Hugging Face's logo

defsound
/
llama38binstruct_summarize

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
defsound commited on
Commit
88f898f
•
1 Parent(s): 8f97bec

defsound/llama38binstruct-summary-100s

Browse files
Files changed (5) hide show
  1. README.md +5 -5
  2. adapter_config.json +5 -5
  3. adapter_model.safetensors +1 -1
  4. runs/Jun13_18-48-13_afe07e31b1f5/events.out.tfevents.1718304527.afe07e31b1f5.362.0 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 2.1544
24
 
25
  ## Model description
26
 
@@ -52,10 +52,10 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:------:|:----:|:---------------:|
55
- | 1.267 | 1.3889 | 25 | 1.4665 |
56
- | 0.465 | 2.7778 | 50 | 1.6850 |
57
- | 0.2423 | 4.1667 | 75 | 1.9029 |
58
- | 0.0544 | 5.5556 | 100 | 2.1544 |
59
 
60
 
61
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 1.6204
24
 
25
  ## Model description
26
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:------:|:----:|:---------------:|
55
+ | 1.351 | 1.1905 | 25 | 1.2017 |
56
+ | 0.5869 | 2.3810 | 50 | 1.4451 |
57
+ | 0.226 | 3.5714 | 75 | 1.6767 |
58
+ | 0.1156 | 4.7619 | 100 | 1.6204 |
59
 
60
 
61
  ### Framework versions
adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "q_proj",
24
- "down_proj",
25
- "k_proj",
26
- "v_proj",
27
  "o_proj",
 
28
  "up_proj",
29
- "gate_proj"
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "gate_proj",
 
 
 
24
  "o_proj",
25
+ "down_proj",
26
  "up_proj",
27
+ "v_proj",
28
+ "k_proj",
29
+ "q_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43e8a417bf142ff59ed552f5c6e742765118b89c69ddf38433b10336987185b0
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a8e3a279a56567ecaf57c77298c3eb7d94ea03309517b887f0483683598bb77
3
  size 167832240
runs/Jun13_18-48-13_afe07e31b1f5/events.out.tfevents.1718304527.afe07e31b1f5.362.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b751962ac7f142f77c2600bc02d84e57914dce0d585bc6e2df307cba7ce06f4e
3
+ size 9238
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ba14c8ca0db26a029c81ba4a6db34a6b4fd6748a297c6b03bdbeafbb2ad933d
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7c1f9c58b20553c0bb1fb41ff915c8e2cdced2dda45e14af5a6bbac3d73847c
3
  size 5368