Manish Singh commited on
Commit
a34e060
·
verified ·
1 Parent(s): 02885bb

End of training

Browse files
Files changed (3) hide show
  1. README.md +13 -13
  2. adapter_config.json +3 -3
  3. adapter_model.safetensors +1 -1
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- base_model: meta-llama/Llama-2-7b-hf
3
  library_name: peft
4
  license: llama2
5
  tags:
@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # outputs
16
 
17
- This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 1.3676
20
 
21
  ## Model description
22
 
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
- | 3.2385 | 0.0134 | 10 | 2.4588 |
55
- | 1.9987 | 0.0267 | 20 | 1.7020 |
56
- | 1.3144 | 0.0401 | 30 | 1.5073 |
57
- | 1.1871 | 0.0535 | 40 | 1.4545 |
58
- | 1.1943 | 0.0668 | 50 | 1.4239 |
59
- | 1.2441 | 0.0802 | 60 | 1.4004 |
60
- | 1.3645 | 0.0936 | 70 | 1.3822 |
61
- | 1.2 | 0.1069 | 80 | 1.3748 |
62
- | 1.1308 | 0.1203 | 90 | 1.3696 |
63
- | 1.1587 | 0.1336 | 100 | 1.3676 |
64
 
65
 
66
  ### Framework versions
 
1
  ---
2
+ base_model: meta-llama/Llama-2-7b-chat-hf
3
  library_name: peft
4
  license: llama2
5
  tags:
 
14
 
15
  # outputs
16
 
17
+ This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 1.4173
20
 
21
  ## Model description
22
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
+ | 3.6173 | 0.0134 | 10 | 2.3897 |
55
+ | 2.2715 | 0.0267 | 20 | 1.7717 |
56
+ | 1.7437 | 0.0401 | 30 | 1.5891 |
57
+ | 1.3236 | 0.0535 | 40 | 1.5109 |
58
+ | 1.3035 | 0.0668 | 50 | 1.4715 |
59
+ | 1.2304 | 0.0802 | 60 | 1.4510 |
60
+ | 1.2023 | 0.0936 | 70 | 1.4357 |
61
+ | 1.37 | 0.1069 | 80 | 1.4268 |
62
+ | 1.2943 | 0.1203 | 90 | 1.4199 |
63
+ | 1.3791 | 0.1336 | 100 | 1.4173 |
64
 
65
 
66
  ### Framework versions
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
@@ -20,8 +20,8 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "v_proj",
24
- "q_proj"
25
  ],
26
  "task_type": "CAUSAL_LM",
27
  "use_dora": false,
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
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,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a5436b96e0ed039a98e86a90f1a1908bf1aff5e178286c5e18c9d9498a22eb3
3
  size 16794200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d29afe4213fa645435bdfb814cfdeade8cf010eb12bcd75ffbf807a401381fbb
3
  size 16794200