Hugging Face's logo

rafaeloc15
/
mistral_instruct_generation_v2

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
6
rafaeloc15 commited on
Commit
82329a4
•
1 Parent(s): 4e27acc

rafaeloc15/mistral-small-v4

Browse files
Files changed (11) hide show
  1. README.md +5 -5
  2. adapter_config.json +1 -0
  3. adapter_model.safetensors +1 -1
  4. runs/Apr19_22-31-37_9503fe95efd9/events.out.tfevents.1713565928.9503fe95efd9.237.0 +3 -0
  5. runs/Apr19_22-31-37_9503fe95efd9/events.out.tfevents.1713566894.9503fe95efd9.237.1 +3 -0
  6. runs/Apr19_23-17-55_9503fe95efd9/events.out.tfevents.1713568718.9503fe95efd9.237.2 +3 -0
  7. runs/Apr19_23-17-55_9503fe95efd9/events.out.tfevents.1713569825.9503fe95efd9.237.3 +3 -0
  8. runs/Apr19_23-17-55_9503fe95efd9/events.out.tfevents.1713570268.9503fe95efd9.237.4 +3 -0
  9. runs/Apr19_23-17-55_9503fe95efd9/events.out.tfevents.1713570357.9503fe95efd9.237.5 +3 -0
  10. runs/Apr19_23-17-55_9503fe95efd9/events.out.tfevents.1713570505.9503fe95efd9.237.6 +3 -0
  11. training_args.bin +1 -1
README.md CHANGED
@@ -5,9 +5,9 @@ tags:
5
  - trl
6
  - sft
7
  - generated_from_trainer
 
8
  datasets:
9
  - generator
10
- base_model: mistralai/Mistral-7B-Instruct-v0.2
11
  model-index:
12
  - name: mistral_instruct_generation_v2
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 [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0738
24
 
25
  ## Model description
26
 
@@ -52,8 +52,8 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-----:|:----:|:---------------:|
55
- | 0.1033 | 1.0 | 82 | 0.0988 |
56
- | 0.0809 | 2.0 | 164 | 0.0738 |
57
 
58
 
59
  ### Framework versions
@@ -61,5 +61,5 @@ The following hyperparameters were used during training:
61
  - PEFT 0.10.0
62
  - Transformers 4.38.2
63
  - Pytorch 2.2.1+cu121
64
- - Datasets 2.18.0
65
  - Tokenizers 0.15.2
 
5
  - trl
6
  - sft
7
  - generated_from_trainer
8
+ base_model: mistralai/Mistral-7B-Instruct-v0.2
9
  datasets:
10
  - generator
 
11
  model-index:
12
  - name: mistral_instruct_generation_v2
13
  results: []
 
20
 
21
  This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.0237
24
 
25
  ## Model description
26
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-----:|:----:|:---------------:|
55
+ | 0.0373 | 1.0 | 110 | 0.0274 |
56
+ | 0.0302 | 2.0 | 220 | 0.0237 |
57
 
58
 
59
  ### Framework versions
 
61
  - PEFT 0.10.0
62
  - Transformers 4.38.2
63
  - Pytorch 2.2.1+cu121
64
+ - Datasets 2.19.0
65
  - Tokenizers 0.15.2
adapter_config.json CHANGED
@@ -6,6 +6,7 @@
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
8
  "init_lora_weights": true,
 
9
  "layers_pattern": null,
10
  "layers_to_transform": null,
11
  "loftq_config": {},
 
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
8
  "init_lora_weights": true,
9
+ "layer_replication": null,
10
  "layers_pattern": null,
11
  "layers_to_transform": null,
12
  "loftq_config": {},
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:030fc4a3b11ca1f9daaf45430f913ce20e97bc6c9590d374f7f7a0a526cf0469
3
  size 109069176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96b67927fcb00c931555dd243722108043295fc73678578097ae65fe6e7ecdcf
3
  size 109069176
runs/Apr19_22-31-37_9503fe95efd9/events.out.tfevents.1713565928.9503fe95efd9.237.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ed5002c0236ba86390971afa1b38b25c56dda75f8d6e29d9f625b435eb939f9
3
+ size 7338
runs/Apr19_22-31-37_9503fe95efd9/events.out.tfevents.1713566894.9503fe95efd9.237.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18b513623342282493ff47c89e230645624e761a706c254a5109f792a909156b
3
+ size 7338
runs/Apr19_23-17-55_9503fe95efd9/events.out.tfevents.1713568718.9503fe95efd9.237.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:202a26a3a98db39330dc405c22122b24566a39440d6a5ba3947c3c48d3c7d831
3
+ size 7338
runs/Apr19_23-17-55_9503fe95efd9/events.out.tfevents.1713569825.9503fe95efd9.237.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d21e38cf569bf89a82292b5fa563a88bfc8852efb26f7d3bab2e735062f3db2f
3
+ size 5061
runs/Apr19_23-17-55_9503fe95efd9/events.out.tfevents.1713570268.9503fe95efd9.237.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bad150580d97258780b28ce04002a774bb76c4128f115f143d56c06efe962b63
3
+ size 5061
runs/Apr19_23-17-55_9503fe95efd9/events.out.tfevents.1713570357.9503fe95efd9.237.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dfd8cb04cfa3bd4204d3c0b7166226cabc3bbb042e352e039e45544462b8db4
3
+ size 6148
runs/Apr19_23-17-55_9503fe95efd9/events.out.tfevents.1713570505.9503fe95efd9.237.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8a8fe31521a812528bdccb5f9672cd5d88fa897d3ce374eb8ce9ce8d5f2c531
3
+ size 10546
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da7e101c0c35f47975325d91caa6d28dc01850bfc3bf2bd7059b7710c2810cb3
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8c798461c57d7010b041a17a668493a8d2410e8526dd949bcb3fb2d86ac4ae4
3
  size 4920