ai-maker-space/mistral-7binstruct-summary-100s
Browse files- README.md +11 -11
- adapter_config.json +1 -0
- adapter_model.safetensors +1 -1
- runs/Apr23_16-55-17_71eb89c5adc3/events.out.tfevents.1713891347.71eb89c5adc3.4267.0 +3 -0
- tokenizer.json +1 -0
- training_args.bin +2 -2
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: mistral7binstruct_summarize
|
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: 1.
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -50,16 +50,16 @@ The following hyperparameters were used during training:
|
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
-
| Training Loss | Epoch
|
54 |
-
|
55 |
-
| 1.
|
56 |
-
| 1.
|
57 |
|
58 |
|
59 |
### Framework versions
|
60 |
|
61 |
-
- PEFT 0.
|
62 |
-
- Transformers 4.
|
63 |
-
- Pytorch 2.1
|
64 |
-
- Datasets 2.
|
65 |
-
- Tokenizers 0.
|
|
|
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: mistral7binstruct_summarize
|
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: 1.4169
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
+
|:-------------:|:------:|:----:|:---------------:|
|
55 |
+
| 1.6064 | 0.2101 | 25 | 1.4635 |
|
56 |
+
| 1.4562 | 0.4202 | 50 | 1.4169 |
|
57 |
|
58 |
|
59 |
### Framework versions
|
60 |
|
61 |
+
- PEFT 0.10.0
|
62 |
+
- Transformers 4.40.0
|
63 |
+
- Pytorch 2.2.1+cu121
|
64 |
+
- Datasets 2.19.0
|
65 |
+
- Tokenizers 0.19.1
|
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:
|
3 |
size 27280152
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a507365e6e361577f2abbb6ce00d9b7aed703670f24ac639f0b5434ae89f257
|
3 |
size 27280152
|
runs/Apr23_16-55-17_71eb89c5adc3/events.out.tfevents.1713891347.71eb89c5adc3.4267.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aad3ccb2a3e0324b096a8dfca2a80129d14f665c5cfea526559f696baf1c9c5e
|
3 |
+
size 7112
|
tokenizer.json
CHANGED
@@ -134,6 +134,7 @@
|
|
134 |
"end_of_word_suffix": null,
|
135 |
"fuse_unk": true,
|
136 |
"byte_fallback": true,
|
|
|
137 |
"vocab": {
|
138 |
"<unk>": 0,
|
139 |
"<s>": 1,
|
|
|
134 |
"end_of_word_suffix": null,
|
135 |
"fuse_unk": true,
|
136 |
"byte_fallback": true,
|
137 |
+
"ignore_merges": false,
|
138 |
"vocab": {
|
139 |
"<unk>": 0,
|
140 |
"<s>": 1,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f79f912866ae220a76f4fe7b451a8659801c11b9f6a0ed238e73155998ba27c
|
3 |
+
size 4984
|