End of training
Browse files- README.md +45 -45
- config.json +1 -1
- final_checkpoint/config.json +1 -1
- final_checkpoint/generation_config.json +1 -1
- final_checkpoint/model-00001-of-00003.safetensors +1 -1
- final_checkpoint/model-00002-of-00003.safetensors +1 -1
- final_checkpoint/model-00003-of-00003.safetensors +1 -1
- generation_config.json +1 -1
- model-00001-of-00003.safetensors +1 -1
- model-00002-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -6,18 +6,18 @@ tags:
|
|
6 |
- sft
|
7 |
- generated_from_trainer
|
8 |
model-index:
|
9 |
-
- name:
|
10 |
results: []
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
should probably proofread and complete it, then remove this comment. -->
|
15 |
|
16 |
-
#
|
17 |
|
18 |
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss:
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -51,51 +51,51 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:-------:|:----:|:---------------:|
|
54 |
-
| 2.
|
55 |
-
|
|
56 |
-
|
|
57 |
-
|
|
58 |
-
|
|
59 |
-
|
|
60 |
-
| 0.
|
61 |
-
|
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.
|
79 |
-
| 0.
|
80 |
-
| 0.
|
81 |
-
| 0.
|
82 |
-
| 0.
|
83 |
-
| 0.
|
84 |
-
| 0.
|
85 |
-
| 0.
|
86 |
-
| 0.
|
87 |
-
| 0.
|
88 |
-
| 0.
|
89 |
-
| 0.
|
90 |
-
| 0.
|
91 |
-
| 0.
|
92 |
-
| 0.
|
93 |
-
| 0.
|
94 |
|
95 |
|
96 |
### Framework versions
|
97 |
|
98 |
-
- Transformers 4.41.
|
99 |
- Pytorch 2.0.0+cu117
|
100 |
-
- Datasets 2.19.
|
101 |
- Tokenizers 0.19.1
|
|
|
6 |
- sft
|
7 |
- generated_from_trainer
|
8 |
model-index:
|
9 |
+
- name: UTI_M2_1000steps_1e6rate_SFT
|
10 |
results: []
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
should probably proofread and complete it, then remove this comment. -->
|
15 |
|
16 |
+
# UTI_M2_1000steps_1e6rate_SFT
|
17 |
|
18 |
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.7960
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:-------:|:----:|:---------------:|
|
54 |
+
| 2.2167 | 0.3333 | 25 | 1.1865 |
|
55 |
+
| 0.9806 | 0.6667 | 50 | 0.9618 |
|
56 |
+
| 0.936 | 1.0 | 75 | 0.9371 |
|
57 |
+
| 0.8294 | 1.3333 | 100 | 0.9512 |
|
58 |
+
| 0.8273 | 1.6667 | 125 | 0.9369 |
|
59 |
+
| 0.7851 | 2.0 | 150 | 0.9036 |
|
60 |
+
| 0.5263 | 2.3333 | 175 | 0.9990 |
|
61 |
+
| 0.5512 | 2.6667 | 200 | 0.9589 |
|
62 |
+
| 0.5272 | 3.0 | 225 | 0.9576 |
|
63 |
+
| 0.2888 | 3.3333 | 250 | 1.1371 |
|
64 |
+
| 0.2968 | 3.6667 | 275 | 1.1164 |
|
65 |
+
| 0.3381 | 4.0 | 300 | 1.1144 |
|
66 |
+
| 0.1802 | 4.3333 | 325 | 1.1697 |
|
67 |
+
| 0.2025 | 4.6667 | 350 | 1.1946 |
|
68 |
+
| 0.2273 | 5.0 | 375 | 1.2614 |
|
69 |
+
| 0.1417 | 5.3333 | 400 | 1.3260 |
|
70 |
+
| 0.1524 | 5.6667 | 425 | 1.3343 |
|
71 |
+
| 0.136 | 6.0 | 450 | 1.3735 |
|
72 |
+
| 0.117 | 6.3333 | 475 | 1.3843 |
|
73 |
+
| 0.1284 | 6.6667 | 500 | 1.3742 |
|
74 |
+
| 0.1172 | 7.0 | 525 | 1.4114 |
|
75 |
+
| 0.0905 | 7.3333 | 550 | 1.5000 |
|
76 |
+
| 0.1027 | 7.6667 | 575 | 1.5142 |
|
77 |
+
| 0.097 | 8.0 | 600 | 1.4912 |
|
78 |
+
| 0.0837 | 8.3333 | 625 | 1.5974 |
|
79 |
+
| 0.0832 | 8.6667 | 650 | 1.6185 |
|
80 |
+
| 0.0781 | 9.0 | 675 | 1.6203 |
|
81 |
+
| 0.0698 | 9.3333 | 700 | 1.6833 |
|
82 |
+
| 0.0722 | 9.6667 | 725 | 1.6960 |
|
83 |
+
| 0.0681 | 10.0 | 750 | 1.7139 |
|
84 |
+
| 0.0635 | 10.3333 | 775 | 1.7732 |
|
85 |
+
| 0.0654 | 10.6667 | 800 | 1.7704 |
|
86 |
+
| 0.0663 | 11.0 | 825 | 1.7647 |
