imdatta0 commited on
Commit
b50c988
1 Parent(s): bf97174

End of training

Browse files
.gitattributes CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  nipsllm_3601.1733584591283538056.pt.trace.json filter=lfs diff=lfs merge=lfs -text
 
 
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  nipsllm_3601.1733584591283538056.pt.trace.json filter=lfs diff=lfs merge=lfs -text
37
+ nipsllm_13350.1733587985088903357.pt.trace.json filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.2332
21
 
22
  ## Model description
23
 
@@ -45,7 +45,7 @@ The following hyperparameters were used during training:
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: cosine
47
  - lr_scheduler_warmup_ratio: 0.02
48
- - num_epochs: 0.36
49
 
50
  ### Training results
51
 
@@ -79,6 +79,9 @@ The following hyperparameters were used during training:
79
  | 1.2469 | 0.3368 | 52 | 1.2331 |
80
  | 1.1653 | 0.3498 | 54 | 1.2330 |
81
  | 1.2752 | 0.3628 | 56 | 1.2332 |
 
 
 
82
 
83
 
84
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 1.2331
21
 
22
  ## Model description
23
 
 
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: cosine
47
  - lr_scheduler_warmup_ratio: 0.02
48
+ - num_epochs: 0.4
49
 
50
  ### Training results
51
 
 
79
  | 1.2469 | 0.3368 | 52 | 1.2331 |
80
  | 1.1653 | 0.3498 | 54 | 1.2330 |
81
  | 1.2752 | 0.3628 | 56 | 1.2332 |
82
+ | 1.2077 | 0.3757 | 58 | 1.2331 |
83
+ | 1.1729 | 0.3887 | 60 | 1.2330 |
84
+ | 1.2643 | 0.4016 | 62 | 1.2331 |
85
 
86
 
87
  ### Framework versions
adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "down_proj",
24
  "up_proj",
25
- "gate_proj",
26
- "o_proj",
27
- "k_proj",
28
  "q_proj",
29
- "v_proj"
 
 
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "up_proj",
 
 
 
24
  "q_proj",
25
+ "k_proj",
26
+ "v_proj",
27
+ "o_proj",
28
+ "down_proj",
29
+ "gate_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
nipsllm_13350.1733587985088903357.pt.trace.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a49e55b6fc8b50e7db83fc03202259c26e51bff767c1c57b8612b194e4eb244
3
+ size 9843112280
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8e71666af93ec5efe9027402a294dba7d8cefad3a830d40cac2832c39216075
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4acdf5d9d14749a7ba943f69011cd34aabbb367437fc76cd520d695b4617adad
3
  size 5304