End of training
Browse files- README.md +91 -0
- config.json +62 -0
- generation_config.json +6 -0
- logs/copy_teacher_modules=_(_lm_head___False)_, learning_rate=1e-06/events.out.tfevents.1723998400.5f530b1cf724 +3 -0
- logs/copy_teacher_modules=_(_lm_head___False)_, learning_rate=1e-06/events.out.tfevents.1724005521.5f530b1cf724 +3 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +22 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: roneneldan/TinyStories-33M
|
3 |
+
library_name: Distily
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: distily_bench_obj_cross_v2.10
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
# distily_bench_obj_cross_v2.10
|
12 |
+
|
13 |
+
This student model is distilled from the teacher model [roneneldan/TinyStories-33M](https://huggingface.co/roneneldan/TinyStories-33M) using the dataset (unspecified).
|
14 |
+
|
15 |
+
The [Distily](https://github.com/lapp0/distily) library was used for this distillation.
|
16 |
+
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- eval_enwikippl: 4839.0244
|
19 |
+
- eval_frwikippl: 39016.5469
|
20 |
+
- eval_zhwikippl: 56057.3555
|
21 |
+
- eval_tinystoriesppl: 1738.1987
|
22 |
+
- eval_loss: 4.8480
|
23 |
+
- eval_runtime: 13.0187
|
24 |
+
- eval_samples_per_second: 76.813
|
25 |
+
- eval_steps_per_second: 9.602
|
26 |
+
|
27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
28 |
+
should probably proofread and complete it, then remove this comment.
|
29 |
+
|
30 |
+
## Model description
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Intended uses & limitations
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training and evaluation data
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
-->
|
42 |
+
|
43 |
+
## Training procedure
|
44 |
+
|
45 |
+
### Training hyperparameters
|
46 |
+
|
47 |
+
The following hyperparameters were used during training:
|
48 |
+
- distillation_objective: DistillationObjective(logits_loss_component=LossComponent(label=logits, weight=1, loss_fn=kl, layer_mapper=None, projector=None), hs_loss_component=LossComponent(label=hs, weight=0, loss_fn=None, layer_mapper=None, projector=None), attn_loss_component=LossComponent(label=attn, weight=0, loss_fn=None, layer_mapper=None, projector=None))
|
49 |
+
- train_embeddings: True
|
50 |
+
- learning_rate: 1e-06
|
51 |
+
- train_batch_size: 1
|
52 |
+
- eval_batch_size: 8
|
53 |
+
- seed: 42
|
54 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
55 |
+
- lr_scheduler_type: linear
|
56 |
+
- num_epochs: 1.0
|
57 |
+
|
58 |
+
### Resource Usage
|
59 |
+
Peak GPU Memory: 6.6048 GB
|
60 |
+
|
61 |
+
### Eval-Phase Metrics
|
62 |
+
| step | epoch | enwikippl | frwikippl | loss | runtime | samples_per_second | steps_per_second | tinystoriesppl | zhwikippl |
|
63 |
+
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
|
64 |
+
| **teacher eval** | | 169.9865 | 47377.9414 | | | | | 3.9789 | 4998.1294 |
|
65 |
