Model save
Browse files- README.md +121 -0
- generation_config.json +6 -0
- model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: pszemraj/verysmol_llama-v10-rw3m_dd
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: verysmol_llama-v10-rw3m_dd-knowledge-inoc-concat-v1-vN
|
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 |
+
# verysmol_llama-v10-rw3m_dd-knowledge-inoc-concat-v1-vN
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [pszemraj/verysmol_llama-v10-rw3m_dd](https://huggingface.co/pszemraj/verysmol_llama-v10-rw3m_dd) on the None dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 2.8876
|
21 |
+
- Accuracy: 0.4502
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 0.00014
|
41 |
+
- train_batch_size: 16
|
42 |
+
- eval_batch_size: 16
|
43 |
+
- seed: 17514
|
44 |
+
- gradient_accumulation_steps: 8
|
45 |
+
- total_train_batch_size: 128
|
46 |
+
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-06
|
47 |
+
- lr_scheduler_type: inverse_sqrt
|
48 |
+
- lr_scheduler_warmup_ratio: 0.05
|
49 |
+
- num_epochs: 2.0
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
55 |
+
| 3.0681 | 0.03 | 150 | 3.0689 | 0.4259 |
|
56 |
+
| 3.0113 | 0.07 | 300 | 3.0433 | 0.4278 |
|
57 |
+
| 2.9468 | 0.1 | 450 | 3.0362 | 0.4288 |
|
58 |
+
| 3.0162 | 0.13 | 600 | 3.0148 | 0.4326 |
|
59 |
+
| 2.9531 | 0.17 | 750 | 3.0012 | 0.4341 |
|
60 |
+
| 2.9282 | 0.2 | 900 | 2.9923 | 0.4358 |
|
61 |
+
| 2.9485 | 0.23 | 1050 | 2.9845 | 0.4357 |
|
62 |
+
| 2.9365 | 0.27 | 1200 | 2.9749 | 0.4375 |
|
63 |
+
| 2.8875 | 0.3 | 1350 | 2.9652 | 0.4391 |
|
64 |
+
| 2.8874 | 0.33 | 1500 | 2.9619 | 0.4402 |
|
65 |
+
| 2.8733 | 0.37 | 1650 | 2.9574 | 0.4408 |
|
66 |
+
| 2.8541 | 0.4 | 1800 | 2.9536 | 0.4403 |
|
67 |
+
| 2.8958 | 0.43 | 1950 | 2.9491 | 0.4414 |
|
68 |
+
| 2.8404 | 0.47 | 2100 | 2.9434 | 0.4427 |
|
69 |
+
| 2.8635 | 0.5 | 2250 | 2.9404 | 0.4425 |
|
70 |
+
| 2.9031 | 0.53 | 2400 | 2.9369 | 0.4428 |
|
71 |
+
| 2.8237 | 0.57 | 2550 | 2.9330 | 0.4440 |
|
72 |
+
| 2.832 | 0.6 | 2700 | 2.9318 | 0.4444 |
|
73 |
+
| 2.8566 | 0.63 | 2850 | 2.9305 | 0.4450 |
|
74 |
+
| 2.8817 | 0.67 | 3000 | 2.9286 | 0.4443 |
|
75 |
+
| 2.8733 | 0.7 | 3150 | 2.9268 | 0.4442 |
|
76 |
+
| 2.8009 | 0.73 | 3300 | 2.9227 | 0.4457 |
|
77 |
+
| 2.9292 | 0.77 | 3450 | 2.9229 | 0.4450 |
|
78 |
+
