Commit
•
e25a6c9
1
Parent(s):
94d3e63
End of training
Browse files- .gitattributes +1 -0
- README.md +148 -0
- adapter_config.json +32 -0
- adapter_model.bin +3 -0
- adapter_model.safetensors +3 -0
- config.json +42 -0
- runs/Feb22_21-33-07_zen/events.out.tfevents.1708637589.zen.1452606.0 +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +49 -0
- training_args.bin +3 -0
.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 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,148 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- axolotl
|
6 |
+
- generated_from_trainer
|
7 |
+
base_model: google/gemma-7b
|
8 |
+
model-index:
|
9 |
+
- name: gemma-7b-Open-Hermes-v0.1
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
17 |
+
<details><summary>See axolotl config</summary>
|
18 |
+
|
19 |
+
axolotl version: `0.4.0`
|
20 |
+
```yaml
|
21 |
+
# use google/gemma-7b if you have access
|
22 |
+
#base_model: mhenrichsen/gemma-7b
|
23 |
+
base_model: google/gemma-7b
|
24 |
+
model_type: AutoModelForCausalLM
|
25 |
+
tokenizer_type: AutoTokenizer
|
26 |
+
|
27 |
+
hub_model_id: MaziyarPanahi/gemma-7b-Open-Hermes-v0.1
|
28 |
+
hf_use_auth_token: true
|
29 |
+
|
30 |
+
load_in_8bit: false
|
31 |
+
load_in_4bit: true
|
32 |
+
strict: false
|
33 |
+
|
34 |
+
# huggingface repo
|
35 |
+
datasets:
|
36 |
+
- path: teknium/openhermes
|
37 |
+
type: alpaca
|
38 |
+
val_set_size: 0.1
|
39 |
+
output_dir: ./qlora-gemma-7b-openhermes
|
40 |
+
|
41 |
+
adapter: qlora
|
42 |
+
lora_r: 32
|
43 |
+
lora_alpha: 16
|
44 |
+
lora_dropout: 0.05
|
45 |
+
lora_target_linear: true
|
46 |
+
|
47 |
+
|
48 |
+
sequence_len: 4096
|
49 |
+
sample_packing: false
|
50 |
+
pad_to_sequence_len: false
|
51 |
+
|
52 |
+
wandb_project:
|
53 |
+
wandb_entity:
|
54 |
+
wandb_watch:
|
55 |
+
wandb_name:
|
56 |
+
wandb_log_model:
|
57 |
+
|
58 |
+
|
59 |
+
gradient_accumulation_steps: 3
|
60 |
+
micro_batch_size: 2
|
61 |
+
num_epochs: 1
|
62 |
+
optimizer: adamw_bnb_8bit
|
63 |
+
lr_scheduler: cosine
|
64 |
+
learning_rate: 0.0002
|
65 |
+
|
66 |
+
train_on_inputs: false
|
67 |
+
group_by_length: false
|
68 |
+
bf16: auto
|
69 |
+
fp16:
|
70 |
+
tf32: false
|
71 |
+
|
72 |
+
gradient_checkpointing: true
|
73 |
+
early_stopping_patience:
|
74 |
+
resume_from_checkpoint:
|
75 |
+
local_rank:
|
76 |
+
logging_steps: 1
|
77 |
+
xformers_attention:
|
78 |
+
flash_attention: true
|
79 |
+
|
80 |
+
warmup_ratio: 0.1
|
81 |
+
evals_per_epoch: 4
|
82 |
+
eval_table_size:
|
83 |
+
eval_max_new_tokens: 128
|
84 |
+
saves_per_epoch: 1
|
85 |
+
debug:
|
86 |
+
deepspeed:
|
87 |
+
weight_decay: 0.0
|
88 |
+
fsdp:
|
89 |
+
fsdp_config:
|
90 |
+
special_tokens:
|
91 |
+
```
|
92 |
+
|
93 |
+
</details><br>
|
94 |
+
|
95 |
+
# gemma-7b-Open-Hermes-v0.1
|
96 |
+
|
97 |
+
This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the None dataset.
