Hugging Face's logo

amnae
/
output

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files
xet
Metrics Community
amnae commited on
Commit
74063dd
·
verified ·
1 Parent(s): a49d513

End of training

Browse files
Files changed (12) hide show
  1. README.md +56 -0
  2. adapter_config.json +29 -0
  3. adapter_model.safetensors +3 -0
  4. runs/Jul27_18-57-42_gressingham.cs.ucl.ac.uk/events.out.tfevents.1722103064.gressingham.cs.ucl.ac.uk.447299.0 +3 -0
  5. runs/Jul27_23-34-15_crested.cs.ucl.ac.uk/events.out.tfevents.1722119658.crested.cs.ucl.ac.uk.453974.0 +3 -0
  6. runs/Jul28_12-53-12_crested.cs.ucl.ac.uk/events.out.tfevents.1722167596.crested.cs.ucl.ac.uk.471674.0 +3 -0
  7. runs/Jul28_18-44-03_crested.cs.ucl.ac.uk/events.out.tfevents.1722188651.crested.cs.ucl.ac.uk.479928.0 +3 -0
  8. special_tokens_map.json +24 -0
  9. tokenizer.json +0 -0
  10. tokenizer.model +3 -0
  11. tokenizer_config.json +0 -0
  12. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: amnae/base_edu_llm_damex
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: output
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
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/maai/huggingface/runs/8tkph8gh)
17
+ # output
18
+
19
+ This model is a fine-tuned version of [amnae/base_edu_llm_damex](https://huggingface.co/amnae/base_edu_llm_damex) on the None dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-05
39
+ - train_batch_size: 5
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - num_epochs: 4
45
+
46
+ ### Training results
47
+
48
+
49
+
50
+ ### Framework versions
51
+
52
+ - PEFT 0.11.1
53
+ - Transformers 4.42.3
54
+ - Pytorch 2.2.0+cu121
55
+ - Datasets 2.20.0
56
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "amnae/base_edu_llm_damex",
5
+ "bias": "none",
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": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "v_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f9dd127e283df55b6572559e52dfbfe0fbaea0c90a98427e75bef9c42962b2f
3
+ size 109069176
runs/Jul27_18-57-42_gressingham.cs.ucl.ac.uk/events.out.tfevents.1722103064.gressingham.cs.ucl.ac.uk.447299.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93536c614d6898a6e4c4d5ed2cb3544fd81e82fa0a43ff52d6c776fe3f9b1c7e
3
+ size 6382
runs/Jul27_23-34-15_crested.cs.ucl.ac.uk/events.out.tfevents.1722119658.crested.cs.ucl.ac.uk.453974.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5321d37e8794c7de9a592beb8c1cdae3d198eff8a0aae733b295d174aef039b
3
+ size 23011
runs/Jul28_12-53-12_crested.cs.ucl.ac.uk/events.out.tfevents.1722167596.crested.cs.ucl.ac.uk.471674.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc337eb27f788164711956759853c43c5912b4dd42fd292688bd795cf755790b
3
+ size 23013
runs/Jul28_18-44-03_crested.cs.ucl.ac.uk/events.out.tfevents.1722188651.crested.cs.ucl.ac.uk.479928.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45d8775e96c3c6b691edb97812912c74360f64eb40f9dc4dac78c1fdbb8f9987
3
+ size 23012
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
3
+ size 587404
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cbd65b9dd9d28033fd160274402e50a218e9d629e8ebf173214e2582467d339
3
+ size 5368