aakarsh-nair
commited on
Commit
•
990d665
1
Parent(s):
090459b
aakarsh-nair/rerun-09-19-2024-experiment-distill-tree-babylm2024-58-2
Browse files- README.md +66 -0
- added_tokens.json +3 -0
- config.json +30 -0
- generation_config.json +7 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Sep19_08-18-31_35b27dd67a12/events.out.tfevents.1726733911.35b27dd67a12.2082.2 +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +44 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: rerun-09-19-2024-experiment-distill-tree-babylm2024-58-2
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# rerun-09-19-2024-experiment-distill-tree-babylm2024-58-2
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 2.6157
|
18 |
+
|
19 |
+
## Model description
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Intended uses & limitations
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- learning_rate: 0.00025
|
37 |
+
- train_batch_size: 64
|
38 |
+
- eval_batch_size: 8
|
39 |
+
- seed: 42
|
40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
+
- lr_scheduler_type: cosine
|
42 |
+
- lr_scheduler_warmup_steps: 200
|
43 |
+
- num_epochs: 10
|
44 |
+
- mixed_precision_training: Native AMP
|
45 |
+
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
50 |
+
| 10.104 | 1.0 | 2065 | 10.4130 |
|
51 |
+
| 5.2452 | 2.0 | 4130 | 5.7628 |
|
52 |
+
| 3.9297 | 3.0 | 6195 | 4.3714 |
|
53 |
+
| 3.3837 | 4.0 | 8260 | 3.7472 |
|
54 |
+
| 2.84 | 5.0 | 10325 | 3.3064 |
|
55 |
+
| 2.6592 | 6.0 | 12390 | 3.0392 |
|
56 |
+
| 2.3847 | 7.0 | 14455 | 2.8177 |
|
57 |
+
| 2.2605 | 8.0 | 16520 | 2.6904 |
|
58 |
+
| 2.1446 | 9.0 | 18585 | 2.6290 |
|
59 |
+
| 2.1841 | 10.0 | 20650 | 2.6157 |
|
60 |
+
|
61 |
+
|
62 |
+
### Framework versions
|
63 |
+
|
64 |
+
- Transformers 4.45.0.dev0
|
65 |
+
- Pytorch 2.4.0+cu121
|
66 |
+
- Tokenizers 0.19.1
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 16000
|
3 |
+
}
|
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"LlamaForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_bias": false,
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"head_dim": 64,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 512,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 1024,
|
14 |
+
"max_position_embeddings": 256,
|
15 |
+
"mlp_bias": false,
|
16 |
+
"model_type": "llama",
|
17 |
+
"num_attention_heads": 8,
|
18 |
+
"num_hidden_layers": 16,
|
19 |
+
"num_key_value_heads": 8,
|
20 |
+
"pad_token_id": 0,
|
21 |
+
"pretraining_tp": 1,
|
22 |
+
"rms_norm_eps": 1e-06,
|
23 |
+
"rope_scaling": null,
|
24 |
+
"rope_theta": 10000.0,
|
25 |
+
"tie_word_embeddings": false,
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.45.0.dev0",
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 16000
|
30 |
+
}
|
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": "4.45.0.dev0"
|
7 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f13eb5532c0b18903062d5313a0eee887fc4af3ed9ac7f646d841072a8597d6d
|
3 |
+
size 233392032
|
runs/Sep19_08-18-31_35b27dd67a12/events.out.tfevents.1726733911.35b27dd67a12.2082.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f8764a4792805d8c629899f49ed189e8073b711475af1883aaad7046b2f8351
|
3 |
+
size 226721
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "<pad>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<pad>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<s>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"16000": {
|
29 |
+
"content": "<|endoftext|>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
}
|
36 |
+
},
|
37 |
+
"bos_token": "<s>",
|
38 |
+
"clean_up_tokenization_spaces": true,
|
39 |
+
"eos_token": "</s>",
|
40 |
+
"model_max_length": 128,
|
41 |
+
"pad_token": "<pad>",
|
42 |
+
"tokenizer_class": "GPT2Tokenizer",
|
43 |
+
"unk_token": "<|endoftext|>"
|
44 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bcea27793cdbfd11d2e3c6fbd34e4316dba4bf37211852fa96ade0058885ce0d
|
3 |
+
size 5368
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|