Hugging Face's logo

distily
/
distily_multi_experiment

TensorBoard
Safetensors
Distily
gpt2
bitnet
1.58b
Generated from Trainer
Model card Files Metrics Community
lapp0 commited on
Commit
9f73e81
·
verified ·
1 Parent(s): b5b49a4

Training in progress, step 61875

Browse files
Files changed (7) hide show
  1. README.md +34 -34
  2. config.json +1 -1
  3. generation_config.json +1 -1
  4. logs/attn_loss_fn=cos, attn_weight=25.0, layer_mapper=layer-2, projector=orthogonal/events.out.tfevents.1724423185.f383272e719b +3 -0
  5. logs/attn_loss_fn=cos, attn_weight=5, layer_mapper=layer-2, projector=orthogonal/completed.flag +0 -0
  6. model.safetensors +1 -1
  7. training_args.bin +1 -1
README.md CHANGED
@@ -44,42 +44,42 @@ More information needed
44
  | step | epoch | enwikippl | frwikippl | loss | runtime | samples_per_second | steps_per_second | tinystoriesppl | zhwikippl |
45
  | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
46
  | **teacher eval** | | 43.25 | 61.25 | | | | | 11.6875 | 19.125 |
47
- | 0 | 0 | 2473901162496.0 | 170424302305280.0 | 21.1784 | 25.4629 | 98.182 | 12.292 | 4060086272.0 | 71468255805440.0 |
48
- | 2500 | 0.0404 | 764.0 | 5376.0 | 2.3601 | 25.4683 | 98.161 | 12.29 | 470.0 | 2080.0 |
49
- | 5000 | 0.0808 | 312.0 | 1344.0 | 1.6575 | 25.5021 | 98.031 | 12.274 | 232.0 | 241.0 |
50
- | 7500 | 0.1212 | 210.0 | 744.0 | 1.3794 | 25.4757 | 98.133 | 12.286 | 171.0 | 154.0 |
51
- | 10000 | 0.1616 | 158.0 | 560.0 | 1.1833 | 25.5064 | 98.015 | 12.271 | 129.0 | 155.0 |
52
- | 12500 | 0.2020 | 117.0 | 456.0 | 0.9690 | 25.4693 | 98.157 | 12.289 | 98.5 | 140.0 |
53
- | 15000 | 0.2424 | 103.5 | 420.0 | 0.8624 | 25.4707 | 98.152 | 12.289 | 84.0 | 110.5 |
54
- | 17500 | 0.2828 | 91.5 | 338.0 | 0.7747 | 25.4792 | 98.119 | 12.285 | 74.5 | 108.0 |
55
- | 20000 | 0.3232 | 78.0 | 292.0 | 0.7217 | 25.5053 | 98.019 | 12.272 | 64.5 | 173.0 |
56
- | 22500 | 0.3636 | 70.0 | 240.0 | 0.6259 | 25.4943 | 98.061 | 12.277 | 57.0 | 84.0 |
57
- | 25000 | 0.4040 | 68.0 | 201.0 | 0.5935 | 25.4853 | 98.096 | 12.282 | 53.25 | 143.0 |
58
- | 27500 | 0.4444 | 66.0 | 205.0 | 0.5698 | 25.4724 | 98.146 | 12.288 | 48.75 | 141.0 |
59
- | 30000 | 0.4848 | 65.5 | 231.0 | 0.5773 | 25.4348 | 98.29 | 12.306 | 50.0 | 76.0 |
60
- | 32500 | 0.5253 | 65.5 | 194.0 | 0.5631 | 25.4793 | 98.119 | 12.284 | 48.25 | 70.0 |
61
- | 35000 | 0.5657 | 61.0 | 192.0 | 0.5233 | 25.4774 | 98.126 | 12.285 | 42.5 | 91.5 |
62
- | 37500 | 0.6061 | 61.5 | 174.0 | 0.5094 | 25.4635 | 98.18 | 12.292 | 45.5 | 87.0 |
63
- | 40000 | 0.6465 | 60.0 | 188.0 | 0.4995 | 25.4422 | 98.262 | 12.302 | 41.75 | 105.5 |
64
- | 42500 | 0.6869 | 59.0 | 173.0 | 0.4839 | 25.5034 | 98.026 | 12.273 | 42.0 | 189.0 |
65
- | 45000 | 0.7273 | 54.5 | 153.0 | 0.4090 | 25.504 | 98.024 | 12.273 | 35.5 | 58.25 |
66
- | 47500 | 0.7677 | 53.75 | 137.0 | 0.3895 | 25.5041 | 98.023 | 12.273 | 35.0 | 42.5 |
67
- | 50000 | 0.8081 | 53.25 | 139.0 | 0.3769 | 25.4755 | 98.133 | 12.286 | 33.75 | 41.25 |
68
- | 52500 | 0.8485 | 51.25 | 131.0 | 0.3691 | 25.4887 | 98.083 | 12.28 | 33.75 | 46.25 |
69
- | 55000 | 0.8889 | 50.75 | 126.5 | 0.3558 | 25.4369 | 98.282 | 12.305 | 32.75 | 38.25 |
70
- | 57500 | 0.9293 | 50.0 | 126.5 | 0.3515 | 25.4349 | 98.29 | 12.306 | 32.25 | 35.5 |
71
- | 60000 | 0.9697 | 50.0 | 126.0 | 0.3490 | 25.4964 | 98.053 | 12.276 | 32.0 | 35.25 |
72
- | 61875 | 1.0 | 49.75 | 126.0 | 0.3487 | 25.4844 | 98.099 | 12.282 | 32.0 | 35.5 |
73
 
