Hugging Face's logo

martimfasantos
/
tinyllama-1.1b-sum-sft-qlora

PEFT
TensorBoard
Safetensors
llama
alignment-handbook
trl
sft
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Metrics Community
martimfasantos commited on
Commit
47eb899
•
1 Parent(s): 8efc863

Model save

Browse files
Files changed (6) hide show
  1. README.md +9 -12
  2. adapter_model.safetensors +1 -1
  3. all_results.json +5 -10
  4. runs/May04_20-41-10_poseidon/events.out.tfevents.1714855393.poseidon.1450584.0 +2 -2
  5. train_results.json +5 -5
  6. trainer_state.json +0 -0
README.md CHANGED
@@ -2,13 +2,12 @@
2
  license: apache-2.0
3
  library_name: peft
4
  tags:
5
- - alignment-handbook
6
  - trl
7
  - sft
8
  - generated_from_trainer
9
  base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
10
  datasets:
11
- - martimfasantos/openai-tldr-filtered
12
  model-index:
13
  - name: tinyllama-1.1b-sum-sft-qlora
14
  results: []
@@ -19,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  # tinyllama-1.1b-sum-sft-qlora
21
 
22
- This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the martimfasantos/openai-tldr-filtered dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 2.1479
25
 
26
  ## Model description
27
 
@@ -40,26 +39,24 @@ More information needed
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
- - learning_rate: 0.0002
44
- - train_batch_size: 4
45
  - eval_batch_size: 8
46
  - seed: 42
47
  - distributed_type: multi-GPU
48
  - gradient_accumulation_steps: 2
49
- - total_train_batch_size: 8
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: cosine
52
  - lr_scheduler_warmup_ratio: 0.1
53
- - num_epochs: 4
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss |
58
  |:-------------:|:-----:|:-----:|:---------------:|
59
- | 2.1066 | 1.0 | 10792 | 2.1614 |
60
- | 2.144 | 2.0 | 21584 | 2.1491 |
61
- | 2.1212 | 3.0 | 32376 | 2.1476 |
62
- | 2.0543 | 4.0 | 43168 | 2.1479 |
63
 
64
 
65
  ### Framework versions
 
2
  license: apache-2.0
3
  library_name: peft
4
  tags:
 
5
  - trl
6
  - sft
7
  - generated_from_trainer
8
  base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
9
  datasets:
10
+ - generator
11
  model-index:
12
  - name: tinyllama-1.1b-sum-sft-qlora
13
  results: []
 
18
 
19
  # tinyllama-1.1b-sum-sft-qlora
20
 
21
+ This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 2.1486
24
 
25
  ## Model description
26
 
 
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
+ - learning_rate: 0.0004
43
+ - train_batch_size: 8
44
  - eval_batch_size: 8
45
  - seed: 42
46
  - distributed_type: multi-GPU
47
  - gradient_accumulation_steps: 2
48
+ - total_train_batch_size: 16
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: cosine
51
  - lr_scheduler_warmup_ratio: 0.1
52
+ - num_epochs: 2
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss |
57
  |:-------------:|:-----:|:-----:|:---------------:|
58
+ | 2.1002 | 1.0 | 5390 | 2.1550 |
59
+ | 2.0952 | 2.0 | 10780 | 2.1486 |
 
 
60
 
61
 
62
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fcda8d01ff2dd2eec7076f9a92b958a716fbfd32a35f7f3581c66aa6e59f74a0
3
  size 25272360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc0b854beee49936419583a58403ef903549c887b5dc3c12f11aa1adf0da6de9
3
  size 25272360
all_results.json CHANGED
@@ -1,13 +1,8 @@
1
  {
2
- "epoch": 4.0,
3
- "eval_loss": 2.14786434173584,
4
- "eval_runtime": 188.8433,
5
- "eval_samples": 6553,
6
- "eval_samples_per_second": 25.709,
7
- "eval_steps_per_second": 3.214,
8
- "train_loss": 2.0942285917837413,
9
- "train_runtime": 51337.8051,
10
  "train_samples": 116722,
11
- "train_samples_per_second": 6.727,
12
- "train_steps_per_second": 0.841
13
  }
 
1
  {
2
+ "epoch": 2.0,
3
+ "train_loss": 2.151964877841645,
4
+ "train_runtime": 21635.5911,
 
 
 
 
 
5
  "train_samples": 116722,
6
+ "train_samples_per_second": 7.971,
7
+ "train_steps_per_second": 0.498
8
  }
runs/May04_20-41-10_poseidon/events.out.tfevents.1714855393.poseidon.1450584.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03505766b1ba2da1854f43a4d06e06d02eae082081934b8c8b9a5f43de41dbfe
3
- size 448761
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e7f83bd2f3624cc155752fec0f2715202a940fde7e07986eed58a5689b2082e
3
+ size 461202
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 4.0,
3
- "train_loss": 2.0942285917837413,
4
- "train_runtime": 51337.8051,
5
  "train_samples": 116722,
6
- "train_samples_per_second": 6.727,
7
- "train_steps_per_second": 0.841
8
  }
 
1
  {
2
+ "epoch": 2.0,
3
+ "train_loss": 2.151964877841645,
4
+ "train_runtime": 21635.5911,
5
  "train_samples": 116722,
6
+ "train_samples_per_second": 7.971,
7
+ "train_steps_per_second": 0.498
8
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff