Update README.md
Browse files
README.md
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
---
|
2 |
-
license:
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
- generated_from_trainer
|
@@ -13,86 +13,10 @@ model-index:
|
|
13 |
should probably proofread and complete it, then remove this comment. -->
|
14 |
|
15 |
[<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)
|
16 |
-
<details><summary>See axolotl config</summary>
|
17 |
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
model_type: LlamaForCausalLM
|
22 |
-
tokenizer_type: AutoTokenizer
|
23 |
-
|
24 |
-
load_in_8bit: false
|
25 |
-
load_in_4bit: false
|
26 |
-
strict: false
|
27 |
-
|
28 |
-
datasets:
|
29 |
-
- path: jondurbin/airoboros-3.2
|
30 |
-
type: sharegpt
|
31 |
-
|
32 |
-
dataset_prepared_path:
|
33 |
-
val_set_size: 0.05
|
34 |
-
output_dir: ./out
|
35 |
-
|
36 |
-
sequence_len: 8192
|
37 |
-
sample_packing: true
|
38 |
-
pad_to_sequence_len: true
|
39 |
-
|
40 |
-
adapter: lora
|
41 |
-
lora_model_dir:
|
42 |
-
lora_r: 32
|
43 |
-
lora_alpha: 16
|
44 |
-
lora_dropout: 0.05
|
45 |
-
lora_target_linear: true
|
46 |
-
lora_fan_in_fan_out:
|
47 |
-
|
48 |
-
wandb_project: llama3
|
49 |
-
wandb_entity: saucam
|
50 |
-
wandb_watch: all
|
51 |
-
wandb_name: llama3-cosmo-run-1
|
52 |
-
wandb_log_model: "end"
|
53 |
-
|
54 |
-
gradient_accumulation_steps: 4
|
55 |
-
micro_batch_size: 2
|
56 |
-
num_epochs: 1
|
57 |
-
optimizer: adamw_bnb_8bit
|
58 |
-
lr_scheduler: cosine
|
59 |
-
learning_rate: 0.0002
|
60 |
-
|
61 |
-
train_on_inputs: false
|
62 |
-
group_by_length: false
|
63 |
-
bf16: auto
|
64 |
-
fp16:
|
65 |
-
tf32: false
|
66 |
-
|
67 |
-
gradient_checkpointing: true
|
68 |
-
early_stopping_patience:
|
69 |
-
resume_from_checkpoint:
|
70 |
-
local_rank:
|
71 |
-
logging_steps: 1
|
72 |
-
xformers_attention:
|
73 |
-
flash_attention: true
|
74 |
-
s2_attention:
|
75 |
-
|
76 |
-
warmup_steps: 10
|
77 |
-
evals_per_epoch: 4
|
78 |
-
eval_table_size:
|
79 |
-
eval_max_new_tokens: 128
|
80 |
-
saves_per_epoch: 1
|
81 |
-
debug:
|
82 |
-
deepspeed:
|
83 |
-
weight_decay: 0.0
|
84 |
-
fsdp:
|
85 |
-
fsdp_config:
|
86 |
-
special_tokens:
|
87 |
-
pad_token: <|end_of_text|>
|
88 |
-
|
89 |
-
```
|
90 |
-
|
91 |
-
</details><br>
|
92 |
-
|
93 |
-
# out
|
94 |
-
|
95 |
-
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
|
96 |
It achieves the following results on the evaluation set:
|
97 |
- Loss: 0.8437
|
98 |
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
13 |
should probably proofread and complete it, then remove this comment. -->
|
14 |
|
15 |
[<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)
|
|
|
16 |
|
17 |
+
# Details
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the jondurbin/airoboros-3.2 dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
It achieves the following results on the evaluation set:
|
21 |
- Loss: 0.8437
|
22 |
|