+
| 0 | 0 | 23326.0117 | 54995.6562 | 6.1135 | 13.0206 | 76.802 | 9.6 | 17003.8281 | 65438.9492 |
|
66 |
+
| 5000 | 0.0505 | 4839.0244 | 39016.5469 | 4.8478 | 13.0137 | 76.842 | 9.605 | 1738.1987 | 56102.2266 |
|
67 |
+
| 10000 | 0.1010 | 4839.0244 | 39016.5469 | 4.8480 | 12.9688 | 77.108 | 9.639 | 1738.1987 | 56087.25 |
|
68 |
+
| 15000 | 0.1515 | 4839.0244 | 39016.5469 | 4.8488 | 12.9532 | 77.201 | 9.65 | 1739.0610 | 56102.2266 |
|
69 |
+
| 20000 | 0.2020 | 4839.0244 | 39016.5469 | 4.8488 | 13.014 | 76.84 | 9.605 | 1738.4856 | 56072.2734 |
|
70 |
+
| 25000 | 0.2525 | 4839.0244 | 39016.5469 | 4.8485 | 13.0041 | 76.899 | 9.612 | 1738.1987 | 56057.3555 |
|
71 |
+
| 30000 | 0.3030 | 4839.0244 | 39016.5469 | 4.8488 | 12.9823 | 77.028 | 9.629 | 1738.4856 | 56057.3555 |
|
72 |
+
| 35000 | 0.3535 | 4839.0244 | 39016.5469 | 4.8485 | 13.037 | 76.705 | 9.588 | 1739.0610 | 56072.2734 |
|
73 |
+
| 40000 | 0.4040 | 4839.0244 | 39016.5469 | 4.8482 | 12.9918 | 76.972 | 9.621 | 1738.1987 | 56057.3555 |
|
74 |
+
| 45000 | 0.4545 | 4839.0244 | 38994.5625 | 4.8485 | 12.9951 | 76.952 | 9.619 | 1738.7732 | 56057.3555 |
|
75 |
+
| 50000 | 0.5051 | 4839.0244 | 39016.5469 | 4.8482 | 12.9731 | 77.083 | 9.635 | 1739.3488 | 56072.2734 |
|
76 |
+
| 55000 | 0.5556 | 4839.0244 | 39016.5469 | 4.8478 | 12.9694 | 77.105 | 9.638 | 1738.4856 | 56057.3555 |
|
77 |
+
| 60000 | 0.6061 | 4839.0244 | 39016.5469 | 4.8488 | 13.0353 | 76.715 | 9.589 | 1738.7732 | 56057.3555 |
|
78 |
+
| 65000 | 0.6566 | 4839.0244 | 39016.5469 | 4.8478 | 13.0087 | 76.872 | 9.609 | 1738.1987 | 56057.3555 |
|
79 |
+
| 70000 | 0.7071 | 4839.0244 | 39016.5469 | 4.8485 | 13.033 | 76.728 | 9.591 | 1738.1987 | 56057.3555 |
|
80 |
+
| 75000 | 0.7576 | 4839.0244 | 39016.5469 | 4.8480 | 13.0328 | 76.729 | 9.591 | 1738.4856 | 56057.3555 |
|
81 |
+
| 80000 | 0.8081 | 4839.0244 | 39016.5469 | 4.8482 | 12.9884 | 76.992 | 9.624 | 1737.9111 | 56057.3555 |
|
82 |
+
| 85000 | 0.8586 | 4839.0244 | 39016.5469 | 4.8485 | 13.0047 | 76.895 | 9.612 | 1738.1987 | 56087.25 |
|
83 |
+
| 90000 | 0.9091 | 4839.0244 | 39016.5469 | 4.8478 | 13.0255 | 76.772 | 9.597 | 1738.1987 | 56057.3555 |
|
84 |
+
| 95000 | 0.9596 | 4839.0244 | 39016.5469 | 4.8482 | 13.0007 | 76.919 | 9.615 | 1738.1987 | 56057.3555 |
|
85 |
+
| 99000 | 1.0 | 4839.0244 | 39016.5469 | 4.8480 | 13.0187 | 76.813 | 9.602 | 1738.1987 | 56057.3555 |
|
86 |
+
|
87 |
+
### Framework versions
|
88 |
+
- Distily 0.2.0
|
89 |
+
- Transformers 4.44.0
|
90 |
+
- Pytorch 2.3.0
|
91 |
+
- Datasets 2.21.0
|
config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roneneldan/TinyStories-33M",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPTNeoForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0,
|
8 |
+
"attention_layers": [
|
9 |
+
"global",
|
10 |
+
"local",
|
11 |
+
"global",
|
12 |
+
"local"
|
13 |
+
],
|
14 |
+
"attention_types": [
|
15 |
+
[
|
16 |
+
[
|
17 |
+
"global",
|
18 |
+
"local"
|
19 |
