Hugging Face's logo

VikrantRamesh
/
Llama-2-CN

Text Generation
Transformers
TensorBoard
Safetensors
llama
Generated from Trainer
text-generation-inference
Inference Endpoints
4-bit precision
bitsandbytes
Model card Files Metrics Community
VikrantRamesh commited on
Commit
76f0c2e
·
verified ·
1 Parent(s): 4e52886

Model save

Browse files
Files changed (6) hide show
  1. README.md +13 -23
  2. adapter_config.json +3 -2
  3. adapter_model.safetensors +1 -1
  4. runs/Mar17_15-20-21_485a833b00a5/events.out.tfevents.1710688822.485a833b00a5.160.0 +3 -0
  5. runs/Mar17_15-20-21_485a833b00a5/events.out.tfevents.1710692008.485a833b00a5.160.1 +3 -0
  6. training_args.bin +1 -1
README.md CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  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.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 2.1092
18
 
19
  ## Model description
20
 
@@ -39,37 +39,27 @@ The following hyperparameters were used during training:
39
  - seed: 42
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
42
- - training_steps: 200
43
 
44
  ### Training results
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
- | 2.7967 | 0.22 | 10 | 2.7779 |
49
- | 2.5905 | 0.44 | 20 | 2.5530 |
50
- | 2.3863 | 0.67 | 30 | 2.4699 |
51
- | 2.3334 | 0.89 | 40 | 2.3923 |
52
- | 2.313 | 1.11 | 50 | 2.3418 |
53
- | 2.0965 | 1.33 | 60 | 2.2902 |
54
- | 2.2402 | 1.56 | 70 | 2.2599 |
55
- | 2.213 | 1.78 | 80 | 2.2329 |
56
- | 2.1118 | 2.0 | 90 | 2.2142 |
57
- | 2.071 | 2.22 | 100 | 2.1969 |
58
- | 2.0024 | 2.44 | 110 | 2.1846 |
59
- | 2.0814 | 2.67 | 120 | 2.1692 |
60
- | 2.0853 | 2.89 | 130 | 2.1540 |
61
- | 1.9573 | 3.11 | 140 | 2.1419 |
62
- | 1.9231 | 3.33 | 150 | 2.1358 |
63
- | 1.921 | 3.56 | 160 | 2.1240 |
64
- | 1.9618 | 3.78 | 170 | 2.1166 |
65
- | 2.0817 | 4.0 | 180 | 2.1120 |
66
- | 2.0458 | 4.22 | 190 | 2.1102 |
67
- | 1.9076 | 4.44 | 200 | 2.1092 |
68
 
69
 
70
  ### Framework versions
71
 
72
  - Transformers 4.39.0.dev0
73
- - Pytorch 2.1.0+cu121
74
  - Datasets 2.18.0
75
  - Tokenizers 0.15.2
 
14
 
15
  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.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 2.4423
18
 
19
  ## Model description
20
 
 
39
  - seed: 42
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
42
+ - training_steps: 100
43
 
44
  ### Training results
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
+ | 3.3431 | 0.03 | 10 | 3.1212 |
49
+ | 2.8976 | 0.05 | 20 | 2.7770 |
50
+ | 2.6878 | 0.08 | 30 | 2.6526 |
51
+ | 2.6344 | 0.1 | 40 | 2.5690 |
52
+ | 2.5165 | 0.13 | 50 | 2.5212 |
53
+ | 2.5377 | 0.15 | 60 | 2.4917 |
54
+ | 2.4577 | 0.18 | 70 | 2.4712 |
55
+ | 2.4309 | 0.21 | 80 | 2.4562 |
56
+ | 2.3986 | 0.23 | 90 | 2.4465 |
57
+ | 2.4445 | 0.26 | 100 | 2.4423 |
 
 
 
 
 
 
 
 
 
 
58
 
59
 
60
  ### Framework versions
61
 
62
  - Transformers 4.39.0.dev0
63
+ - Pytorch 2.2.1+cu121
64
  - Datasets 2.18.0
65
  - Tokenizers 0.15.2
adapter_config.json CHANGED
@@ -6,6 +6,7 @@
6
  "fan_in_fan_out": false,
7
  "inference_mode": false,
8
  "init_lora_weights": true,
 
9
  "layers_pattern": null,
10
  "layers_to_transform": null,
11
  "loftq_config": {},
@@ -19,8 +20,8 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "q_proj",
23
- "v_proj"
24
  ],
25
  "task_type": "CAUSAL_LM",
26
  "use_dora": false,
 
6
  "fan_in_fan_out": false,
7
  "inference_mode": false,
8
  "init_lora_weights": true,
9
+ "layer_replication": null,
10
  "layers_pattern": null,
11
  "layers_to_transform": null,
12
  "loftq_config": {},
 
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,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cfd9d88b14058fbf3ad8ce7f236add4e59c361dba6448a89d28a1cd7aaa299d
3
  size 16794200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed7d6de8b7c52bacd210c20b16faf33905e39b10e5ca18f9a2cbd91b0493a979
3
  size 16794200
runs/Mar17_15-20-21_485a833b00a5/events.out.tfevents.1710688822.485a833b00a5.160.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d19dbb32d4a95c0220438c50528a10848fa59e65ebba69ee233d9ee1fbf74446
3
+ size 10154
runs/Mar17_15-20-21_485a833b00a5/events.out.tfevents.1710692008.485a833b00a5.160.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b040b90e368ebe0af6f66de3061df2c474fb78dd09c7844aac4da6867e24993e
3
+ size 354
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4a6eff38eb5e666f4a74d12cf9f1f08bca89d3040a9ba99e04778a0b5f7043c
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cddfc46772e5e0a83d0d3f74a3c7cc05afdb6eafd14efd3a5696416970e40ab
3
  size 4856