NeuralNovel
commited on
Commit
•
debb14e
1
Parent(s):
84d69bb
Delete .ipynb_checkpoints
Browse files
.ipynb_checkpoints/README-checkpoint.md
DELETED
@@ -1,154 +0,0 @@
|
|
1 |
-
---
|
2 |
-
license: apache-2.0
|
3 |
-
base_model: mistralai/Mistral-7B-v0.1
|
4 |
-
tags:
|
5 |
-
- generated_from_trainer
|
6 |
-
model-index:
|
7 |
-
- name: out
|
8 |
-
results: []
|
9 |
-
---
|
10 |
-
|
11 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
-
should probably proofread and complete it, then remove this comment. -->
|
13 |
-
|
14 |
-
[<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)
|
15 |
-
<details><summary>See axolotl config</summary>
|
16 |
-
|
17 |
-
axolotl version: `0.4.0`
|
18 |
-
```yaml
|
19 |
-
base_model: mistralai/Mistral-7B-v0.1
|
20 |
-
model_type: AutoModelForCausalLM
|
21 |
-
tokenizer_type: AutoTokenizer
|
22 |
-
is_mistral_derived_model: true
|
23 |
-
|
24 |
-
load_in_8bit: false
|
25 |
-
load_in_4bit: false
|
26 |
-
strict: false
|
27 |
-
|
28 |
-
datasets:
|
29 |
-
- path: practical-dreamer/RPGPT_PublicDomain-alpaca
|
30 |
-
type: alpaca
|
31 |
-
format: "[INST] {instruction} [/INST]"
|
32 |
-
no_input_format: "[INST] {instruction} [/INST]"
|
33 |
-
|
34 |
-
datasets:
|
35 |
-
- path: shuyuej/metamath_gsm8k
|
36 |
-
type: jeopardy
|
37 |
-
format: "[INST] {instruction} [/INST]"
|
38 |
-
no_input_format: "[INST] {instruction} [/INST]"
|
39 |
-
|
40 |
-
datasets:
|
41 |
-
- path: NeuralNovel/Neural-DPO
|
42 |
-
type:
|
43 |
-
system_prompt: ""
|
44 |
-
field_system: system
|
45 |
-
field_instruction: chosen
|
46 |
-
field_output: chosen
|
47 |
-
format: "[INST] {instruction} [/INST]"
|
48 |
-
no_input_format: "[INST] {instruction} [/INST]"
|
49 |
-
|
50 |
-
dataset_prepared_path:
|
51 |
-
val_set_size: 0.05
|
52 |
-
output_dir: ./out
|
53 |
-
|
54 |
-
sequence_len: 8192
|
55 |
-
sample_packing: false
|
56 |
-
pad_to_sequence_len: true
|
57 |
-
eval_sample_packing: false
|
58 |
-
|
59 |
-
wandb_project:
|
60 |
-
wandb_entity:
|
61 |
-
wandb_watch:
|
62 |
-
wandb_name:
|
63 |
-
wandb_log_model:
|
64 |
-
|
65 |
-
gradient_accumulation_steps: 4
|
66 |
-
micro_batch_size: 2
|
67 |
-
num_epochs: 1
|
68 |
-
optimizer: adamw_bnb_8bit
|
69 |
-
lr_scheduler: cosine
|
70 |
-
learning_rate: 0.000005
|
71 |
-
|
72 |
-
train_on_inputs: false
|
73 |
-
group_by_length: false
|
74 |
-
bf16: auto
|
75 |
-
fp16:
|
76 |
-
tf32: false
|
77 |
-
|
78 |
-
gradient_checkpointing: true
|
79 |
-
early_stopping_patience:
|
80 |
-
resume_from_checkpoint:
|
81 |
-
local_rank:
|
82 |
-
logging_steps: 1
|
83 |
-
xformers_attention:
|
84 |
-
flash_attention: true
|
85 |
-
|
86 |
-
warmup_steps: 10
|
87 |
-
evals_per_epoch: 4
|
88 |
-
eval_table_size:
|
89 |
-
eval_max_new_tokens: 128
|
90 |
-
saves_per_epoch: 0
|
91 |
-
debug:
|
92 |
-
deepspeed:
|
93 |
-
weight_decay: 0.0
|
94 |
-
fsdp:
|
95 |
-
fsdp_config:
|
96 |
-
special_tokens:
|
97 |
-
bos_token: "<s>"
|
98 |
-
eos_token: "</s>"
|
99 |
-
unk_token: "<unk>"
|
100 |
-
|
101 |
-
```
|
102 |
-
|
103 |
-
</details><br>
|
104 |
-
|
105 |
-
# out
|
106 |
-
|
107 |
-
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
|
108 |
-
It achieves the following results on the evaluation set:
|
109 |
-
- Loss: 0.0000
|
110 |
-
|
111 |
-
## Model description
|
112 |
-
|
113 |
-
More information needed
|
114 |
-
|
115 |
-
## Intended uses & limitations
|
116 |
-
|
117 |
-
More information needed
|
118 |
-
|
119 |
-
## Training and evaluation data
|
120 |
-
|
121 |
-
More information needed
|
122 |
-
|
123 |
-
## Training procedure
|
124 |
-
|
125 |
-
### Training hyperparameters
|
126 |
-
|
127 |
-
The following hyperparameters were used during training:
|
128 |
-
- learning_rate: 5e-06
|
129 |
-
- train_batch_size: 2
|
130 |
-
- eval_batch_size: 2
|
131 |
-
- seed: 42
|
132 |
-
- gradient_accumulation_steps: 4
|
133 |
-
- total_train_batch_size: 8
|
134 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
135 |
-
- lr_scheduler_type: cosine
|
136 |
-
- lr_scheduler_warmup_steps: 10
|
137 |
-
- num_epochs: 1
|
138 |
-
|
139 |
-
### Training results
|
140 |
-
|
141 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
142 |
-
|:-------------:|:-----:|:----:|:---------------:|
|
143 |
-
| 0.2061 | 0.01 | 1 | 0.3139 |
|
144 |
-
| 0.0 | 0.25 | 32 | 0.0000 |
|
145 |
-
| 0.0 | 0.5 | 64 | 0.0010 |
|
146 |
-
| 0.0 | 0.76 | 96 | 0.0000 |
|
147 |
-
|
148 |
-
|
149 |
-
### Framework versions
|
150 |
-
|
151 |
-
- Transformers 4.38.0.dev0
|
152 |
-
- Pytorch 2.2.0+cu121
|
153 |
-
- Datasets 2.17.1
|
154 |
-
- Tokenizers 0.15.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
.ipynb_checkpoints/config-checkpoint.json
DELETED
@@ -1,26 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "mistralai/Mistral-7B-v0.1",
|
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": "4.38.0.dev0",
|
24 |
-
"use_cache": false,
|
25 |
-
"vocab_size": 32000
|
26 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|