74
  # Resource Usage Comparison
75
 
76
- - VRAM Use: 7.7851 GB
77
 
78
- # Distillation (Teacher -> Student) Architecture Difference:
79
 
80
  - **Architecture**: `GPT2LMHeadModel` -> `GPT2LMHeadModel`
81
  - **Total Parameters**: 124,439,808 -> 124,439,808
82
- - **Data Type (dtype)**: torch.bfloat16 -> torch.bfloat16
83
  - **Model Size**: 0.24 GB -> 0.24 GB
84
 
85
  <details>
@@ -103,7 +103,7 @@ Trained on 145,744,973 tokens from the [wikimedia/wikipedia](https://huggingface
103
  # Training Objective
104
 
105
  ```
106
- DistillationObjective(logits_loss_component=LossComponent(label=logits, weight=1, loss_fn=kl), attn_loss_component=LossComponent(label=attn, weight=5, loss_fn=kl, layer_mapper=layer-2))
107
  ```
108
 
109
  # Hyperparameters
@@ -120,9 +120,9 @@ The following hyperparameters were used during training:
120
  - lr_scheduler_type: `linear`
121
  - lr_scheduler_warmup_ratio: `0.5`
122
  - num_epochs: `1.0`
123
- - distillation_objective: `DistillationObjective(logits_loss_component=LossComponent(label=logits, weight=1, loss_fn=kl), attn_loss_component=LossComponent(label=attn, weight=5, loss_fn=kl, layer_mapper=layer-2))`
124
  - train_embeddings: `True`
125
- - lr_scheduler: `<torch.optim.lr_scheduler.LambdaLR object at 0x7f040858e4a0>`
126
  - student_model_name_or_path: `None`
127
  - student_config_name_or_path: `None`
128
  - student_model_config: `None`
@@ -154,6 +154,6 @@ The following hyperparameters were used during training:
154
 
155
  # Framework Versions
156
  - Distily 0.2.0
157
- - Transformers 4.44.1
158
- - Pytorch 2.5.0.dev20240821+cu121
159
  - Datasets 2.21.0
 
