Hugging Face's logo

Wing4
/
llama3-8b-sentiment-analyzer

Text Generation
PEFT
TensorBoard
Safetensors
Transformers
llama
lora
conversational
text-generation-inference
Model card Files
xet
Metrics Community
Wing4 commited on
Commit
98794ef
·
verified ·
1 Parent(s): fce7afb

Wing4/llama3-8b-sentiment-3class-final

Browse files
Files changed (5) hide show
  1. README.md +5 -11
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +1 -1
  4. runs/Aug17_13-34-29_842a2f1f8506/events.out.tfevents.1755437671.842a2f1f8506.406.0 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -19,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.0704
23
 
24
  ## Model description
25
 
@@ -53,16 +53,10 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss |
55
  |:-------------:|:------:|:----:|:---------------:|
56
- | 0.074 | 0.0980 | 250 | 0.0805 |
57
- | 0.0733 | 0.1960 | 500 | 0.0744 |
58
- | 0.0727 | 0.2941 | 750 | 0.0723 |
59
- | 0.0699 | 0.3921 | 1000 | 0.0729 |
60
- | 0.0701 | 0.4901 | 1250 | 0.0717 |
61
- | 0.0702 | 0.5881 | 1500 | 0.0709 |
62
- | 0.0703 | 0.6861 | 1750 | 0.0712 |
63
- | 0.0688 | 0.7842 | 2000 | 0.0712 |
64
- | 0.0701 | 0.8822 | 2250 | 0.0707 |
65
- | 0.0683 | 0.9802 | 2500 | 0.0704 |
66
 
67
 
68
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.0790
23
 
24
  ## Model description
25
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss |
55
  |:-------------:|:------:|:----:|:---------------:|
56
+ | 0.0959 | 0.2116 | 250 | 0.1097 |
57
+ | 0.0869 | 0.4233 | 500 | 0.0841 |
58
+ | 0.08 | 0.6349 | 750 | 0.0805 |
59
+ | 0.0797 | 0.8466 | 1000 | 0.0790 |
 
 
 
 
 
 
60
 
61
 
62
  ### Framework versions
adapter_config.json CHANGED
@@ -25,10 +25,10 @@
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
 
28
  "k_proj",
29
- "v_proj",
30
  "q_proj",
31
- "o_proj"
32
  ],
33
  "target_parameters": null,
34
  "task_type": "CAUSAL_LM",
 
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
28
+ "o_proj",
29
  "k_proj",
 
30
  "q_proj",
31
+ "v_proj"
32
  ],
33
  "target_parameters": null,
34
  "task_type": "CAUSAL_LM",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ce05ed3a8d65436c1608bdde57229293dc214e59de191cca49c8ed8b2f8cbc1
3
  size 54560368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dd335b0c2f421eb712e058e9684153d8e46e66df8b5657586cb72165571bf12
3
  size 54560368
runs/Aug17_13-34-29_842a2f1f8506/events.out.tfevents.1755437671.842a2f1f8506.406.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22c4ac79fb7cf4033dbddd0937050ab750cd7d2063536d91717aea498287cc0e
3
+ size 17040
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1996b912e7f6f53b6ac85cdda6323b6faeeec81f25c241a4b606be33a0132a7d
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3e3e3fe69210a639b02b34172ed31f41c0466d055829064d48b2d2a622f1f40
3
  size 5368