|
98 |
+
It achieves the following results on the evaluation set:
|
99 |
+
- Loss: 1.4456
|
100 |
+
|
101 |
+
## Model description
|
102 |
+
|
103 |
+
More information needed
|
104 |
+
|
105 |
+
## Intended uses & limitations
|
106 |
+
|
107 |
+
More information needed
|
108 |
+
|
109 |
+
## Training and evaluation data
|
110 |
+
|
111 |
+
More information needed
|
112 |
+
|
113 |
+
## Training procedure
|
114 |
+
|
115 |
+
### Training hyperparameters
|
116 |
+
|
117 |
+
The following hyperparameters were used during training:
|
118 |
+
- learning_rate: 0.0002
|
119 |
+
- train_batch_size: 2
|
120 |
+
- eval_batch_size: 2
|
121 |
+
- seed: 42
|
122 |
+
- distributed_type: multi-GPU
|
123 |
+
- num_devices: 4
|
124 |
+
- gradient_accumulation_steps: 3
|
125 |
+
- total_train_batch_size: 24
|
126 |
+
- total_eval_batch_size: 8
|
127 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
128 |
+
- lr_scheduler_type: cosine
|
129 |
+
- lr_scheduler_warmup_steps: 227
|
130 |
+
- num_epochs: 1
|
131 |
+
|
132 |
+
### Training results
|
133 |
+
|
134 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
135 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
136 |
+
| 1.3258 | 0.0 | 1 | 1.9697 |
|
137 |
+
| 0.63 | 0.25 | 2277 | 1.5227 |
|
138 |
+
| 0.642 | 0.5 | 4554 | 1.4835 |
|
139 |
+
| 0.7721 | 0.75 | 6831 | 1.4456 |
|
140 |
+
|
141 |
+
|
142 |
+
### Framework versions
|
143 |
+
|
144 |
+
- PEFT 0.8.2
|
145 |
+
- Transformers 4.39.0.dev0
|
146 |
+
- Pytorch 2.2.0+cu121
|
147 |
+
- Datasets 2.17.0
|
148 |
+
- Tokenizers 0.15.0
|
adapter_config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "google/gemma-7b",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 16,
|
13 |
+
"lora_dropout": 0.05,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 32,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"k_proj",
|
23 |
+
"up_proj",
|
24 |
+
"gate_proj",
|
25 |
+
"q_proj",
|
26 |
+
"o_proj",
|
27 |
+
"v_proj",
|
28 |
+
"down_proj"
|
29 |
+
],
|
30 |
+
"task_type": "CAUSAL_LM",
|
31 |
+
"use_rslora": false
|
32 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:671229bfc35e87fa9a923676b4a08a255e8cd8e5bd2d4d559e607095012c7834
|
3 |
+
size 400173482
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e4276021b5987792bb3d8f356997abc9fbf369ac5f1bdc9d52bc01ed5a88db1
|
3 |
+
size 400084608
|
config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/gemma-7b",
|
3 |
+
"architectures": [
|
4 |
+
"GemmaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 2,
|
9 |
+
"eos_token_id": 1,
|
10 |
+
"head_dim": 256,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_size": 3072,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 24576,
|
15 |
+
"max_position_embeddings": 8192,
|
16 |
+
"model_type": "gemma",
|
17 |
+
"num_attention_heads": 16,
|
18 |
+
"num_hidden_layers": 28,
|
19 |
+
"num_key_value_heads": 16,
|
20 |
+
"pad_token_id": 0,
|
21 |
+
"quantization_config": {
|
22 |
+
"_load_in_4bit": true,
|
23 |
+
"_load_in_8bit": false,
|
24 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
25 |
+
"bnb_4bit_quant_type": "nf4",
|
26 |
+
"bnb_4bit_use_double_quant": true,
|
27 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
28 |
+
"llm_int8_has_fp16_weight": false,
|
29 |
+
"llm_int8_skip_modules": null,
|
30 |
+
"llm_int8_threshold": 6.0,
|
31 |
+
"load_in_4bit": true,
|
32 |
+
"load_in_8bit": false,
|
33 |
+
"quant_method": "bitsandbytes"
|
34 |
+
},
|
35 |
+
"rms_norm_eps": 1e-06,
|
36 |
+
"rope_scaling": null,
|
37 |
+
"rope_theta": 10000.0,
|
38 |
+
"torch_dtype": "bfloat16",
|
39 |
+
"transformers_version": "4.39.0.dev0",
|
40 |
+
"use_cache": false,
|
41 |
+
"vocab_size": 256000
|
42 |
+
}
|
runs/Feb22_21-33-07_zen/events.out.tfevents.1708637589.zen.1452606.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:745df8070d326f1d832c295df1f76f165fab444f9f26fda95f6b83a9cc3b41fb
|
3 |
+
size 1927866
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<bos>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<eos>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
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
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0d908b4f9326e0998815690e325b6abbd378978553e10627924dd825db7e243
|
3 |
+
size 17477553
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
|
3 |
+
size 4241003
|
tokenizer_config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<pad>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<eos>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "<bos>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"3": {
|
30 |
+
"content": "<unk>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"bos_token": "<bos>",
|
39 |
+
"clean_up_tokenization_spaces": false,
|
40 |
+
"eos_token": "<eos>",
|
41 |
+
"legacy": null,
|
42 |
+
"model_max_length": 1000000000000000019884624838656,
|
43 |
+
"pad_token": "<pad>",
|
44 |
+
"sp_model_kwargs": {},
|
45 |
+
"spaces_between_special_tokens": false,
|
46 |
+
"tokenizer_class": "GemmaTokenizer",
|
47 |
+
"unk_token": "<unk>",
|
48 |
+
"use_default_system_prompt": false
|
49 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52a30bdcb81a21e8c21767e001e3d6ead09b444076c2945ea756096bfea315e6
|
3 |
+
size 5624
|