| 2.8562 | 0.8 | 3600 | 2.9193 | 0.4456 |
|
79 |
+
| 2.8441 | 0.83 | 3750 | 2.9188 | 0.4460 |
|
80 |
+
| 2.904 | 0.87 | 3900 | 2.9171 | 0.4458 |
|
81 |
+
| 2.857 | 0.9 | 4050 | 2.9140 | 0.4461 |
|
82 |
+
| 2.8344 | 0.93 | 4200 | 2.9134 | 0.4467 |
|
83 |
+
| 2.8382 | 0.97 | 4350 | 2.9122 | 0.4467 |
|
84 |
+
| 2.8227 | 1.0 | 4500 | 2.9104 | 0.4468 |
|
85 |
+
| 2.8121 | 1.03 | 4650 | 2.9099 | 0.4472 |
|
86 |
+
| 2.8127 | 1.07 | 4800 | 2.9082 | 0.4473 |
|
87 |
+
| 2.8013 | 1.1 | 4950 | 2.9084 | 0.4478 |
|
88 |
+
| 2.7983 | 1.14 | 5100 | 2.9069 | 0.4474 |
|
89 |
+
| 2.811 | 1.17 | 5250 | 2.9076 | 0.4480 |
|
90 |
+
| 2.7807 | 1.2 | 5400 | 2.9065 | 0.4471 |
|
91 |
+
| 2.8512 | 1.24 | 5550 | 2.9056 | 0.4483 |
|
92 |
+
| 2.8146 | 1.27 | 5700 | 2.9049 | 0.4478 |
|
93 |
+
| 2.8101 | 1.3 | 5850 | 2.9024 | 0.4482 |
|
94 |
+
| 2.7968 | 1.34 | 6000 | 2.9005 | 0.4484 |
|
95 |
+
| 2.8197 | 1.37 | 6150 | 2.9001 | 0.4481 |
|
96 |
+
| 2.8035 | 1.4 | 6300 | 2.8997 | 0.4488 |
|
97 |
+
| 2.7905 | 1.44 | 6450 | 2.8996 | 0.4488 |
|
98 |
+
| 2.8239 | 1.47 | 6600 | 2.8982 | 0.4487 |
|
99 |
+
| 2.8579 | 1.5 | 6750 | 2.8975 | 0.4492 |
|
100 |
+
| 2.7996 | 1.54 | 6900 | 2.8960 | 0.4492 |
|
101 |
+
| 2.8337 | 1.57 | 7050 | 2.8984 | 0.4490 |
|
102 |
+
| 2.8087 | 1.6 | 7200 | 2.8959 | 0.4492 |
|
103 |
+
| 2.8066 | 1.64 | 7350 | 2.8952 | 0.4499 |
|
104 |
+
| 2.7991 | 1.67 | 7500 | 2.8950 | 0.4492 |
|
105 |
+
| 2.8215 | 1.7 | 7650 | 2.8943 | 0.4496 |
|
106 |
+
| 2.7714 | 1.74 | 7800 | 2.8914 | 0.4501 |
|
107 |
+
| 2.8132 | 1.77 | 7950 | 2.8913 | 0.4500 |
|
108 |
+
| 2.8505 | 1.8 | 8100 | 2.8906 | 0.4502 |
|
109 |
+
| 2.8294 | 1.84 | 8250 | 2.8901 | 0.4502 |
|
110 |
+
| 2.7977 | 1.87 | 8400 | 2.8891 | 0.4499 |
|
111 |
+
| 2.7501 | 1.9 | 8550 | 2.8878 | 0.4505 |
|
112 |
+
| 2.8038 | 1.94 | 8700 | 2.8883 | 0.4504 |
|
113 |
+
| 2.7547 | 1.97 | 8850 | 2.8876 | 0.4502 |
|
114 |
+
|
115 |
+
|
116 |
+
### Framework versions
|
117 |
+
|
118 |
+
- Transformers 4.33.3
|
119 |
+
- Pytorch 2.2.0.dev20231017+cu121
|
120 |
+
- Datasets 2.14.5
|
121 |
+
- Tokenizers 0.13.3
|
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": "4.33.3"
|
6 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 232292512
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ea330c0052600266e95d7982e8edc79a84647cdaab554d3785e81cb8376b8dc
|
3 |
size 232292512
|