44
  | step | epoch | enwikippl | frwikippl | loss | runtime | samples_per_second | steps_per_second | tinystoriesppl | zhwikippl |
45
  | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
46
  | **teacher eval** | | 43.25 | 61.25 | | | | | 11.6875 | 19.125 |
47
+ | 0 | 0 | 2473901162496.0 | 170424302305280.0 | 25.7744 | 30.269 | 82.593 | 10.341 | 4060086272.0 | 71468255805440.0 |
48
+ | 2500 | 0.0404 | 952.0 | 8032.0 | 6.1202 | 30.2377 | 82.678 | 10.351 | 652.0 | 6432.0 |
49
+ | 5000 | 0.0808 | 378.0 | 1880.0 | 5.0293 | 30.3345 | 82.414 | 10.318 | 270.0 | 288.0 |
50
+ | 7500 | 0.1212 | 230.0 | 820.0 | 4.5127 | 30.2749 | 82.577 | 10.339 | 201.0 | 174.0 |
51
+ | 10000 | 0.1616 | 173.0 | 628.0 | 4.2288 | 30.3713 | 82.315 | 10.306 | 152.0 | 172.0 |
52
+ | 12500 | 0.2020 | 127.5 | 482.0 | 3.8554 | 30.4218 | 82.178 | 10.289 | 106.5 | 157.0 |
53
+ | 15000 | 0.2424 | 109.0 | 436.0 | 3.6684 | 30.2501 | 82.644 | 10.347 | 87.5 | 148.0 |
54
+ | 17500 | 0.2828 | 93.5 | 350.0 | 3.5226 | 30.2559 | 82.628 | 10.345 | 73.5 | 119.5 |
55
+ | 20000 | 0.3232 | 75.5 | 282.0 | 3.3351 | 30.5792 | 81.755 | 10.236 | 64.5 | 114.5 |
56
+ | 22500 | 0.3636 | 67.5 | 213.0 | 3.1522 | 30.4457 | 82.113 | 10.281 | 53.25 | 80.5 |
57
+ | 25000 | 0.4040 | 64.0 | 197.0 | 3.0806 | 30.4623 | 82.069 | 10.275 | 45.0 | 95.5 |
58
+ | 27500 | 0.4444 | 58.25 | 203.0 | 3.0308 | 30.2865 | 82.545 | 10.335 | 40.75 | 93.0 |
59
+ | 30000 | 0.4848 | 59.5 | 195.0 | 3.0207 | 30.2442 | 82.66 | 10.349 | 43.25 | 61.5 |
60
+ | 32500 | 0.5253 | 58.5 | 172.0 | 3.0015 | 30.3473 | 82.38 | 10.314 | 41.75 | 60.75 |
61
+ | 35000 | 0.5657 | 57.25 | 171.0 | 2.9425 | 30.2295 | 82.701 | 10.354 | 38.0 | 51.5 |
62
+ | 37500 | 0.6061 | 57.25 | 157.0 | 2.9166 | 31.0953 | 80.398 | 10.066 | 38.0 | 55.0 |
63
+ | 40000 | 0.6465 | 54.75 | 160.0 | 2.8987 | 30.9607 | 80.747 | 10.11 | 35.5 | 58.75 |
64
+ | 42500 | 0.6869 | 53.75 | 153.0 | 2.8783 | 30.2174 | 82.734 | 10.358 | 35.75 | 67.0 |
65
+ | 45000 | 0.7273 | 50.25 | 136.0 | 2.7764 | 30.1636 | 82.881 | 10.377 | 30.375 | 41.25 |
66
+ | 47500 | 0.7677 | 50.25 | 126.5 | 2.7509 | 30.252 | 82.639 | 10.346 | 29.375 | 38.0 |
67
+ | 50000 | 0.8081 | 49.0 | 127.5 | 2.7362 | 30.1988 | 82.785 | 10.365 | 28.75 | 40.0 |
68
+ | 52500 | 0.8485 | 48.5 | 121.0 | 2.7263 | 30.2772 | 82.57 | 10.338 | 29.0 | 35.5 |
69
+ | 55000 | 0.8889 | 48.0 | 119.0 | 2.7102 | 30.1534 | 82.909 | 10.38 | 28.0 | 34.0 |
70
+ | 57500 | 0.9293 | 47.5 | 118.5 | 2.7043 | 30.181 | 82.834 | 10.371 | 27.875 | 32.5 |
71
+ | 60000 | 0.9697 | 47.5 | 118.0 | 2.7013 | 30.3322 | 82.421 | 10.319 | 27.75 | 32.25 |
72
+ | 61875 | 1.0 | 47.5 | 118.0 | 2.7006 | 30.5306 | 81.885 | 10.252 | 27.625 | 32.25 |
73
 
