Hugging Face's logo

emily49
/
mistral-7b-instruct-connections

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
emily49 commited on
Commit
c74fbea
•
1 Parent(s): 23f147b

End of training

Browse files
Files changed (1) hide show
  1. README.md +6 -13
README.md CHANGED
@@ -14,17 +14,12 @@ model-index:
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
  should probably proofread and complete it, then remove this comment. -->
16
 
17
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/emilycs229/huggingface/runs/405rlxb2)
18
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/emilycs229/huggingface/runs/405rlxb2)
19
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/emilycs229/huggingface/runs/405rlxb2)
20
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/emilycs229/huggingface/runs/405rlxb2)
21
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/emilycs229/224n_connections/runs/vz9otsu5)
22
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/emilycs229/224n_connections/runs/k7e9e0v3)
23
  # mistral-7b-instruct-connections
24
 
25
  This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on an unknown dataset.
26
  It achieves the following results on the evaluation set:
27
- - Loss: 0.6526
28
 
29
  ## Model description
30
 
@@ -52,17 +47,15 @@ The following hyperparameters were used during training:
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
  - lr_scheduler_type: constant
54
  - lr_scheduler_warmup_ratio: 0.03
55
- - num_epochs: 5
56
 
57
  ### Training results
58
 
59
  | Training Loss | Epoch | Step | Validation Loss |
60
  |:-------------:|:------:|:----:|:---------------:|
61
- | No log | 0.9855 | 17 | 0.5535 |
62
- | 0.8187 | 1.9710 | 34 | 0.5099 |
63
- | 0.4261 | 2.9565 | 51 | 0.5141 |
64
- | 0.4261 | 4.0 | 69 | 0.5708 |
65
- | 0.2769 | 4.9275 | 85 | 0.6526 |
66
 
67
 
68
  ### Framework versions
 
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
  should probably proofread and complete it, then remove this comment. -->
16
 
17
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/emilycs229/224n_connections/runs/tref0mx3)
 
 
 
 
 
18
  # mistral-7b-instruct-connections
19
 
20
  This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.5142
23
 
24
  ## Model description
25
 
 
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: constant
49
  - lr_scheduler_warmup_ratio: 0.03
50
+ - num_epochs: 3
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss |
55
  |:-------------:|:------:|:----:|:---------------:|
56
+ | No log | 0.9855 | 17 | 0.5505 |
57
+ | 0.8186 | 1.9710 | 34 | 0.5126 |
58
+ | 0.4309 | 2.9565 | 51 | 0.5142 |
 
 
59
 
60
 
61
  ### Framework versions