+
],
|
20 |
+
2
|
21 |
+
]
|
22 |
+
],
|
23 |
+
"bos_token_id": 50256,
|
24 |
+
"classifier_dropout": 0.1,
|
25 |
+
"embed_dropout": 0,
|
26 |
+
"eos_token_id": 50256,
|
27 |
+
"gradient_checkpointing": false,
|
28 |
+
"hidden_size": 768,
|
29 |
+
"initializer_range": 0.02,
|
30 |
+
"intermediate_size": null,
|
31 |
+
"layer_norm_epsilon": 1e-05,
|
32 |
+
"max_position_embeddings": 2048,
|
33 |
+
"model_type": "gpt_neo",
|
34 |
+
"num_heads": 16,
|
35 |
+
"num_layers": 4,
|
36 |
+
"quantization_config": {
|
37 |
+
"_load_in_4bit": false,
|
38 |
+
"_load_in_8bit": true,
|
39 |
+
"bnb_4bit_compute_dtype": "float32",
|
40 |
+
"bnb_4bit_quant_storage": "uint8",
|
41 |
+
"bnb_4bit_quant_type": "fp4",
|
42 |
+
"bnb_4bit_use_double_quant": false,
|
43 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
44 |
+
"llm_int8_has_fp16_weight": false,
|
45 |
+
"llm_int8_skip_modules": null,
|
46 |
+
"llm_int8_threshold": 6.0,
|
47 |
+
"load_in_4bit": false,
|
48 |
+
"load_in_8bit": true,
|
49 |
+
"quant_method": "bitsandbytes"
|
50 |
+
},
|
51 |
+
"resid_dropout": 0,
|
52 |
+
"summary_activation": null,
|
53 |
+
"summary_first_dropout": 0.1,
|
54 |
+
"summary_proj_to_labels": true,
|
55 |
+
"summary_type": "cls_index",
|
56 |
+
"summary_use_proj": true,
|
57 |
+
"torch_dtype": "bfloat16",
|
58 |
+
"transformers_version": "4.44.0",
|
59 |
+
"use_cache": true,
|
60 |
+
"vocab_size": 50257,
|
61 |
+
"window_size": 256
|
62 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.44.0"
|
6 |
+
}
|
logs/copy_teacher_modules=_(_lm_head___False)_, learning_rate=1e-06/events.out.tfevents.1723998400.5f530b1cf724
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6a1da2b0ccd2f87b1550c7e06416bb0b9e139f85ce00b865672b938a9bc2f70
|
3 |
+
size 47487517
|
logs/copy_teacher_modules=_(_lm_head___False)_, learning_rate=1e-06/events.out.tfevents.1724005521.5f530b1cf724
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73414ab075c3fd461913ecb7a65d29b9d5de07447e4bb83586db7ba7ccdf6bf6
|
3 |
+
size 312
|
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 sha256:19cf3e5a17b5ef181ea66a3c2008ea5dc816321a70b4b68a3043e29c10e0de0e
|
3 |
+
size 137033984
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<|endoftext|>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<|endoftext|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"50256": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
}
|
13 |
+
},
|
14 |
+
"bos_token": "<|endoftext|>",
|
15 |
+
"clean_up_tokenization_spaces": true,
|
16 |
+
"eos_token": "<|endoftext|>",
|
17 |
+
"errors": "replace",
|
18 |
+
"model_max_length": 2048,
|
19 |
+
"pad_token": "<|endoftext|>",
|
20 |
+
"tokenizer_class": "GPT2Tokenizer",
|
21 |
+
"unk_token": "<|endoftext|>"
|
22 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:827e2b807e281f8fbb81cfc83cd941fe9ce9532baae53b48e9e0324ef613a9b0
|
3 |
+
size 1017948040
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|