Hugging Face's logo

tutrinh
/
prc-test

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
tutrinh commited on
Commit
bbb7801
•
1 Parent(s): 3fdfa62

prc-test-model

Browse files
Files changed (16) hide show
  1. README.md +56 -0
  2. adapter_config.json +27 -0
  3. adapter_model.safetensors +3 -0
  4. logs/events.out.tfevents.1707369586.rnn.ist.berkeley.edu.19818.0 +3 -0
  5. logs/events.out.tfevents.1707456185.rnn.ist.berkeley.edu.1554930.0 +3 -0
  6. logs/events.out.tfevents.1707512696.rnn.ist.berkeley.edu.3004003.0 +3 -0
  7. logs/events.out.tfevents.1707513744.rnn.ist.berkeley.edu.3066513.0 +3 -0
  8. logs/events.out.tfevents.1707514200.rnn.ist.berkeley.edu.3074602.0 +3 -0
  9. logs/events.out.tfevents.1707514442.rnn.ist.berkeley.edu.3100726.0 +3 -0
  10. logs/events.out.tfevents.1709062041.rnn.ist.berkeley.edu.1672898.0 +3 -0
  11. logs/events.out.tfevents.1709069164.rnn.ist.berkeley.edu.40795.0 +3 -0
  12. logs/events.out.tfevents.1709070025.rnn.ist.berkeley.edu.96117.0 +3 -0
  13. logs/events.out.tfevents.1714902014.gan.ist.berkeley.edu.3021074.0 +3 -0
  14. logs/events.out.tfevents.1714902359.gan.ist.berkeley.edu.3023358.0 +3 -0
  15. logs/events.out.tfevents.1714902632.gan.ist.berkeley.edu.3024030.0 +3 -0
  16. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: mistralai/Mistral-7B-Instruct-v0.2
7
+ model-index:
8
+ - name: huggingface_out
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # huggingface_out
16
+
17
+ This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the None dataset.
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 3e-05
37
+ - train_batch_size: 4
38
+ - eval_batch_size: 4
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: cosine
42
+ - lr_scheduler_warmup_ratio: 0.065
43
+ - num_epochs: 3
44
+ - mixed_precision_training: Native AMP
45
+
46
+ ### Training results
47
+
48
+
49
+
50
+ ### Framework versions
51
+
52
+ - PEFT 0.7.2.dev0
53
+ - Transformers 4.37.1
54
+ - Pytorch 2.2.2+cu121
55
+ - Datasets 2.9.0
56
+ - Tokenizers 0.15.1
adapter_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 512,
13
+ "lora_dropout": 0,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 256,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "q_proj",
23
+ "v_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM",
26
+ "use_rslora": false
27
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12a88757931812f950030669a23aa51534f1eeddd149f5d528ea6d9dab2ed9cd
3
+ size 436225216
logs/events.out.tfevents.1707369586.rnn.ist.berkeley.edu.19818.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bad2e3dc1a0704480b55d384932d4a273b2bbb6298aabd1c24c0410e58d6cd96
3
+ size 5062
logs/events.out.tfevents.1707456185.rnn.ist.berkeley.edu.1554930.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21d3a94e3f62b3e8a138b6b7e334566b208fe693a54b09cd65acd5cfc7823235
3
+ size 5730
logs/events.out.tfevents.1707512696.rnn.ist.berkeley.edu.3004003.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98f9b0c03d2bc0f1707e39892bc52347df20ce9727e6d5094de0d02b1c2d2e80
3
+ size 5096
logs/events.out.tfevents.1707513744.rnn.ist.berkeley.edu.3066513.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca94459d1d5b1e95675020e66665865d8100f8e68793615e57f7f375ea06a195
3
+ size 5096
logs/events.out.tfevents.1707514200.rnn.ist.berkeley.edu.3074602.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ee89bc9d0bba8ce62b83a8484aceac968f2d39a38dc847b2bdbaf9315569b09
3
+ size 5096
logs/events.out.tfevents.1707514442.rnn.ist.berkeley.edu.3100726.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b46494fded4c35be266b51329ed7dc9d4365089e58b3deb8904e70ccc13acf7
3
+ size 5730
logs/events.out.tfevents.1709062041.rnn.ist.berkeley.edu.1672898.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9efda8306e221d88ad9fa16ec39803806b4c299b9d84fcd296a460e7e18217b1
3
+ size 4749
logs/events.out.tfevents.1709069164.rnn.ist.berkeley.edu.40795.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d3bede35d0e6ff8c8b7479f6c95a37d31f929aa4e61d76636e79278a175140e
3
+ size 4749
logs/events.out.tfevents.1709070025.rnn.ist.berkeley.edu.96117.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e19f8ebf6d4dfec7ac3342b005fcc46aceaa06cd8fb1ccaea3ab35437e647bf
3
+ size 6830
logs/events.out.tfevents.1714902014.gan.ist.berkeley.edu.3021074.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cfda7c8161c3d393059af5aa4498d3c8105f91250a3f7df184ca2b0d97cb0d6
3
+ size 4748
logs/events.out.tfevents.1714902359.gan.ist.berkeley.edu.3023358.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9653f17c61c42c37daa2164f60960c957e37b38952dfa95fed6ab5ef743ef185
3
+ size 4748
logs/events.out.tfevents.1714902632.gan.ist.berkeley.edu.3024030.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aed9cef42e0e7c299b1f86e4f3f3687c52ff9af0b53973419754c8c195fc14d6
3
+ size 5730
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7f4ac37ecdab58330753a76241106b95a54e3a2c06a82d75aefd9645f3c8618
3
+ size 4664