Hugging Face's logo

martimfasantos
/
tinyllama-1.1b-sum-dpo-full_LR5e-8_BS64_2epochs_old

Text Generation
Transformers
TensorBoard
Safetensors
llama
alignment-handbook
trl
dpo
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
martimfasantos commited on
Commit
477cfc7
•
1 Parent(s): af71c4c

Model save

Browse files
Files changed (7) hide show
  1. README.md +99 -0
  2. all_results.json +9 -0
  3. generation_config.json +7 -0
  4. model.safetensors +1 -1
  5. runs/Jun26_23-14-32_poseidon/events.out.tfevents.1719444079.poseidon.621768.0 +2 -2
  6. train_results.json +9 -0
  7. trainer_state.json +0 -0
README.md ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: martimfasantos/tinyllama-1.1b-sum-sft-full_old
4
+ tags:
5
+ - trl
6
+ - dpo
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: tinyllama-1.1b-sum-dpo-full_LR5e-8_BS64_2epochs_old
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
+ # tinyllama-1.1b-sum-dpo-full_LR5e-8_BS64_2epochs_old
17
+
18
+ This model is a fine-tuned version of [martimfasantos/tinyllama-1.1b-sum-sft-full_old](https://huggingface.co/martimfasantos/tinyllama-1.1b-sum-sft-full_old) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.6891
21
+ - Rewards/chosen: -0.0201
22
+ - Rewards/rejected: -0.0288
23
+ - Rewards/accuracies: 0.5911
24
+ - Rewards/margins: 0.0087
25
+ - Logps/rejected: -66.0638
26
+ - Logps/chosen: -60.7225
27
+ - Logits/rejected: -3.0949
28
+ - Logits/chosen: -3.1006
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 5e-08
48
+ - train_batch_size: 8
49
+ - eval_batch_size: 8
50
+ - seed: 42
51
+ - distributed_type: multi-GPU
52
+ - gradient_accumulation_steps: 8
53
+ - total_train_batch_size: 64
54
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
55
+ - lr_scheduler_type: cosine
56
+ - lr_scheduler_warmup_ratio: 0.1
57
+ - num_epochs: 2
58
+
59
+ ### Training results
60
+
61
+ | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
62
+ |:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
63
+ | 0.6931 | 0.0689 | 100 | 0.6931 | 0.0001 | 0.0001 | 0.5023 | 0.0000 | -63.1703 | -58.7007 | -3.1577 | -3.1633 |
64
+ | 0.6931 | 0.1378 | 200 | 0.6932 | 0.0001 | 0.0002 | 0.4875 | -0.0001 | -63.1621 | -58.7010 | -3.1575 | -3.1632 |
65
+ | 0.6929 | 0.2068 | 300 | 0.6931 | 0.0004 | 0.0003 | 0.5149 | 0.0001 | -63.1505 | -58.6712 | -3.1569 | -3.1625 |
66
+ | 0.6927 | 0.2757 | 400 | 0.6930 | 0.0007 | 0.0005 | 0.5258 | 0.0003 | -63.1350 | -58.6397 | -3.1555 | -3.1611 |
67
+ | 0.692 | 0.3446 | 500 | 0.6929 | 0.0012 | 0.0007 | 0.5246 | 0.0005 | -63.1102 | -58.5951 | -3.1536 | -3.1592 |
68
+ | 0.6915 | 0.4135 | 600 | 0.6927 | 0.0016 | 0.0007 | 0.5504 | 0.0009 | -63.1105 | -58.5481 | -3.1508 | -3.1564 |
69
+ | 0.6912 | 0.4824 | 700 | 0.6924 | 0.0019 | 0.0004 | 0.5671 | 0.0015 | -63.1424 | -58.5229 | -3.1481 | -3.1538 |
70
+ | 0.69 | 0.5513 | 800 | 0.6922 | 0.0019 | -0.0000 | 0.5760 | 0.0019 | -63.1839 | -58.5249 | -3.1444 | -3.1500 |
71
+ | 0.6893 | 0.6203 | 900 | 0.6919 | 0.0017 | -0.0008 | 0.5709 | 0.0025 | -63.2630 | -58.5425 | -3.1403 | -3.1459 |
72
+ | 0.6892 | 0.6892 | 1000 | 0.6917 | 0.0011 | -0.0020 | 0.5725 | 0.0030 | -63.3758 | -58.6063 | -3.1361 | -3.1418 |
73
+ | 0.6892 | 0.7581 | 1100 | 0.6914 | 0.0002 | -0.0034 | 0.5809 | 0.0036 | -63.5250 | -58.6939 | -3.1313 | -3.1369 |
74
+ | 0.6885 | 0.8270 | 1200 | 0.6911 | -0.0007 | -0.0050 | 0.5755 | 0.0043 | -63.6802 | -58.7853 | -3.1282 | -3.1338 |
75
