Hugging Face's logo

Litzy619
/
O0428HMA1

Safetensors
Generated from Trainer
Model card Files
xet
 Community
Litzy619 commited on
Commit
386ff2a
·
verified ·
1 Parent(s): b58c193

End of training

Browse files
Files changed (6) hide show
  1. README.md +34 -34
  2. adapter_config.json +27 -2
  3. adapter_model.bin +2 -2
  4. model.safetensors +2 -2
  5. tokenizer.json +6 -1
  6. training_args.bin +2 -2
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [allenai/OLMo-1B](https://huggingface.co/allenai/OLMo-1B) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.1452
19
 
20
  ## Model description
21
 
@@ -50,39 +50,39 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
- | 1.8046 | 0.09 | 10 | 0.6641 |
54
- | 0.2763 | 0.18 | 20 | 0.1556 |
55
- | 0.1495 | 0.27 | 30 | 0.1607 |
56
- | 0.1527 | 0.36 | 40 | 0.1512 |
57
- | 0.148 | 0.45 | 50 | 0.1490 |
58
- | 0.1487 | 0.54 | 60 | 0.1498 |
59
- | 0.1478 | 0.63 | 70 | 0.1489 |
60
- | 0.1488 | 0.73 | 80 | 0.1495 |
61
- | 0.1462 | 0.82 | 90 | 0.1497 |
62
- | 0.1478 | 0.91 | 100 | 0.1485 |
63
- | 0.1489 | 1.0 | 110 | 0.1505 |
64
- | 0.1461 | 1.09 | 120 | 0.1490 |
65
- | 0.1453 | 1.18 | 130 | 0.1512 |
66
- | 0.1463 | 1.27 | 140 | 0.1500 |
67
- | 0.1486 | 1.36 | 150 | 0.1461 |
68
- | 0.1443 | 1.45 | 160 | 0.1488 |
69
- | 0.1451 | 1.54 | 170 | 0.1471 |
70
- | 0.1465 | 1.63 | 180 | 0.1459 |
71
- | 0.1467 | 1.72 | 190 | 0.1507 |
72
- | 0.1448 | 1.81 | 200 | 0.1499 |
73
- | 0.1496 | 1.9 | 210 | 0.1465 |
74
- | 0.1459 | 1.99 | 220 | 0.1497 |
75
- | 0.146 | 2.08 | 230 | 0.1464 |
76
- | 0.1401 | 2.18 | 240 | 0.1460 |
77
- | 0.1427 | 2.27 | 250 | 0.1473 |
78
- | 0.1439 | 2.36 | 260 | 0.1472 |
79
- | 0.1421 | 2.45 | 270 | 0.1460 |
80
- | 0.1408 | 2.54 | 280 | 0.1458 |
81
- | 0.1406 | 2.63 | 290 | 0.1466 |
82
- | 0.1442 | 2.72 | 300 | 0.1452 |
83
- | 0.1436 | 2.81 | 310 | 0.1451 |
84
- | 0.1426 | 2.9 | 320 | 0.1452 |
85
- | 0.1438 | 2.99 | 330 | 0.1452 |
86
 
87
 
88
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [allenai/OLMo-1B](https://huggingface.co/allenai/OLMo-1B) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.0540
19
 
20
  ## Model description
21
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
+ | 1.8099 | 0.09 | 10 | 0.1912 |
54
+ | 0.1798 | 0.18 | 20 | 0.1531 |
55
+ | 0.1494 | 0.27 | 30 | 0.1613 |
56
+ | 0.1557 | 0.36 | 40 | 0.1576 |
57
+ | 0.1505 | 0.45 | 50 | 0.1489 |
58
+ | 0.1502 | 0.54 | 60 | 0.1467 |
59
+ | 0.1486 | 0.63 | 70 | 0.1468 |
60
+ | 0.1478 | 0.73 | 80 | 0.1530 |
61
+ | 0.1418 | 0.82 | 90 | 0.1254 |
62
+ | 0.1393 | 0.91 | 100 | 0.1264 |
63
+ | 0.114 | 1.0 | 110 | 0.0868 |
64
+ | 0.0713 | 1.09 | 120 | 0.0721 |
65
+ | 0.0753 | 1.18 | 130 | 0.1096 |
66
+ | 0.0868 | 1.27 | 140 | 0.0649 |
67
+ | 0.124 | 1.36 | 150 | 0.0621 |
68
+ | 0.058 | 1.45 | 160 | 0.0572 |
69
+ | 0.0688 | 1.54 | 170 | 0.0600 |
70
+ | 0.0626 | 1.63 | 180 | 0.0618 |
71
+ | 0.0673 | 1.72 | 190 | 0.0575 |
72
+ | 0.0579 | 1.81 | 200 | 0.0574 |
73
+ | 0.0592 | 1.9 | 210 | 0.0554 |
74
+ | 0.0577 | 1.99 | 220 | 0.0546 |
75
+ | 0.0568 | 2.08 | 230 | 0.0548 |
76
+ | 0.0807 | 2.18 | 240 | 0.0912 |
77
+ | 0.0728 | 2.27 | 250 | 0.0610 |
78
+ | 0.0629 | 2.36 | 260 | 0.0589 |
79
+ | 0.0554 | 2.45 | 270 | 0.0552 |
80
+ | 0.0523 | 2.54 | 280 | 0.0547 |
81
+ | 0.0544 | 2.63 | 290 | 0.0560 |
82
+ | 0.0551 | 2.72 | 300 | 0.0541 |
83
+ | 0.056 | 2.81 | 310 | 0.0539 |
84
+ | 0.0574 | 2.9 | 320 | 0.0540 |
85
+ | 0.0586 | 2.99 | 330 | 0.0540 |
86
 
