dmariko commited on
Commit
92556bb
1 Parent(s): 302ca49

HuggingFaceTB/SmolLM-360M-Instruct

Browse files
README.md CHANGED
@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [HuggingFaceTB/SmolLM-360M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM-360M-Instruct) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 2.0409
24
 
25
  ## Model description
26
 
@@ -39,7 +39,7 @@ More information needed
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
- - learning_rate: 0.0002
43
  - train_batch_size: 8
44
  - eval_batch_size: 8
45
  - seed: 42
@@ -51,18 +51,32 @@ The following hyperparameters were used during training:
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: constant
53
  - lr_scheduler_warmup_ratio: 0.03
54
- - num_epochs: 6
55
 
56
  ### Training results
57
 
58
- | Training Loss | Epoch | Step | Validation Loss |
59
- |:-------------:|:------:|:----:|:---------------:|
60
- | 2.3444 | 0.9524 | 10 | 2.3038 |
61
- | 2.2609 | 2.0 | 21 | 2.1919 |
62
- | 2.1732 | 2.9524 | 31 | 2.1334 |
63
- | 2.1255 | 4.0 | 42 | 2.0941 |
64
- | 2.0831 | 4.9524 | 52 | 2.0632 |
65
- | 2.0563 | 5.7143 | 60 | 2.0409 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
66
 
67
 
68
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [HuggingFaceTB/SmolLM-360M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM-360M-Instruct) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 1.7710
24
 
25
  ## Model description
26
 
 
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
+ - learning_rate: 0.001
43
  - train_batch_size: 8
44
  - eval_batch_size: 8
45
  - seed: 42
 
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: constant
53
  - lr_scheduler_warmup_ratio: 0.03
54
+ - num_epochs: 20
55
 
56
  ### Training results
57
 
58
+ | Training Loss | Epoch | Step | Validation Loss |
59
+ |:-------------:|:-------:|:----:|:---------------:|
60
+ | 2.2354 | 0.9524 | 10 | 2.1179 |
61
+ | 2.0715 | 2.0 | 21 | 2.0075 |
62
+ | 1.9885 | 2.9524 | 31 | 1.9518 |
63
+ | 1.9385 | 4.0 | 42 | 1.9090 |
64
+ | 1.8925 | 4.9524 | 52 | 1.8811 |
65
+ | 1.867 | 6.0 | 63 | 1.8578 |
66
+ | 1.8507 | 6.9524 | 73 | 1.8416 |
67
+ | 1.8314 | 8.0 | 84 | 1.8279 |
68
+ | 1.8086 | 8.9524 | 94 | 1.8177 |
69
+ | 1.7969 | 10.0 | 105 | 1.8085 |
70
+ | 1.7858 | 10.9524 | 115 | 1.8016 |
71
+ | 1.7711 | 12.0 | 126 | 1.7957 |
72
+ | 1.7616 | 12.9524 | 136 | 1.7904 |
73
+ | 1.7504 | 14.0 | 147 | 1.7854 |
74
+ | 1.7399 | 14.9524 | 157 | 1.7821 |
75
+ | 1.732 | 16.0 | 168 | 1.7791 |
76
+ | 1.7218 | 16.9524 | 178 | 1.7755 |
77
+ | 1.7142 | 18.0 | 189 | 1.7735 |
78
+ | 1.6992 | 18.9524 | 199 | 1.7708 |
79
+ | 1.6993 | 19.0476 | 200 | 1.7710 |
80
 
81
 
82
  ### Framework versions
adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "gate_proj",
24
- "up_proj",
25
  "o_proj",
26
  "q_proj",
27
- "k_proj",
28
- "down_proj",
29
- "v_proj"
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "k_proj",
 
24
  "o_proj",
25
  "q_proj",
26
+ "gate_proj",
27
+ "v_proj",
28
+ "up_proj",
29
+ "down_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e0216683abaa9c920d78c4c5a90aed2f701cdb4ae4b481dc09618211a026e35d
3
  size 17426248
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31c655e84ff620beca55c5028fc8e5f810800373205f1a8dab2d4379558b1bef
3
  size 17426248
runs/Aug28_13-15-09_algo-1/events.out.tfevents.1724850924.algo-1.67.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f93a6bb2ccc83a4cd3e3ac02d6438a63a93a6aa05d9ae451b70af47e501e78c
3
+ size 15294
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d57dd6dc0a640f00c6f19e312c5fd1fd07932eb590221acbbcd4acbb9a2c7ba0
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fef496847ab2924b511e4f67bfdd2b7f90755757b282a49c79c06fd4b763a1a
3
  size 5240