Hugging Face's logo

pbaoo2705
/
falcon-7b-sharded-2

Generated from Trainer
Model card Files Community
pbaoo2705 commited on
Commit
400ecbc
•
1 Parent(s): 0f1894c

QLoRA applied #4

Browse files
Files changed (4) hide show
  1. README.md +1 -1
  2. adapter_config.json +3 -3
  3. adapter_model.bin +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -38,7 +38,7 @@ The following hyperparameters were used during training:
38
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
39
  - lr_scheduler_type: constant
40
  - lr_scheduler_warmup_ratio: 0.03
41
- - training_steps: 500
42
 
43
  ### Training results
44
 
 
38
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
39
  - lr_scheduler_type: constant
40
  - lr_scheduler_warmup_ratio: 0.03
41
+ - training_steps: 600
42
 
43
  ### Training results
44
 
adapter_config.json CHANGED
@@ -16,10 +16,10 @@
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
19
- "dense",
20
  "dense_h_to_4h",
21
- "dense_4h_to_h",
22
- "query_key_value"
 
23
  ],
24
  "task_type": "QUESTION_ANSWERING"
25
  }
 
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
 
19
  "dense_h_to_4h",
20
+ "query_key_value",
21
+ "dense",
22
+ "dense_4h_to_h"
23
  ],
24
  "task_type": "QUESTION_ANSWERING"
25
  }
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2adc0882d2fac6bc73446eb3ee2aab650549ba5f8cdff5abf642b8a61d878c35
3
  size 261226517
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a68ff053219497b38ec722aeaf22be5eb0f7f29d498b64b7a4caf94520bc744e
3
  size 261226517
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d140dc39254311114541b93880aa4c7d50d5096304c401d5aca9d2967ea1483a
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e12d324eceb8abe722ac5da81f53ce4305b679f8478bc9f3494dda75d394776
3
  size 4091