Model save
Browse files
README.md
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
metrics:
|
5 |
+
- accuracy
|
6 |
+
model-index:
|
7 |
+
- name: smolm-autoreg-bpe-counterfactual-babylm-pipps_10k-1e-3
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# smolm-autoreg-bpe-counterfactual-babylm-pipps_10k-1e-3
|
15 |
+
|
16 |
+
This model was trained from scratch on the None dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 3.3378
|
19 |
+
- Accuracy: 0.4121
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 0.001
|
39 |
+
- train_batch_size: 32
|
40 |
+
- eval_batch_size: 64
|
41 |
+
- seed: 42
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- lr_scheduler_warmup_steps: 32000
|
45 |
+
- num_epochs: 20.0
|
46 |
+
- mixed_precision_training: Native AMP
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
+
|:-------------:|:-----:|:------:|:---------------:|:--------:|
|
52 |
+
| 3.6013 | 1.0 | 18720 | 3.7465 | 0.3588 |
|
53 |
+
| 3.3867 | 2.0 | 37440 | 3.4883 | 0.3819 |
|
54 |
+
| 3.2589 | 3.0 | 56160 | 3.4083 | 0.3943 |
|
55 |
+
| 3.1811 | 4.0 | 74880 | 3.3900 | 0.3986 |
|
56 |
+
| 3.1273 | 5.0 | 93600 | 3.3351 | 0.4020 |
|
57 |
+
| 3.0824 | 6.0 | 112320 | 3.3293 | 0.4028 |
|
58 |
+
| 3.0466 | 7.0 | 131040 | 3.3131 | 0.4065 |
|
59 |
+
| 3.0117 | 8.0 | 149760 | 3.2990 | 0.4092 |
|
60 |
+
| 2.9899 | 9.0 | 168480 | 3.2979 | 0.4097 |
|
61 |
+
| 2.9556 | 10.0 | 187200 | 3.2939 | 0.4105 |
|
62 |
+
| 2.9395 | 11.0 | 205920 | 3.2948 | 0.4120 |
|
63 |
+
| 2.9155 | 12.0 | 224640 | 3.3005 | 0.4110 |
|
64 |
+
| 2.8971 | 13.0 | 243360 | 3.2907 | 0.4126 |
|
65 |
+
| 2.8777 | 14.0 | 262080 | 3.2993 | 0.4121 |
|
66 |
+
| 2.8546 | 15.0 | 280800 | 3.2985 | 0.4128 |
|
67 |
+
| 2.8337 | 16.0 | 299520 | 3.2980 | 0.4130 |
|
68 |
+
| 2.8153 | 17.0 | 318240 | 3.3254 | 0.4116 |
|
69 |
+
| 2.799 | 18.0 | 336960 | 3.3345 | 0.4114 |
|
70 |
+
| 2.7824 | 19.0 | 355680 | 3.3410 | 0.4117 |
|
71 |
+
| 2.7614 | 20.0 | 374400 | 3.3378 | 0.4121 |
|
72 |
+
|
73 |
+
|
74 |
+
### Framework versions
|
75 |
+
|
76 |
+
- Transformers 4.35.0
|
77 |
+
- Pytorch 2.1.0+cu121
|
78 |
+
- Datasets 2.12.0
|
79 |
+
- Tokenizers 0.14.1
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.35.0"
|
7 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 391376736
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e0b8ad41d78a7c075fcabcdb5e5b0e6ad12ffe1274a160a6ae2c018ed1bcc64
|
3 |
size 391376736
|
runs/Jan28_21-00-34_phyl-ling-p01.la.utexas.edu/events.out.tfevents.1706497587.phyl-ling-p01.la.utexas.edu.2501562.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d75c09802b4b66156e75337161fc172514f08f7aed29447a776cb8734b046fb
|
3 |
+
size 71292
|