Junxiong Wang commited on
Commit
74d28bb
·
1 Parent(s): 034ff19

add models

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,3 +1,67 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: JunxiongWang/zephyr_0.50_mamba_progressive
3
+ tags:
4
+ - mamba
5
+ - alignment-handbook
6
+ - generated_from_trainer
7
+ datasets:
8
+ - JunxiongWang/sftdataset
9
+ model-index:
10
+ - name: mamba_0_5_sft
11
+ results: []
12
+ ---
13
+
14
+ Please check [here](https://github.com/jxiw/MambaInLlama/tree/main) for details.
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # mamba_0_5_sft
20
+
21
+ This model is a fine-tuned version of [JunxiongWang/zephyr_0.50_mamba_progressive](https://huggingface.co/JunxiongWang/zephyr_0.50_mamba_progressive) on the JunxiongWang/sftdataset dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.5661
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 2e-05
43
+ - train_batch_size: 8
44
+ - eval_batch_size: 8
45
+ - seed: 42
46
+ - distributed_type: multi-GPU
47
+ - num_devices: 8
48
+ - total_train_batch_size: 64
49
+ - total_eval_batch_size: 64
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: cosine
52
+ - lr_scheduler_warmup_ratio: 0.01
53
+ - num_epochs: 1
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss |
58
+ |:-------------:|:-----:|:-----:|:---------------:|
59
+ | 0.6021 | 1.0 | 55064 | 0.5661 |
60
+
61
+
62
+ ### Framework versions
63
+
64
+ - Transformers 4.41.2
65
+ - Pytorch 2.1.0+cu118
66
+ - Datasets 2.20.0
67
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 0.5660967230796814,
4
+ "eval_runtime": 17.7951,
5
+ "eval_samples": 4096,
6
+ "eval_samples_per_second": 48.103,
7
+ "eval_steps_per_second": 0.787,
8
+ "total_flos": 7.680275121596006e+16,
9
+ "train_loss": 0.6780993922750357,
10
+ "train_runtime": 284116.9477,
11
+ "train_samples": 15487525,
12
+ "train_samples_per_second": 12.403,
13
+ "train_steps_per_second": 0.194
14
+ }
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
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
+ "pad_token_id": 2,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_theta": 10000.0,
21
+ "sliding_window": 4096,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.41.2",
25
+ "use_cache": true,
26
+ "vocab_size": 32000
27
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 0.5660967230796814,
4
+ "eval_runtime": 17.7951,
5
+ "eval_samples": 4096,
6
+ "eval_samples_per_second": 48.103,
7
+ "eval_steps_per_second": 0.787
8
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.41.2"
6
+ }
mamba_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "d_model": 4096,
3
+ "ssm_cfg": {
4
+ "expand": 1
5
+ },
6
+ "rms_norm_eps": 1e-05,
7
+ "vocab_size": null,
8
+ "d_xb": 1024,
9
+ "intermediate_size": 14336,
10
+ "hidden_act": "silu",
11
+ "n_layer": 32,
12
+ "attn_layers": [
13
+ 1,
14
+ 3,
15
+ 5,
16
+ 7,
17
+ 9,
18
+ 11,
19
+ 13,
20
+ 15,
21
+ 17,
22
+ 19,
23
+ 21,
24
+ 23,
25
+ 25,
26
+ 27,
27
+ 29,
28
+ 31
29
+ ]
30
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b64adf9786ce27db9d4bb5c45515af2e51b3cb509441c837a605f405a673c10d
3
+ size 30181056602
special_tokens_map.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "<unk>",
32
+ "<s>",
33
+ "</s>"
34
+ ],
35
+ "bos_token": "<s>",
36
+ "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 %}",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "</s>",
39
+ "legacy": true,
40
+ "model_max_length": 2048,
41
+ "pad_token": "</s>",
42
+ "sp_model_kwargs": {},
43
+ "spaces_between_special_tokens": false,
44
+ "tokenizer_class": "LlamaTokenizer",
45
+ "truncation_side": "left",
46
+ "unk_token": "<unk>",
47
+ "use_default_system_prompt": true
48
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 7.680275121596006e+16,
4
+ "train_loss": 0.6780993922750357,
5
+ "train_runtime": 284116.9477,
6
+ "train_samples": 15487525,
7
+ "train_samples_per_second": 12.403,
8
+ "train_steps_per_second": 0.194
9
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dad108ff1d4bd6d402a67d20497d43aa059ff9d9815f3c13b0d7825168561008
3
+ size 6392