Hugging Face's logo

Litzy619
/
AOLM2

Safetensors
Generated from Trainer
Model card Files
xet
Community
Litzy619 commited on
Commit
ebd46cc
·
verified ·
1 Parent(s): ba22b57

End of training

Browse files
Files changed (4) hide show
  1. README.md +34 -34
  2. adapter_config.json +1 -1
  3. model.safetensors +1 -1
  4. training_args.bin +1 -1
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: 0.1410
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
- | 2.9303 | 0.09 | 10 | 0.9380 |
54
- | 0.3692 | 0.18 | 20 | 0.1548 |
55
- | 0.1539 | 0.27 | 30 | 0.1633 |
56
- | 0.1561 | 0.36 | 40 | 0.1560 |
57
- | 0.1518 | 0.45 | 50 | 0.1541 |
58
- | 0.1518 | 0.54 | 60 | 0.1478 |
59
- | 0.1488 | 0.63 | 70 | 0.1481 |
60
- | 0.1486 | 0.73 | 80 | 0.1550 |
61
- | 0.1467 | 0.82 | 90 | 0.1513 |
62
- | 0.1476 | 0.91 | 100 | 0.1491 |
63
- | 0.149 | 1.0 | 110 | 0.1483 |
64
- | 0.1456 | 1.09 | 120 | 0.1493 |
65
- | 0.1442 | 1.18 | 130 | 0.1517 |
66
- | 0.1474 | 1.27 | 140 | 0.1478 |
67
- | 0.1482 | 1.36 | 150 | 0.1495 |
68
- | 0.1455 | 1.45 | 160 | 0.1479 |
69
- | 0.1455 | 1.54 | 170 | 0.1474 |
70
- | 0.1467 | 1.63 | 180 | 0.1452 |
71
- | 0.1464 | 1.72 | 190 | 0.1486 |
72
- | 0.145 | 1.81 | 200 | 0.1469 |
73
- | 0.1485 | 1.9 | 210 | 0.1460 |
74
- | 0.1453 | 1.99 | 220 | 0.1480 |
75
- | 0.1432 | 2.08 | 230 | 0.1456 |
76
- | 0.1376 | 2.18 | 240 | 0.1444 |
77
- | 0.1392 | 2.27 | 250 | 0.1451 |
78
- | 0.1385 | 2.36 | 260 | 0.1441 |
79
- | 0.137 | 2.45 | 270 | 0.1441 |
80
- | 0.1352 | 2.54 | 280 | 0.1420 |
81
- | 0.1338 | 2.63 | 290 | 0.1423 |
82
- | 0.1352 | 2.72 | 300 | 0.1410 |
83
- | 0.1351 | 2.81 | 310 | 0.1407 |
84
- | 0.1317 | 2.9 | 320 | 0.1409 |
85
- | 0.1361 | 2.99 | 330 | 0.1410 |
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: 0.1428
19
 
20
  ## Model description
21
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
+ | 2.9303 | 0.09 | 10 | 0.9652 |
54
+ | 0.3692 | 0.18 | 20 | 0.1604 |
55
+ | 0.1539 | 0.27 | 30 | 0.1626 |
56
+ | 0.1561 | 0.36 | 40 | 0.1535 |
57
+ | 0.1518 | 0.45 | 50 | 0.1511 |
58
+ | 0.1518 | 0.54 | 60 | 0.1483 |
59
+ | 0.1488 | 0.63 | 70 | 0.1485 |
60
+ | 0.1486 | 0.73 | 80 | 0.1528 |
61
+ | 0.1467 | 0.82 | 90 | 0.1504 |
62
+ | 0.1476 | 0.91 | 100 | 0.1485 |
63
+ | 0.149 | 1.0 | 110 | 0.1477 |
64
+ | 0.1456 | 1.09 | 120 | 0.1490 |
65
+ | 0.1442 | 1.18 | 130 | 0.1499 |
66
+ | 0.1474 | 1.27 | 140 | 0.1479 |
67
+ | 0.1482 | 1.36 | 150 | 0.1486 |
68
+ | 0.1455 | 1.45 | 160 | 0.1483 |
69
+ | 0.1455 | 1.54 | 170 | 0.1467 |
70
+ | 0.1467 | 1.63 | 180 | 0.1455 |
71
+ | 0.1464 | 1.72 | 190 | 0.1485 |
72
+ | 0.145 | 1.81 | 200 | 0.1468 |
73
+ | 0.1485 | 1.9 | 210 | 0.1458 |
74
+ | 0.1453 | 1.99 | 220 | 0.1477 |
75
+ | 0.1432 | 2.08 | 230 | 0.1457 |
76
+ | 0.1376 | 2.18 | 240 | 0.1447 |
77
+ | 0.1392 | 2.27 | 250 | 0.1446 |
78
+ | 0.1385 | 2.36 | 260 | 0.1443 |
79
+ | 0.137 | 2.45 | 270 | 0.1444 |
80
+ | 0.1352 | 2.54 | 280 | 0.1436 |
81
+ | 0.1338 | 2.63 | 290 | 0.1435 |
82
+ | 0.1352 | 2.72 | 300 | 0.1430 |
83
+ | 0.1351 | 2.81 | 310 | 0.1428 |
84
+ | 0.1317 | 2.9 | 320 | 0.1430 |
85
+ | 0.1361 | 2.99 | 330 | 0.1428 |
86
 
87
 
88
  ### Framework versions
adapter_config.json CHANGED
@@ -20,7 +20,7 @@
20
  "pool_selective_training": true,
21
  "r": 16,
22
  "random_routing": false,
23
- "random_routing_inference": false,
24
  "selective_num": 8,
25
  "simple_hidden_matching": false,
26
  "simple_instance_matching": true,
 
20
  "pool_selective_training": true,
21
  "r": 16,
22
  "random_routing": false,
23
+ "random_routing_inference": true,
24
  "selective_num": 8,
25
  "simple_hidden_matching": false,
26
  "simple_instance_matching": true,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f327b959b58b66f5656911d5ebe51dffc9d77f1bf6d456c28dbc02d18b9c89b5
3
  size 4776316480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ea63e3b17c0479e4b28b0635a5b8db0792f97c44feba092d75df6d6e7ec408e
3
  size 4776316480
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d2e18687701770a833fe7ff80e65ef51d25b07be3c73322f9d3fdd82a430e88
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06c01c8eed8de70302041110f8064b38a4c6ec342e686b91713421af867992fd
3
  size 5112