87
 
88
  ### Framework versions
adapter_config.json CHANGED
@@ -1,18 +1,43 @@
1
  {
 
 
 
2
  "auto_mapping": null,
3
  "base_model_name_or_path": "allenai/OLMo-1B",
4
  "bias": "none",
 
 
 
5
  "enable_lora": null,
 
6
  "fan_in_fan_out": false,
 
7
  "inference_mode": true,
 
8
  "lora_alpha": 16,
9
  "lora_dropout": 0.05,
10
  "merge_weights": false,
11
  "modules_to_save": null,
12
- "peft_type": "LORA",
 
 
 
 
 
 
 
 
 
 
 
13
  "r": 16,
 
 
 
 
14
  "target_modules": [
15
  "attn_out"
16
  ],
17
- "task_type": "CAUSAL_LM"
 
18
  }
 
1
  {
2
+ "adaptive_ratio": 0.01,
3
+ "adaptive_ratio_decay": 1.0,
4
+ "additive_modeling": false,
5
  "auto_mapping": null,
6
  "base_model_name_or_path": "allenai/OLMo-1B",
7
  "bias": "none",
8
+ "curr_learning": true,
9
+ "detached_training": true,
10
+ "dynamic_adapter_pool": true,
11
  "enable_lora": null,
12
+ "encoder_hidden_size": 2048,
13
  "fan_in_fan_out": false,
14
+ "hypernetwork": true,
15
  "inference_mode": true,
16
+ "input_based_adapter_selection": true,
17
  "lora_alpha": 16,
18
  "lora_dropout": 0.05,
19
  "merge_weights": false,
20
  "modules_to_save": null,
21
+ "num_attention_heads": 16,
22
+ "num_layers": 16,
23
+ "num_prefix_set": 3,
24
+ "num_transformer_submodules": 1,
25
+ "num_virtual_tokens": 30,
26
+ "number_of_adapter_pre_layer": 8,
27
+ "ot_diversified_dispatcher": false,
28
+ "ot_diversified_prefix": false,
29
+ "peft_type": "PREFIX_MA_LORA",
30
+ "pool_selective_inference": true,
31
+ "pool_selective_training": true,
32
+ "prefix_projection": true,
33
  "r": 16,
34
+ "scale": 64,
35
+ "selective_num": 8,
36
+ "simple_hidden_matching": false,
37
+ "simple_instance_matching": true,
38
  "target_modules": [
39
  "attn_out"
40
  ],
41
+ "task_type": "CAUSAL_LM",
42
+ "token_dim": 2048
43
  }
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd7392b0b684e4b27c1356675552fa4f046735d974180a3bf659c74097d1b697
3
- size 2108942
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af04a03c7f8ade6755b08dbb944d25d7535357db501c61546b46a66e094562ad
3
+ size 101036502
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82450d3abb86d29402848cf283275cd633732f5c4fdf16a2d11ec85f5d0175cf
3
- size 4709168176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f78a8ee84d1d34a459f88cef3445389313a40085cc2c581db4e64d0b9acca86
3
+ size 4774383804
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": 128,
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:bef2db007a0b7270f540e00c401d12f41aa77bcad42b09bb1c3fad268f8476ad
3
- size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d086993ff875ad4162e2b32d5c4f2cfefeddf38d05c9c3a670112179f850766d
3
+ size 5176