Hugging Face's logo

llm-wizard
/
llama38binstruct_summarize

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
llm-wizard commited on
Commit
e06d11e
•
1 Parent(s): 1f17daa

ai-maker-space/llama38binstruct-summary-100s

Browse files
Files changed (5) hide show
  1. README.md +5 -5
  2. adapter_config.json +6 -1
  3. adapter_model.safetensors +2 -2
  4. runs/Jun11_22-41-53_cbe9160191fc/events.out.tfevents.1718145721.cbe9160191fc.22684.1 +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: 1.3068
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
- | 1.6136 | 1.1905 | 25 | 1.2093 |
56
- | 1.2326 | 2.3810 | 50 | 1.1685 |
57
- | 0.8728 | 3.5714 | 75 | 1.2155 |
58
- | 0.722 | 4.7619 | 100 | 1.3068 |
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: 1.6753
24
 
25
  ## Model description
26
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:------:|:----:|:---------------:|
55
+ | 1.4436 | 1.1905 | 25 | 1.0958 |
56
+ | 0.5989 | 2.3810 | 50 | 1.2958 |
57
+ | 0.2448 | 3.5714 | 75 | 1.5235 |
58
+ | 0.099 | 4.7619 | 100 | 1.6753 |
59
 
60
 
61
  ### Framework versions
adapter_config.json CHANGED
@@ -20,8 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "q_proj",
24
- "v_proj"
 
 
 
 
25
  ],
26
  "task_type": "CAUSAL_LM",
27
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "down_proj",
24
  "q_proj",
25
+ "v_proj",
26
+ "up_proj",
27
+ "gate_proj",
28
+ "k_proj",
29
+ "o_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:ed572566638e45a957887794101f1784b4779cb378d912604488e575f671d09d
3
- size 27280152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e830cf60d62fd1beae745801b2eebd6ca2035f72dbcf013a55efb8625a87d86d
3
+ size 167832240
runs/Jun11_22-41-53_cbe9160191fc/events.out.tfevents.1718145721.cbe9160191fc.22684.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e930e2c8e0f71b9188b4dd647702e7809f7c587bca541d779b5eeecbcf338d05
3
+ size 9237
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb4edad8e2dea54255292b49a715e17bf490841238f31af75d3a5086e9726aaa
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ec406f70a4db0f7b6ca78d6f1e68a2e38a26462493b4efaf8ca0e9819f20c0f
3
  size 5368