|
87 |
+
| 0.0604 | 11.3333 | 850 | 1.7840 |
|
88 |
+
| 0.0628 | 11.6667 | 875 | 1.7916 |
|
89 |
+
| 0.0627 | 12.0 | 900 | 1.7947 |
|
90 |
+
| 0.061 | 12.3333 | 925 | 1.7962 |
|
91 |
+
| 0.062 | 12.6667 | 950 | 1.7967 |
|
92 |
+
| 0.0607 | 13.0 | 975 | 1.7960 |
|
93 |
+
| 0.0605 | 13.3333 | 1000 | 1.7960 |
|
94 |
|
95 |
|
96 |
### Framework versions
|
97 |
|
98 |
+
- Transformers 4.41.2
|
99 |
- Pytorch 2.0.0+cu117
|
100 |
+
- Datasets 2.19.2
|
101 |
- Tokenizers 0.19.1
|
config.json
CHANGED
@@ -20,7 +20,7 @@
|
|
20 |
"sliding_window": null,
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "float16",
|
23 |
-
"transformers_version": "4.41.
|
24 |
"use_cache": false,
|
25 |
"vocab_size": 32000
|
26 |
}
|
|
|
20 |
"sliding_window": null,
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "float16",
|
23 |
+
"transformers_version": "4.41.2",
|
24 |
"use_cache": false,
|
25 |
"vocab_size": 32000
|
26 |
}
|
final_checkpoint/config.json
CHANGED
@@ -20,7 +20,7 @@
|
|
20 |
"sliding_window": null,
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "float16",
|
23 |
-
"transformers_version": "4.41.
|
24 |
"use_cache": false,
|
25 |
"vocab_size": 32000
|
26 |
}
|
|
|
20 |
"sliding_window": null,
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "float16",
|
23 |
+
"transformers_version": "4.41.2",
|
24 |
"use_cache": false,
|
25 |
"vocab_size": 32000
|
26 |
}
|
final_checkpoint/generation_config.json
CHANGED
@@ -2,5 +2,5 @@
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
-
"transformers_version": "4.41.
|
6 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.41.2"
|
6 |
}
|
final_checkpoint/model-00001-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4943162240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e62ed3b72dc7a5fe13bb50e75c99aec82d8b4ddb930d9255a0ce990dd4758067
|
3 |
size 4943162240
|
final_checkpoint/model-00002-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999819232
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11e0ebfbd84055ea6321452edeaff4191e7bb470e8b072270a6e62b04b0ba59f
|
3 |
size 4999819232
|
final_checkpoint/model-00003-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4540516256
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1455bdf4d2a45e55cf179acdb42249f4bd48df2af6c8c449bea31d9bc1edd45f
|
3 |
size 4540516256
|
generation_config.json
CHANGED
@@ -2,5 +2,5 @@
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
-
"transformers_version": "4.41.
|
6 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.41.2"
|
6 |
}
|
model-00001-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4943162240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e62ed3b72dc7a5fe13bb50e75c99aec82d8b4ddb930d9255a0ce990dd4758067
|
3 |
size 4943162240
|
model-00002-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999819232
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11e0ebfbd84055ea6321452edeaff4191e7bb470e8b072270a6e62b04b0ba59f
|
3 |
size 4999819232
|
model-00003-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4540516256
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1455bdf4d2a45e55cf179acdb42249f4bd48df2af6c8c449bea31d9bc1edd45f
|
3 |
size 4540516256
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4603
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4087ee1fad72c7539d1be4b6a2a09277949417a580d66b558e069226cf106161
|
3 |
size 4603
|