Hugging Face's logo

zzzwisebird
/
finetune_starcoder2

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files
xet
Community
zzzwisebird commited on
Commit
091e727
·
verified ·
1 Parent(s): 67f7e54

Upload model

Browse files
Files changed (6) hide show
  1. README.md +1 -1
  2. adapter_config.json +4 -4
  3. adapter_model.safetensors +1 -1
  4. final_checkpoint/model.safetensors +1 -1
  5. tokenizer.json +6 -1
  6. training_args.bin +1 -1
README.md CHANGED
@@ -44,7 +44,7 @@ The following hyperparameters were used during training:
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: cosine
46
  - lr_scheduler_warmup_steps: 20
47
- - training_steps: 100
48
 
49
  ### Training results
50
 
 
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: cosine
46
  - lr_scheduler_warmup_steps: 20
47
+ - training_steps: 200
48
 
49
  ### Training results
50
 
adapter_config.json CHANGED
@@ -19,13 +19,13 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "down_proj",
23
- "q_proj",
24
  "gate_proj",
25
- "o_proj",
26
  "k_proj",
 
27
  "v_proj",
28
- "up_proj"
 
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "use_rslora": false
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
+ "up_proj",
 
23
  "gate_proj",
 
24
  "k_proj",
25
+ "o_proj",
26
  "v_proj",
27
+ "q_proj",
28
+ "down_proj"
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "use_rslora": false
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ae8880cedb79e36703cdbf34c8927549c111360fb7fa37c110471f96ee1e1ba
3
  size 18218008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41e59c3145a70e9c9a34da09e341e6d016184e8f523c0cf6e8576cfb17199ece
3
  size 18218008
final_checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:513d1f3c6019da4f2af65f94aeb1bc0c366460f55623ee1d676d0d83da59dfe1
3
  size 2245556180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed211344e91b85c3fddb53cd877eccbdf06575a9907684876de0f573c99ba31f
3
  size 2245556180
tokenizer.json CHANGED
@@ -1,6 +1,11 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 256,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
  "padding": null,
10
  "added_tokens": [
11
  {
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f680d8f04bd8a21b8e507fed51cfb20280da9761f7e5b25a4d66fc832c199020
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64b03d138e8086ef79dbc9813f6d8630b7c5cbfc8cc7becbfd6d1156da0a83e0
3
  size 4920