74
  # Resource Usage Comparison
75
 
76
+ - VRAM Use: 7.7830 GB
77
 
78
+ `# Distillation (Teacher -> Student) Architecture Difference:
79
 
80
  - **Architecture**: `GPT2LMHeadModel` -> `GPT2LMHeadModel`
81
  - **Total Parameters**: 124,439,808 -> 124,439,808
82
+ - **Data Type (dtype)**: 124439808 -> torch.bfloat16
83
  - **Model Size**: 0.24 GB -> 0.24 GB
84
 
85
  <details>
 
103
  # Training Objective
104
 
105
  ```
106
+ DistillationObjective(logits_loss_component=LossComponent(label=logits, weight=1, loss_fn=kl), attn_loss_component=LossComponent(label=attn, weight=5, loss_fn=cos, layer_mapper=layer-2))
107
  ```
108
 
109
  # Hyperparameters
 
120
  - lr_scheduler_type: `linear`
121
  - lr_scheduler_warmup_ratio: `0.5`
122
  - num_epochs: `1.0`
123
+ - distillation_objective: `DistillationObjective(logits_loss_component=LossComponent(label=logits, weight=1, loss_fn=kl), attn_loss_component=LossComponent(label=attn, weight=5, loss_fn=cos, layer_mapper=layer-2))`
124
  - train_embeddings: `True`
125
+ - lr_scheduler: `<torch.optim.lr_scheduler.LambdaLR object at 0x7fb7a85a5a50>`
126
  - student_model_name_or_path: `None`
127
  - student_config_name_or_path: `None`
128
  - student_model_config: `None`
 
154
 
155
  # Framework Versions
156
  - Distily 0.2.0
157
+ - Transformers 4.44.0
158
+ - Pytorch 2.3.0
159
  - Datasets 2.21.0
config.json CHANGED
@@ -33,7 +33,7 @@
33
  }
34
  },
35
  "torch_dtype": "bfloat16",
36
- "transformers_version": "4.44.1",
37
  "use_cache": true,
38
  "vocab_size": 50257
39
  }
 
33
  }
34
  },
35
  "torch_dtype": "bfloat16",
36
+ "transformers_version": "4.44.0",
37
  "use_cache": true,
38
  "vocab_size": 50257
39
  }
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 50256,
4
  "eos_token_id": 50256,
5
- "transformers_version": "4.44.1"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 50256,
4
  "eos_token_id": 50256,
5
+ "transformers_version": "4.44.0"
6
  }
logs/attn_loss_fn=cos, attn_weight=25.0, layer_mapper=layer-2, projector=orthogonal/events.out.tfevents.1724423185.f383272e719b ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4712ab6a97271f7d308fc31c7011ce2d38fe253df0aa9e5c67ec81623f1b7c3
3
+ size 29632529
logs/attn_loss_fn=cos, attn_weight=5, layer_mapper=layer-2, projector=orthogonal/completed.flag ADDED
File without changes
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff6338fdb174c372a77a1353481ed44d2a503fab9f3f00bce47ea2268e6f3f0c
3
  size 248894656
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:033fe84f0bd0bba5bf9dd45ff2eee03ac4adfe41a5f982b5f3af0fac6c6a4733
3
  size 248894656
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71ef455847b63b48a12aa4a0dc55bf581102a59c12916d5dd2fc022bc2a79821
3
  size 1017899144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7878ce5e7937b22714760a9a4020f4ab482e7dae2b151ebfb1f220757f4d9dad
3
  size 1017899144