+ | 0.6877 | 0.8959 | 1300 | 0.6908 | -0.0024 | -0.0073 | 0.5781 | 0.0048 | -63.9072 | -58.9567 | -3.1223 | -3.1280 |
76
+ | 0.6874 | 0.9649 | 1400 | 0.6907 | -0.0040 | -0.0092 | 0.5771 | 0.0053 | -64.1026 | -59.1085 | -3.1205 | -3.1262 |
77
+ | 0.6871 | 1.0338 | 1500 | 0.6904 | -0.0055 | -0.0113 | 0.5825 | 0.0058 | -64.3106 | -59.2603 | -3.1153 | -3.1210 |
78
+ | 0.6863 | 1.1027 | 1600 | 0.6902 | -0.0075 | -0.0138 | 0.5888 | 0.0063 | -64.5576 | -59.4592 | -3.1122 | -3.1179 |
79
+ | 0.6854 | 1.1716 | 1700 | 0.6900 | -0.0096 | -0.0163 | 0.5867 | 0.0067 | -64.8090 | -59.6681 | -3.1086 | -3.1143 |
80
+ | 0.6855 | 1.2405 | 1800 | 0.6898 | -0.0120 | -0.0192 | 0.5827 | 0.0072 | -65.0974 | -59.9114 | -3.1070 | -3.1126 |
81
+ | 0.6824 | 1.3094 | 1900 | 0.6897 | -0.0139 | -0.0213 | 0.5825 | 0.0074 | -65.3089 | -60.1001 | -3.1034 | -3.1091 |
82
+ | 0.6851 | 1.3784 | 2000 | 0.6895 | -0.0155 | -0.0234 | 0.5906 | 0.0079 | -65.5166 | -60.2616 | -3.1014 | -3.1071 |
83
+ | 0.6834 | 1.4473 | 2100 | 0.6895 | -0.0167 | -0.0247 | 0.5862 | 0.0080 | -65.6501 | -60.3842 | -3.0998 | -3.1055 |
84
+ | 0.6828 | 1.5162 | 2200 | 0.6894 | -0.0179 | -0.0261 | 0.5874 | 0.0082 | -65.7914 | -60.5049 | -3.0984 | -3.1041 |
85
+ | 0.6833 | 1.5851 | 2300 | 0.6892 | -0.0188 | -0.0273 | 0.5901 | 0.0085 | -65.9073 | -60.5933 | -3.0973 | -3.1030 |
86
+ | 0.6835 | 1.6540 | 2400 | 0.6892 | -0.0193 | -0.0279 | 0.5862 | 0.0086 | -65.9739 | -60.6469 | -3.0961 | -3.1018 |
87
+ | 0.6826 | 1.7229 | 2500 | 0.6892 | -0.0197 | -0.0283 | 0.5850 | 0.0086 | -66.0099 | -60.6819 | -3.0956 | -3.1013 |
88
+ | 0.6825 | 1.7919 | 2600 | 0.6891 | -0.0198 | -0.0285 | 0.5890 | 0.0088 | -66.0344 | -60.6882 | -3.0949 | -3.1007 |
89
+ | 0.6823 | 1.8608 | 2700 | 0.6891 | -0.0200 | -0.0287 | 0.5890 | 0.0087 | -66.0526 | -60.7165 | -3.0949 | -3.1006 |
90
+ | 0.6816 | 1.9297 | 2800 | 0.6891 | -0.0201 | -0.0289 | 0.5841 | 0.0088 | -66.0728 | -60.7263 | -3.0951 | -3.1008 |
91
+ | 0.6836 | 1.9986 | 2900 | 0.6891 | -0.0201 | -0.0288 | 0.5911 | 0.0087 | -66.0638 | -60.7225 | -3.0949 | -3.1006 |
92
+
93
+
94
+ ### Framework versions
95
+
96
+ - Transformers 4.41.2
97
+ - Pytorch 2.1.2
98
+ - Datasets 2.20.0
99
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 0.0,
4
+ "train_loss": 0.6870454205553093,
5
+ "train_runtime": 56536.4846,
6
+ "train_samples": 92858,
7
+ "train_samples_per_second": 3.285,
8
+ "train_steps_per_second": 0.051
9
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "eos_token_id": 2,
4
+ "max_length": 2048,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.41.2"
7
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de4c744357315a062db5a982c51ce32a971d3d9305ef4d6232a8e8bbbf32e982
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e61335dc21b995e6589067bd5e4a19461be6b49d97d452bd0a9cc0dbe7bb6b2
3
  size 4400216536
runs/Jun26_23-14-32_poseidon/events.out.tfevents.1719444079.poseidon.621768.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2b01d7399a40ba31cfbc10a7b336c38d107b48a6acda798ba9dfcf092ff64aa
3
- size 226678
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6fe6a5edac770fc985acb891072894fd9c38cf4f8a16dfa08e9821a83546bda
3
+ size 227032
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 0.0,
4
+ "train_loss": 0.6870454205553093,
5
+ "train_runtime": 56536.4846,
6
+ "train_samples": 92858,
7
+ "train_samples_per_second": 3.285,
8
+ "train_steps_per_second": 0.051
9
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff