) hide show
  1. final_model/config.json +31 -0
  2. final_model/generation_config.json +7 -0
  3. final_model/merges.txt +0 -0
  4. final_model/model.safetensors +3 -0
  5. final_model/special_tokens_map.json +30 -0
  6. final_model/tokenizer.json +0 -0
  7. final_model/tokenizer_config.json +31 -0
  8. final_model/vocab.json +0 -0
  9. model.safetensors +1 -1
  10. runs/Feb03_13-29-26_4f6d7d3e9b72/events.out.tfevents.1738589368.4f6d7d3e9b72.1282.0 +2 -2
  11. runs/Feb03_13-51-06_4f6d7d3e9b72/events.out.tfevents.1738590667.4f6d7d3e9b72.1282.1 +3 -0
  12. runs/Feb03_13-58-42_4f6d7d3e9b72/events.out.tfevents.1738591124.4f6d7d3e9b72.10305.0 +3 -0
  13. training_args.bin +1 -1
final_model/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ccore/RDW3",
3
+ "_remove_final_layer_norm": false,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "architectures": [
7
+ "OPTForCausalLM"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 2,
11
+ "do_layer_norm_before": false,
12
+ "dropout": 0.1,
13
+ "enable_bias": true,
14
+ "eos_token_id": 2,
15
+ "ffn_dim": 4096,
16
+ "hidden_size": 1024,
17
+ "init_std": 0.02,
18
+ "layer_norm_elementwise_affine": true,
19
+ "layerdrop": 0.0,
20
+ "max_position_embeddings": 2048,
21
+ "model_type": "opt",
22
+ "num_attention_heads": 16,
23
+ "num_hidden_layers": 24,
24
+ "pad_token_id": 1,
25
+ "prefix": "</s>",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.47.1",
28
+ "use_cache": true,
29
+ "vocab_size": 50272,
30
+ "word_embed_proj_dim": 512
31
+ }
final_model/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.47.1"
7
+ }
final_model/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
final_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f246aa6cc0081fa9b7e4332214ed8e193ec105b00011ef4ed4a4e7205284468e
3
+ size 1324830880
final_model/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "</s>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
final_model/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
final_model/tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "1": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "2": {
14
+ "content": "</s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ }
21
+ },
22
+ "bos_token": "</s>",
23
+ "clean_up_tokenization_spaces": false,
24
+ "eos_token": "</s>",
25
+ "errors": "replace",
26
+ "extra_special_tokens": {},
27
+ "model_max_length": 1000000000000000019884624838656,
28
+ "pad_token": "<pad>",
29
+ "tokenizer_class": "GPT2Tokenizer",
30
+ "unk_token": "</s>"
31
+ }
final_model/vocab.json 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:f246aa6cc0081fa9b7e4332214ed8e193ec105b00011ef4ed4a4e7205284468e
3
  size 1324830880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:545cda87f9ea5d8fd9a6838df76dcf7fa5654bf4af9e8dbb1dca7fcc33b511a0
3
  size 1324830880
runs/Feb03_13-29-26_4f6d7d3e9b72/events.out.tfevents.1738589368.4f6d7d3e9b72.1282.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70bf9fe5fb37d9772e2875958a9cd49d341bc53c79802526ca3420a18477ab49
3
- size 41168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f8ec7901453d4313474820a12c5bca0ca694a1f0d87689cab30e8787a1beae2
3
+ size 41522
runs/Feb03_13-51-06_4f6d7d3e9b72/events.out.tfevents.1738590667.4f6d7d3e9b72.1282.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be5a0c9451de4c318b5725ef9ac4db21c1dcc14b95d7ec4e6ded3ee741d21848
3
+ size 5362
runs/Feb03_13-58-42_4f6d7d3e9b72/events.out.tfevents.1738591124.4f6d7d3e9b72.10305.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca2173046d92e8d2f25bc976daf9004630413be8a54748d631bea48e8e26e075
3
+ size 24524
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:228b31a33cdb89916f0345448bcc71416a768a57a127423492ac7dd71507ccc9
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01ee0c77a84c59226be8580dfbe625c82d72bc4456ab0e2ca0a40baf78f82e26
3
  size 5368