Hugging Face's logo

Ellio98
/
mistral-0.5B-base

Text Generation
Transformers
Safetensors
mistral
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
Ellio98 commited on
Commit
9c9013e
·
verified ·
1 Parent(s): 3aaa02d

End of training

Browse files
Files changed (5) hide show
  1. README.md +18 -19
  2. config.json +2 -3
  3. model.safetensors +2 -2
  4. tokenizer.json +2 -2
  5. training_args.bin +1 -1
README.md CHANGED
@@ -1,6 +1,5 @@
1
  ---
2
  library_name: transformers
3
- base_model: Ellio98/mistral-0.5B-base
4
  tags:
5
  - generated_from_trainer
6
  model-index:
@@ -13,9 +12,9 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # mistral-0.5B-base
15
 
16
- This model is a fine-tuned version of [Ellio98/mistral-0.5B-base](https://huggingface.co/Ellio98/mistral-0.5B-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 2.0625
19
 
20
  ## Model description
21
 
@@ -35,30 +34,30 @@ More information needed
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 0.0005
38
- - train_batch_size: 4
39
- - eval_batch_size: 4
40
  - seed: 42
41
  - gradient_accumulation_steps: 4
42
- - total_train_batch_size: 16
43
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
44
  - lr_scheduler_type: cosine
45
  - lr_scheduler_warmup_steps: 100
46
- - num_epochs: 1
47
 
48
  ### Training results
49
 
50
- | Training Loss | Epoch | Step | Validation Loss |
51
- |:-------------:|:-----:|:----:|:---------------:|
52
- | 2.4315 | 0.1 | 129 | 2.4184 |
53
- | 2.3834 | 0.2 | 258 | 2.3990 |
54
- | 2.4535 | 0.3 | 387 | 2.3923 |
55
- | 2.2178 | 0.4 | 516 | 2.3198 |
56
- | 2.3863 | 0.5 | 645 | 2.2612 |
57
- | 2.2739 | 0.6 | 774 | 2.2014 |
58
- | 2.0353 | 0.7 | 903 | 2.1402 |
59
- | 2.1386 | 0.8 | 1032 | 2.0911 |
60
- | 2.0759 | 0.9 | 1161 | 2.0672 |
61
- | 2.1736 | 1.0 | 1290 | 2.0625 |
62
 
63
 
64
  ### Framework versions
 
1
  ---
2
  library_name: transformers
 
3
  tags:
4
  - generated_from_trainer
5
  model-index:
 
12
 
13
  # mistral-0.5B-base
14
 
15
+ This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 3.8893
18
 
19
  ## Model description
20
 
 
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 0.0005
37
+ - train_batch_size: 16
38
+ - eval_batch_size: 16
39
  - seed: 42
40
  - gradient_accumulation_steps: 4
41
+ - total_train_batch_size: 64
42
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: cosine
44
  - lr_scheduler_warmup_steps: 100
45
+ - num_epochs: 4
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:------:|:----:|:---------------:|
51
+ | 5.9695 | 0.3989 | 74 | 6.0154 |
52
+ | 5.0148 | 0.7978 | 148 | 5.1781 |
53
+ | 4.459 | 1.1941 | 222 | 4.7603 |
54
+ | 4.0585 | 1.5930 | 296 | 4.4421 |
55
+ | 3.8404 | 1.9919 | 370 | 4.2375 |
56
+ | 3.1164 | 2.3881 | 444 | 4.0944 |
57
+ | 2.4948 | 2.7871 | 518 | 3.9528 |
58
+ | 1.6126 | 3.1833 | 592 | 3.9094 |
59
+ | 1.5873 | 3.5822 | 666 | 3.8964 |
60
+ | 1.4401 | 3.9811 | 740 | 3.8893 |
61
 
62
 
63
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,4 @@
1
  {
2
- "_name_or_path": "Ellio98/mistral-0.5B-base",
3
  "architectures": [
4
  "MistralForCausalLM"
5
  ],
@@ -16,7 +15,7 @@
16
  "hidden_size": 1536,
17
  "initializer_range": 0.02,
18
  "intermediate_size": 4096,
19
- "max_position_embeddings": 2048,
20
  "model_type": "mistral",
21
  "num_attention_heads": 8,
22
  "num_hidden_layers": 16,
@@ -29,5 +28,5 @@
29
  "torch_dtype": "float32",
30
  "transformers_version": "4.47.0",
31
  "use_cache": true,
32
- "vocab_size": 32000
33
  }
 
1
  {
 
2
  "architectures": [
3
  "MistralForCausalLM"
4
  ],
 
15
  "hidden_size": 1536,
16
  "initializer_range": 0.02,
17
  "intermediate_size": 4096,
18
+ "max_position_embeddings": 4096,
19
  "model_type": "mistral",
20
  "num_attention_heads": 8,
21
  "num_hidden_layers": 16,
 
28
  "torch_dtype": "float32",
29
  "transformers_version": "4.47.0",
30
  "use_cache": true,
31
+ "vocab_size": 32768
32
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c00fb6335ef2b3b089ee315a68c6a89ee11c84075715fa298e20e22ddd1a3c3
3
- size 2054379856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8839c68dc06b4ea5c30fe89f930c3952588ba17896a32c25ac0a30c518977b79
3
+ size 2063817040
tokenizer.json CHANGED
@@ -2,13 +2,13 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 512,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
  "padding": {
10
  "strategy": {
11
- "Fixed": 512
12
  },
13
  "direction": "Left",
14
  "pad_to_multiple_of": null,
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 256,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
  "padding": {
10
  "strategy": {
11
+ "Fixed": 256
12
  },
13
  "direction": "Left",
14
  "pad_to_multiple_of": null,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ee1aca07e2c000d45f1af350f62cf6b3c2038c85f5c343accf1e2064ef3cee1
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79aead2ffe48c9db3adaebd26efae9c67c63713bea0729b7b90665938d5c5a3c
3
  size 5304