Hugging Face's logo

AmberYifan
/
spin-v-high-loss

Text Generation
Transformers
TensorBoard
Safetensors
mistral
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
AmberYifan commited on
Commit
d19fa01
•
1 Parent(s): 6b993f2

Training in progress, step 100

Browse files
Files changed (10) hide show
  1. config.json +26 -0
  2. runs/Jun24_21-53-20_gilbreth-j001.rcac.purdue.edu/events.out.tfevents.1719280598.gilbreth-j001.rcac.purdue.edu.197048.0 +3 -0
  3. runs/Jun24_22-05-14_gilbreth-j001.rcac.purdue.edu/events.out.tfevents.1719281259.gilbreth-j001.rcac.purdue.edu.213975.0 +3 -0
  4. runs/Jun24_22-23-16_gilbreth-j001.rcac.purdue.edu/events.out.tfevents.1719282300.gilbreth-j001.rcac.purdue.edu.218723.0 +3 -0
  5. runs/Jun24_22-29-27_gilbreth-j001.rcac.purdue.edu/events.out.tfevents.1719282709.gilbreth-j001.rcac.purdue.edu.220607.0 +3 -0
  6. runs/Jun24_22-35-46_gilbreth-j001.rcac.purdue.edu/events.out.tfevents.1719283059.gilbreth-j001.rcac.purdue.edu.222862.0 +3 -0
  7. special_tokens_map.json +30 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +43 -0
  10. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "alignment-handbook/zephyr-7b-sft-full",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.37.0",
24
+ "use_cache": false,
25
+ "vocab_size": 32000
26
+ }
runs/Jun24_21-53-20_gilbreth-j001.rcac.purdue.edu/events.out.tfevents.1719280598.gilbreth-j001.rcac.purdue.edu.197048.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8694b78b48bac7ad485adfdf4f7c227c5978d5db5ff5826152f0188abd7eb04
3
+ size 9006
runs/Jun24_22-05-14_gilbreth-j001.rcac.purdue.edu/events.out.tfevents.1719281259.gilbreth-j001.rcac.purdue.edu.213975.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91529e19e6957f09ee0765087e4b629de72de2ac57cf3efc5d8497539159748c
3
+ size 11486
runs/Jun24_22-23-16_gilbreth-j001.rcac.purdue.edu/events.out.tfevents.1719282300.gilbreth-j001.rcac.purdue.edu.218723.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:002e1879ccdd4de262778e1ddc4f05cbc1f2d15e440fad95a8f11dd4bd7ba56c
3
+ size 7676
runs/Jun24_22-29-27_gilbreth-j001.rcac.purdue.edu/events.out.tfevents.1719282709.gilbreth-j001.rcac.purdue.edu.220607.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98338da121e775940cc861789eb4565ce080e5e4c85428c42696a32374ce5c6f
3
+ size 7676
runs/Jun24_22-35-46_gilbreth-j001.rcac.purdue.edu/events.out.tfevents.1719283059.gilbreth-j001.rcac.purdue.edu.222862.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc3e6f23ca5e8db757a9ab52aebb105e92e66e6949d14c700fd9572e7d7aad1
3
+ size 12845
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 2048,
37
+ "pad_token": "</s>",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": true
43
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36c7cc2506f27bb63919cfb74ce3b29d9d9b5f478cb31f2c6178c0aaebf6e8fe
3
+ size 5880