patruff commited on
Commit
11117ca
1 Parent(s): 082c018

patruff/mistralNemoSFT2DIRTY5

Browse files
README.md ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/mistral-nemo-base-2407-bnb-4bit
3
+ library_name: peft
4
+ license: apache-2.0
5
+ tags:
6
+ - trl
7
+ - sft
8
+ - unsloth
9
+ - generated_from_trainer
10
+ model-index:
11
+ - name: mistralNemoSFTnewPEFTdirty5
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # mistralNemoSFTnewPEFTdirty5
19
+
20
+ This model is a fine-tuned version of [unsloth/mistral-nemo-base-2407-bnb-4bit](https://huggingface.co/unsloth/mistral-nemo-base-2407-bnb-4bit) on an unknown dataset.
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 8e-05
40
+ - train_batch_size: 1
41
+ - eval_batch_size: 8
42
+ - seed: 3407
43
+ - gradient_accumulation_steps: 2
44
+ - total_train_batch_size: 2
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 5
48
+ - num_epochs: 2
49
+
50
+ ### Training results
51
+
52
+
53
+
54
+ ### Framework versions
55
+
56
+ - PEFT 0.12.0
57
+ - Transformers 4.44.2
58
+ - Pytorch 2.4.0+cu121
59
+ - Datasets 2.21.0
60
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/mistral-nemo-base-2407-bnb-4bit",
5
+ "bias": "none",
6
+ "fan_in_fan_out": true,
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": 128,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": [
18
+ "lm_head"
19
+ ],
20
+ "peft_type": "LORA",
21
+ "r": 128,
22
+ "rank_pattern": {},
23
+ "revision": null,
24
+ "target_modules": [
25
+ "q_proj",
26
+ "k_proj",
27
+ "o_proj",
28
+ "down_proj",
29
+ "up_proj",
30
+ "gate_proj",
31
+ "v_proj"
32
+ ],
33
+ "task_type": "CAUSAL_LM",
34
+ "use_dora": false,
35
+ "use_rslora": true
36
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd13e13e838d85631919962564929d105b13373c16df78702f0eb7795509b6b2
3
+ size 4508954448
runs/Sep06_07-15-13_e76614b2a4e8/events.out.tfevents.1725606919.e76614b2a4e8.1135.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00e274ecad8da31152cf31ec8c6e42f8d07f1b0b4ffaa5a8bfd1e87975df3448
3
+ size 654614
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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 sha256:602255963850dac0e341577342216d784b2dcfd3fc658af43135a3d6166fb49c
3
+ size 5432