End of training
Browse files- README.md +117 -0
- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- runs/Sep23_10-07-52_sammie/events.out.tfevents.1727108974.sammie.1130.0 +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +42 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- sft
|
7 |
+
- unsloth
|
8 |
+
- generated_from_trainer
|
9 |
+
base_model: unsloth/tinyllama-bnb-4bit
|
10 |
+
datasets:
|
11 |
+
- generator
|
12 |
+
model-index:
|
13 |
+
- name: MunicipalPredictionModel-TinyLlama
|
14 |
+
results: []
|
15 |
+
---
|
16 |
+
|
17 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
18 |
+
should probably proofread and complete it, then remove this comment. -->
|
19 |
+
|
20 |
+
# MunicipalPredictionModel-TinyLlama
|
21 |
+
|
22 |
+
This model is a fine-tuned version of [unsloth/tinyllama-bnb-4bit](https://huggingface.co/unsloth/tinyllama-bnb-4bit) on the generator dataset.
|
23 |
+
It achieves the following results on the evaluation set:
|
24 |
+
- Loss: 1.2394
|
25 |
+
|
26 |
+
## Model description
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Intended uses & limitations
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training and evaluation data
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training procedure
|
39 |
+
|
40 |
+
### Training hyperparameters
|
41 |
+
|
42 |
+
The following hyperparameters were used during training:
|
43 |
+
- learning_rate: 0.0002
|
44 |
+
- train_batch_size: 8
|
45 |
+
- eval_batch_size: 8
|
46 |
+
- seed: 42
|
47 |
+
- gradient_accumulation_steps: 4
|
48 |
+
- total_train_batch_size: 32
|
49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
+
- lr_scheduler_type: linear
|
51 |
+
- num_epochs: 3
|
52 |
+
- mixed_precision_training: Native AMP
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
57 |
+
|:-------------:|:------:|:----:|:---------------:|
|
58 |
+
| 1.788 | 0.0578 | 10 | 1.4309 |
|
59 |
+
| 1.3849 | 0.1156 | 20 | 1.3661 |
|
60 |
+
| 1.3425 | 0.1734 | 30 | 1.3366 |
|
61 |
+
| 1.3263 | 0.2312 | 40 | 1.3180 |
|
62 |
+
| 1.3223 | 0.2890 | 50 | 1.3034 |
|
63 |
+
| 1.293 | 0.3468 | 60 | 1.2890 |
|
64 |
+
| 1.2815 | 0.4046 | 70 | 1.2816 |
|
65 |
+
| 1.275 | 0.4624 | 80 | 1.2763 |
|
66 |
+
| 1.2765 | 0.5202 | 90 | 1.2676 |
|
67 |
+
| 1.2786 | 0.5780 | 100 | 1.2635 |
|
68 |
+
| 1.25 | 0.6358 | 110 | 1.2576 |
|
69 |
+
| 1.2476 | 0.6936 | 120 | 1.2524 |
|
70 |
+
| 1.2479 | 0.7514 | 130 | 1.2491 |
|
71 |
+
| 1.2497 | 0.8092 | 140 | 1.2437 |
|
72 |
+
| 1.2362 | 0.8671 | 150 | 1.2409 |
|
73 |
+
| 1.2511 | 0.9249 | 160 | 1.2363 |
|
74 |
+
| 1.2368 | 0.9827 | 170 | 1.2335 |
|
75 |
+
| 1.1279 | 1.0405 | 180 | 1.2404 |
|
76 |
+
| 1.0929 | 1.0983 | 190 | 1.2408 |
|
77 |
+
| 1.0803 | 1.1561 | 200 | 1.2426 |
|
78 |
+
| 1.0939 | 1.2139 | 210 | 1.2391 |
|
79 |
+
