Sanjeevl commited on
Commit
31bbfe0
1 Parent(s): 4391b47

sanjeevl/llama38binstruct-summary-100s

Browse files
README.md CHANGED
@@ -1,13 +1,13 @@
1
  ---
2
- license: other
 
 
3
  library_name: peft
 
4
  tags:
5
  - trl
6
  - sft
7
  - generated_from_trainer
8
- base_model: NousResearch/Meta-Llama-3-8B-Instruct
9
- datasets:
10
- - generator
11
  model-index:
12
  - name: llama38binstruct_summarize
13
  results: []
@@ -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: 2.3460
24
 
25
  ## Model description
26
 
@@ -45,23 +45,23 @@ The following hyperparameters were used during training:
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: constant
48
- - lr_scheduler_warmup_steps: 0.03
49
  - training_steps: 100
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss |
54
- |:-------------:|:------:|:----:|:---------------:|
55
- | 1.5536 | 1.3889 | 25 | 1.5880 |
56
- | 0.6175 | 2.7778 | 50 | 1.8927 |
57
- | 0.2685 | 4.1667 | 75 | 1.9919 |
58
- | 0.0612 | 5.5556 | 100 | 2.3460 |
59
 
60
 
61
  ### Framework versions
62
 
63
  - PEFT 0.11.1
64
- - Transformers 4.41.2
65
  - Pytorch 2.3.0+cu121
66
  - Datasets 2.20.0
67
  - Tokenizers 0.19.1
 
1
  ---
2
+ base_model: NousResearch/Meta-Llama-3-8B-Instruct
3
+ datasets:
4
+ - generator
5
  library_name: peft
6
+ license: other
7
  tags:
8
  - trl
9
  - sft
10
  - generated_from_trainer
 
 
 
11
  model-index:
12
  - name: llama38binstruct_summarize
13
  results: []
 
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: 1.7929
24
 
25
  ## Model description
26
 
 
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: constant
48
+ - lr_scheduler_warmup_steps: 3
49
  - training_steps: 100
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss |
54
+ |:-------------:|:-----:|:----:|:---------------:|
55
+ | 1.5444 | 1.25 | 25 | 1.4502 |
56
+ | 0.4769 | 2.5 | 50 | 1.7111 |
57
+ | 0.2309 | 3.75 | 75 | 1.7707 |
58
+ | 0.13 | 5.0 | 100 | 1.7929 |
59
 
60
 
61
  ### Framework versions
62
 
63
  - PEFT 0.11.1
64
+ - Transformers 4.42.4
65
  - Pytorch 2.3.0+cu121
66
  - Datasets 2.20.0
67
  - Tokenizers 0.19.1
adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
23
  "down_proj",
 
24
  "gate_proj",
25
- "o_proj",
26
- "k_proj",
27
  "v_proj",
28
- "q_proj",
29
- "up_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "up_proj",
24
+ "k_proj",
25
  "down_proj",
26
+ "q_proj",
27
  "gate_proj",
 
 
28
  "v_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 sha256:003eaf659e67572b4002048d7feb424158449e22446c197ba8fd6a0c2ac55fe0
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6a8648d4b7e7bde406268bf26bfdd731a0862b15b596f49f6ec819664225192
3
  size 167832240
runs/Jul16_08-37-47_86f5e2bdd820/events.out.tfevents.1721119418.86f5e2bdd820.283.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42a944756f5097ad7d46ba92fb1f405fa895f75e407b608d831393edc853348f
3
+ size 9261
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69425bbb0ceb71772f12bd470389d94e1a482f642810773f1a86b80c2412f46c
3
- size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3d8d6456dbc62bf599621e8ac7136d792623beddb1a96f2197897c607abcba1
3
+ size 5432