Hugging Face's logo

Fishball02
/
llama-topical-chat

TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
Fishball02 commited on
Commit
d6dff42
·
1 Parent(s): 95dc00f

Fishball02/llama-topical-chat

Browse files
Files changed (8) hide show
  1. README.md +23 -7
  2. adapter_model.safetensors +1 -1
  3. runs/Nov10_01-01-47_69332eb5d77e/events.out.tfevents.1699578107.69332eb5d77e.14876.0 +3 -0
  4. runs/Nov10_01-03-01_69332eb5d77e/events.out.tfevents.1699578182.69332eb5d77e.14876.1 +3 -0
  5. runs/Nov10_01-06-45_69332eb5d77e/events.out.tfevents.1699578406.69332eb5d77e.14876.2 +3 -0
  6. runs/Nov10_01-08-23_69332eb5d77e/events.out.tfevents.1699578504.69332eb5d77e.14876.3 +3 -0
  7. runs/Nov10_01-10-41_69332eb5d77e/events.out.tfevents.1699578642.69332eb5d77e.14876.4 +3 -0
  8. training_args.bin +2 -2
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 the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 2.5527
18
 
19
  ## Model description
20
 
@@ -34,20 +34,36 @@ More information needed
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 2e-05
37
- - train_batch_size: 8
38
- - eval_batch_size: 8
39
  - seed: 42
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
42
- - num_epochs: 3.0
 
43
 
44
  ### Training results
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
- | No log | 1.0 | 147 | 2.8403 |
49
- | No log | 2.0 | 294 | 2.6048 |
50
- | No log | 3.0 | 441 | 2.5527 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51
 
52
 
53
  ### Framework versions
 
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 the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 2.2213
18
 
19
  ## Model description
20
 
 
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 2e-05
37
+ - train_batch_size: 4
38
+ - eval_batch_size: 4
39
  - seed: 42
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
42
+ - num_epochs: 4
43
+ - mixed_precision_training: Native AMP
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | 2.4511 | 0.21 | 256 | 2.3800 |
50
+ | 2.3704 | 0.43 | 512 | 2.3322 |
51
+ | 2.3548 | 0.64 | 768 | 2.2984 |
52
+ | 2.3161 | 0.86 | 1024 | 2.2793 |
53
+ | 2.2941 | 1.07 | 1280 | 2.2647 |
54
+ | 2.276 | 1.29 | 1536 | 2.2542 |
55
+ | 2.2891 | 1.5 | 1792 | 2.2462 |
56
+ | 2.2585 | 1.72 | 2048 | 2.2398 |
57
+ | 2.2395 | 1.93 | 2304 | 2.2357 |
58
+ | 2.2342 | 2.15 | 2560 | 2.2326 |
59
+ | 2.2343 | 2.36 | 2816 | 2.2311 |
60
+ | 2.217 | 2.58 | 3072 | 2.2277 |
61
+ | 2.2263 | 2.79 | 3328 | 2.2252 |
62
+ | 2.244 | 3.0 | 3584 | 2.2237 |
63
+ | 2.2198 | 3.22 | 3840 | 2.2229 |
64
+ | 2.2157 | 3.43 | 4096 | 2.2224 |
65
+ | 2.1992 | 3.65 | 4352 | 2.2219 |
66
+ | 2.2254 | 3.86 | 4608 | 2.2213 |
67
 
68
 
69
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:031d752ae33862d1a09639c82c3cbec7b612398c7ac9379c0df7b7c005fe31e1
3
  size 134235048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e30fea857b97e033354a16c4aabae19f3d46b42975e1f8e287bc7b2b219ab0a5
3
  size 134235048
runs/Nov10_01-01-47_69332eb5d77e/events.out.tfevents.1699578107.69332eb5d77e.14876.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f56664edaf0388ae3d586fc9b3a14803f43a4bcdc7303ad0fafdf7093852be88
3
+ size 4619
runs/Nov10_01-03-01_69332eb5d77e/events.out.tfevents.1699578182.69332eb5d77e.14876.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d4235777c75fd83f3272a1dcbe9d8096afe180a46b0a8b29ebeda40745f826b
3
+ size 5545
runs/Nov10_01-06-45_69332eb5d77e/events.out.tfevents.1699578406.69332eb5d77e.14876.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eca5cab4ddf413fb5f40d376d8aec5ef390864c8f5ba2d5e39540fc58a7430c7
3
+ size 4770
runs/Nov10_01-08-23_69332eb5d77e/events.out.tfevents.1699578504.69332eb5d77e.14876.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:399caf6b885606cfdaba1f4054a1713744d43a80bd66a273487c9aaeb402de5e
3
+ size 4772
runs/Nov10_01-10-41_69332eb5d77e/events.out.tfevents.1699578642.69332eb5d77e.14876.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45497559df6ee8efb35701f0802db5afc8594b22f70dd2263dcc3526a2aad802
3
+ size 12676
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91cc86ea45b2fca7fae9fe3634cdd61f0cb3896ce3dff60ffc605df4c9d791b7
3
- size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:283660df3ac10267291c7441e6210e2f31ce3de8207326fb26d26a366e9c4586
3
+ size 4536