| 1.0869 | 1.2717 | 220 | 1.2364 |
|
80 |
+
| 1.084 | 1.3295 | 230 | 1.2337 |
|
81 |
+
| 1.0967 | 1.3873 | 240 | 1.2314 |
|
82 |
+
| 1.0922 | 1.4451 | 250 | 1.2287 |
|
83 |
+
| 1.0774 | 1.5029 | 260 | 1.2264 |
|
84 |
+
| 1.0825 | 1.5607 | 270 | 1.2247 |
|
85 |
+
| 1.08 | 1.6185 | 280 | 1.2217 |
|
86 |
+
| 1.0828 | 1.6763 | 290 | 1.2174 |
|
87 |
+
| 1.0791 | 1.7341 | 300 | 1.2169 |
|
88 |
+
| 1.0907 | 1.7919 | 310 | 1.2148 |
|
89 |
+
| 1.0748 | 1.8497 | 320 | 1.2137 |
|
90 |
+
| 1.082 | 1.9075 | 330 | 1.2104 |
|
91 |
+
| 1.0753 | 1.9653 | 340 | 1.2081 |
|
92 |
+
| 1.0165 | 2.0231 | 350 | 1.2490 |
|
93 |
+
| 0.9266 | 2.0809 | 360 | 1.2431 |
|
94 |
+
| 0.9239 | 2.1387 | 370 | 1.2440 |
|
95 |
+
| 0.9207 | 2.1965 | 380 | 1.2443 |
|
96 |
+
| 0.9218 | 2.2543 | 390 | 1.2485 |
|
97 |
+
| 0.9262 | 2.3121 | 400 | 1.2447 |
|
98 |
+
| 0.9246 | 2.3699 | 410 | 1.2463 |
|
99 |
+
| 0.9145 | 2.4277 | 420 | 1.2422 |
|
100 |
+
| 0.9178 | 2.4855 | 430 | 1.2457 |
|
101 |
+
| 0.9229 | 2.5434 | 440 | 1.2421 |
|
102 |
+
| 0.9205 | 2.6012 | 450 | 1.2429 |
|
103 |
+
| 0.9184 | 2.6590 | 460 | 1.2436 |
|
104 |
+
| 0.93 | 2.7168 | 470 | 1.2395 |
|
105 |
+
| 0.9111 | 2.7746 | 480 | 1.2418 |
|
106 |
+
| 0.9125 | 2.8324 | 490 | 1.2396 |
|
107 |
+
| 0.9268 | 2.8902 | 500 | 1.2389 |
|
108 |
+
| 0.9148 | 2.9480 | 510 | 1.2394 |
|
109 |
+
|
110 |
+
|
111 |
+
### Framework versions
|
112 |
+
|
113 |
+
- PEFT 0.12.0
|
114 |
+
- Transformers 4.43.4
|
115 |
+
- Pytorch 2.2.0+cu121
|
116 |
+
- Datasets 2.18.0
|
117 |
+
- Tokenizers 0.19.0
|
adapter_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "unsloth/tinyllama-bnb-4bit",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.1,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 128,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"mlp.gate_up_proj",
|
24 |
+
"self_attn.qkv_proj.weight",
|
25 |
+
"self_attn.o_proj.weight",
|
26 |
+
"mlp.down_proj"
|
27 |
+
],
|
28 |
+
"task_type": "CAUSAL_LM",
|
29 |
+
"use_dora": false,
|
30 |
+
"use_rslora": false
|
31 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f80b9db16e5fed0bf6ecae0adbad111753a18767096b07670e575d400522b07e
|
3 |
+
size 403743472
|
runs/Sep23_10-07-52_sammie/events.out.tfevents.1727108974.sammie.1130.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:891e814e65ad449c904aed97cf4d53b507c4146eb988b5ed3070905dccf9a2b5
|
3 |
+
size 30783
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
}
|
30 |
+
},
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"legacy": false,
|
35 |
+
"model_max_length": 2048,
|
36 |
+
"pad_token": "</s>",
|
37 |
+
"padding_side": "left",
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": false
|
42 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5c8d4ca54c402a351b455c5aa2a1c419b359bb8071d4496b4ab4bdb1d95dda2
|
3 |
+
size 5560
|