Hugging Face's logo

dominguesm
/
mambarim-110m-chat

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
dominguesm commited on
Commit
c4a49b7
•
1 Parent(s): 47378a9

End of training

Browse files
Files changed (4) hide show
  1. README.md +115 -0
  2. adapter_config.json +3 -3
  3. adapter_model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-4.0
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ base_model: dominguesm/mambarim-110m
9
+ model-index:
10
+ - name: mambarim-110m-chat
11
+ results: []
12
+ ---
13
+
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
+ # mambarim-110m-chat
18
+
19
+ This model is a fine-tuned version of [dominguesm/mambarim-110m](https://huggingface.co/dominguesm/mambarim-110m) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 2.5904
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 0.002
41
+ - train_batch_size: 4
42
+ - eval_batch_size: 4
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 3
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:------:|:-----:|:---------------:|
52
+ | 2.8055 | 0.0545 | 1000 | 2.7821 |
53
+ | 2.8298 | 0.1089 | 2000 | 2.7619 |
54
+ | 2.9104 | 0.1634 | 3000 | 2.7539 |
55
+ | 2.6692 | 0.2178 | 4000 | 2.7379 |
56
+ | 2.5876 | 0.2723 | 5000 | 2.7325 |
57
+ | 2.7439 | 0.3267 | 6000 | 2.7203 |
58
+ | 2.7787 | 0.3812 | 7000 | 2.7178 |
59
+ | 2.8461 | 0.4356 | 8000 | 2.7117 |
60
+ | 2.6929 | 0.4901 | 9000 | 2.7060 |
61
+ | 2.7229 | 0.5445 | 10000 | 2.7005 |
62
+ | 2.5014 | 0.5990 | 11000 | 2.6948 |
63
+ | 2.5046 | 0.6535 | 12000 | 2.6923 |
64
+ | 2.6258 | 0.7079 | 13000 | 2.6898 |
65
+ | 2.5822 | 0.7624 | 14000 | 2.6847 |
66
+ | 2.6399 | 0.8168 | 15000 | 2.6847 |
67
+ | 2.5342 | 0.8713 | 16000 | 2.6768 |
68
+ | 2.6878 | 0.9257 | 17000 | 2.6726 |
69
+ | 2.8872 | 0.9802 | 18000 | 2.6729 |
70
+ | 2.6565 | 1.0346 | 19000 | 2.6693 |
71
+ | 2.4293 | 1.0891 | 20000 | 2.6672 |
72
+ | 2.8411 | 1.1435 | 21000 | 2.6620 |
73
+ | 2.7126 | 1.1980 | 22000 | 2.6618 |
74
+ | 2.5516 | 1.2525 | 23000 | 2.6609 |
75
+ | 2.6093 | 1.3069 | 24000 | 2.6557 |
76
+ | 2.6489 | 1.3614 | 25000 | 2.6554 |
77
+ | 2.6014 | 1.4158 | 26000 | 2.6522 |
78
+ | 2.6185 | 1.4703 | 27000 | 2.6477 |
79
+ | 2.6896 | 1.5247 | 28000 | 2.6468 |
80
+ | 2.6222 | 1.5792 | 29000 | 2.6433 |
81
+ | 2.6227 | 1.6336 | 30000 | 2.6415 |
82
+ | 2.5772 | 1.6881 | 31000 | 2.6377 |
83
+ | 2.4859 | 1.7425 | 32000 | 2.6356 |
84
+ | 2.3725 | 1.7970 | 33000 | 2.6327 |
85
+ | 2.5452 | 1.8514 | 34000 | 2.6308 |
86
+ | 2.6545 | 1.9059 | 35000 | 2.6281 |
87
+ | 2.6109 | 1.9604 | 36000 | 2.6265 |
88
+ | 2.5004 | 2.0148 | 37000 | 2.6237 |
89
+ | 2.4471 | 2.0693 | 38000 | 2.6236 |
90
+ | 2.5242 | 2.1237 | 39000 | 2.6211 |
91
+ | 2.6242 | 2.1782 | 40000 | 2.6175 |
92
+ | 2.561 | 2.2326 | 41000 | 2.6168 |
93
+ | 2.5065 | 2.2871 | 42000 | 2.6149 |
94
+ | 2.6165 | 2.3415 | 43000 | 2.6122 |
95
+ | 2.4452 | 2.3960 | 44000 | 2.6098 |
96
+ | 2.6277 | 2.4504 | 45000 | 2.6075 |
97
+ | 2.5547 | 2.5049 | 46000 | 2.6062 |
98
+ | 2.5153 | 2.5594 | 47000 | 2.6028 |
99
+ | 2.6322 | 2.6138 | 48000 | 2.6020 |
100
+ | 2.5263 | 2.6683 | 49000 | 2.5995 |
101
+ | 2.7165 | 2.7227 | 50000 | 2.5974 |
102
+ | 2.6576 | 2.7772 | 51000 | 2.5956 |
103
+ | 2.5471 | 2.8316 | 52000 | 2.5940 |
104
+ | 2.7174 | 2.8861 | 53000 | 2.5923 |
105
+ | 2.5018 | 2.9405 | 54000 | 2.5910 |
106
+ | 2.6201 | 2.9950 | 55000 | 2.5904 |
107
+
108
+
109
+ ### Framework versions
110
+
111
+ - PEFT 0.10.0
112
+ - Transformers 4.40.1
113
+ - Pytorch 2.2.1+cu121
114
+ - Datasets 2.19.0
115
+ - Tokenizers 0.19.1
adapter_config.json CHANGED
@@ -20,11 +20,11 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "embeddings",
24
- "lm_head",
25
- "dt_proj",
26
  "in_proj",
 
 
27
  "out_proj",
 
28
  "x_proj"
29
  ],
30
  "task_type": "CAUSAL_LM",
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
 
23
  "in_proj",
24
+ "lm_head",
25
+ "embeddings",
26
  "out_proj",
27
+ "dt_proj",
28
  "x_proj"
29
  ],
30
  "task_type": "CAUSAL_LM",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da85bed48eacef0db4d344652821dc079988f0412a05a824e7b5cbdfa4d15498
3
  size 202319288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d98db4b27a5c9bd87b4a096bf7fe6a28807b7e039fb5ca2ec0856e144da7a60
3
  size 202319288
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc6bb28728ba589f2206cfb3356a2abed789f35ec962f09bfb7de85cf083f55d
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b219e1b549e59338d27e84106a727c5ac18b8417cf209ce38c8e57807af85f37
3
  size 4984