lapp0 commited on
Commit
cd11314
1 Parent(s): 64bf8d5

End of training

Browse files
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