training / README.md

aisuko

aisuko/encoder-L6-V2

573158c verified 3 months ago

preview code

raw

history blame contribute delete

30.3 kB

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:4984
  - loss:MultipleNegativesRankingLoss
base_model: sentence-transformers/all-MiniLM-L6-v2
widget:
  - source_sentence: |-
      <think>
      Let’s think through this step by step
      rp = 500/month
      fp = 10/day
      lp = 60/lesson
      lpw = 2 lessons/week
      yp = 12 months/year
      total = (500 × 12) + (10 × 365) + (60 × 2 × 52)
      total = 6000 + 3650 + 6240
      total = 15890
      </think>
      \boxed{15890}
    sentences:
      - |-
        <think>
        Let’s think through this step by step
        rp = 500/month
        fp = 10/day
        lp = 60/lesson
        tp = (500 × 12) + (10 × 365) + (60 × 2 × 52)
        tp = 6000 + 3650 + 6240
        tp = 15890
        </think>
        \boxed{15890}
      - |-
        <think>
        Let’s think through this step by step
        h1 = 500 ft
        h2 = 2 * h1 = 2 * 500 = 1000 ft
        Total height = h1 + h2 = 500 + 1000 = 1500 ft
        </think>
        \boxed{1500}
      - |-
        <think>
        Let’s think through this step by step
        fc = 200
        lc = 500
        dc = 500 × 0.8 = 400
        nc = 200 - 50 = 150
        tc = 150 + 400 = 550
        </think>
        \boxed{550}
  - source_sentence: |-
      <think>
      Let’s think through this step by step
      s = 5 MB/song
      m1 = 10 songs
      m2 = 15 songs
      m3 = 3 songs
      total = (10 + 15 + 3) × 5
      total = 28 × 5 = 140 MB
      </think>
      \boxed{140}
    sentences:
      - |-
        <think>
        Let’s think through this step by step
        s = 5 MB/song
        m1 = 10 songs
        m2 = 15 songs
        m3 = 3 songs
        Total memory = (10 + 15 + 3) × 5
        Total memory = 28 × 5 = 140 MB
        </think>
        \boxed{140}
      - |-
        <think>
        Let’s think through this step by step
        total_slices = 12
        eaten_slices = 12 × (1/4) = 3
        kept_slices = 12 - 3 = 9
        </think>
        \boxed{9}
      - |-
        <think>
        Let’s think through this step by step
        Bald Mountain = 1.5 meters = 150 cm
        Billy Mountain = 3.5 meters = 350 cm
        Mount Pilot = 126 cm
        Difference between Billy Mountain and Bald Mountain = 350 - 150 = 200 cm
        Difference between Mount Pilot and Bald Mountain = 126 - 150 = -24 cm
        </think>
        \boxed{200}
  - source_sentence: |-
      <think>
      Let’s think through this step by step
      Strength training: 1 hour/session × 3 sessions/week = 3 hours/week
      Boxing training: 1.5 hours/session × 4 sessions/week = 6 hours/week
      Total training hours per week = 3 + 6 = 9 hours/week
      </think>
      \boxed{9}
    sentences:
      - |-
        <think>
        Let’s think through this step by step
        t = 5
        p = 4
        s = 6
        r = 5 / 2 = 2.5
        income = (2 × 5) + 4 + (4 × 6) + (6 × 2.5)
        income = 10 + 4 + 24 + 15
        income = 53
        </think>
        \boxed{53}
      - |-
        <think>
        Let’s think through this step by step
        Strength training: 1 hour/session × 3 sessions/week = 3 hours/week
        Boxing training: 1.5 hours/session × 4 sessions/week = 6 hours/week
        Total training hours per week = 3 + 6 = 9 hours/week
        </think>
        \boxed{9}
      - |-
        <think>
        Let’s think through this step by step
        Let d be the number of ducks sold
        Earnings from selling chickens = 5 × 8 = 40
        Earnings from selling ducks = 10d
        Total earnings = 40 + 10d
        Amount spent on wheelbarrow = (1/2)(40 + 10d)
        Amount earned from selling wheelbarrow = 60
        40 + 10d = 2(60)
        10d = 80
        d = 8
        </think>
        \boxed{8}
  - source_sentence: |-
      <think>
      Let’s think through this step by step
      up = 3 flights
      down = 3 flights
      total = (3 + 3) × 5 = 30 flights
      </think>
      \boxed{30}
    sentences:
      - |-
        <think>
        Let’s think through this step by step
        up = 3 flights
        down = 3 flights
        total = (3 + 3) × 5 = 30 flights
        </think>
        \boxed{30}
      - |-
        <think>
        Let’s think through this step by step
        J = M + 10
        J + 10 = 25
        (M + 10) + 10 = 25
        M + 20 = 25
        M = 5
        J = 5 + 10 = 15
        Sum = 5 + 15 = 20
        </think>
        \boxed{20}
      - |-
        <think>
        Let’s think through this step by step
        total_money = 7(1) + 4(5) + 2(10) + 1(20) = 7 + 20 + 20 + 20 = 67
        cost = 67 - 4 = 63
        pounds = 63 / 3 = 21
        days = 7
        average = 21 / 7 = 3
        </think>
        \boxed{3}
  - source_sentence: |-
      <think>
      Let’s think through this step by step
      n = 4
      sp = 75
      t = 36
      spt = 36 / 4 = 9
      op = 75 + 9 = 84
      </think>
      \boxed{84}
    sentences:
      - |-
        <think>
        Let’s think through this step by step
        Let B be Benedict's house size
        K = 10000 sq ft
        K = 4B + 600
        10000 = 4B + 600
        4B = 9400
        B = 2350 sq ft
        </think>
        \boxed{2350}
      - |-
        <think>
        Let’s think through this step by step
        Total throws = 80
        No pass thrown = 30% of 80 = 0.3 × 80 = 24
        Sacked for a loss = 0.5 × 24 = 12
        </think>
        \boxed{12}
      - |-
        <think>
        Let’s think through this step by step
        n = 4
        sp = 75
        t = 36
        spt = t / n = 36 / 4 = 9
        op = sp + spt = 75 + 9 = 84
        </think>
        \boxed{84}
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - pearson_cosine
  - spearman_cosine
model-index:
  - name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev
          type: sts-dev
        metrics:
          - type: pearson_cosine
            value: 0.8793284892973376
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.876484495899188
            name: Spearman Cosine
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test
          type: sts-test
        metrics:
          - type: pearson_cosine
            value: 0.879334132854901
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8764936381058213
            name: Spearman Cosine

SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2 on the csv dataset. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: sentence-transformers/all-MiniLM-L6-v2
Maximum Sequence Length: 256 tokens
Output Dimensionality: 384 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- csv

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): Normalize()
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("training")
# Run inference
sentences = [
    '<think>\nLet’s think through this step by step\nn = 4\nsp = 75\nt = 36\nspt = 36 / 4 = 9\nop = 75 + 9 = 84\n</think>\n\\boxed{84}',
    '<think>\nLet’s think through this step by step\nn = 4\nsp = 75\nt = 36\nspt = t / n = 36 / 4 = 9\nop = sp + spt = 75 + 9 = 84\n</think>\n\\boxed{84}',
    "<think>\nLet’s think through this step by step\nLet B be Benedict's house size\nK = 10000 sq ft\nK = 4B + 600\n10000 = 4B + 600\n4B = 9400\nB = 2350 sq ft\n</think>\n\\boxed{2350}",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Semantic Similarity

Datasets: sts-dev and sts-test
Evaluated with EmbeddingSimilarityEvaluator

Metric	sts-dev	sts-test
pearson_cosine	0.8793	0.8793
spearman_cosine	0.8765	0.8765

Training Details

Training Dataset

csv

Dataset: csv
Size: 4,984 training samples
Columns: anchor and positive
Approximate statistics based on the first 1000 samples:
anchor positive
type string string
details
min: 34 tokens
mean: 66.41 tokens
max: 256 tokens

min: 36 tokens
mean: 67.03 tokens
max: 256 tokens

	anchor	positive
type	string	string
details	min: 34 tokens mean: 66.41 tokens max: 256 tokens	min: 36 tokens mean: 67.03 tokens max: 256 tokens

Samples:

anchor	positive
`Let’s think through this step by step ht_hare = 14 inches ht_camel = 24 × 14 = 336 inches ht_camel_ft = 336 / 12 = 28 feet \boxed{28}`	`Let’s think through this step by step ht_hare = 14 inches ht_camel = 24 * 14 = 336 inches ht_camel_ft = 336 / 12 = 28 feet \boxed{28}`
`Let’s think through this step by step cpb = 5 sp = 90 pmpb = 2 tp = 5 × 5 = 25 tpmp = 5 × 2 = 10 profit = 90 - 25 - 10 = 55 \boxed{55}`	`Let’s think through this step by step cp = 5 × 5 = 25 sp = 90 p = sp - cp - (5 × 2) = 90 - 25 - 10 = 55 \boxed{55}`
`Let’s think through this step by step Time to iron a blouse = 15 minutes Time to iron a dress = 20 minutes Time spent on blouses = 2 hours = 120 minutes Time spent on dresses = 3 hours = 180 minutes Number of blouses ironed = 120 / 15 = 8 Number of dresses ironed = 180 / 20 = 9 Total pieces of clothes ironed = 8 + 9 = 17 \boxed{17}`	`Let’s think through this step by step Time to iron 1 blouse = 15 minutes Time to iron 1 dress = 20 minutes Time spent on blouses = 2 hours = 120 minutes Time spent on dresses = 3 hours = 180 minutes Number of blouses ironed = 120 / 15 = 8 Number of dresses ironed = 180 / 20 = 9 Total pieces of clothes ironed = 8 + 9 = 17 \boxed{17}`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim"
}

Evaluation Dataset

csv

Dataset: csv
Size: 4,984 evaluation samples
Columns: anchor and positive
Approximate statistics based on the first 1000 samples:
anchor positive
type string string
details
min: 33 tokens
mean: 66.68 tokens
max: 164 tokens

min: 33 tokens
mean: 66.71 tokens
max: 161 tokens

	anchor	positive
type	string	string
details	min: 33 tokens mean: 66.68 tokens max: 164 tokens	min: 33 tokens mean: 66.71 tokens max: 161 tokens

Samples:

anchor	positive
`Let’s think through this step by step sg = 36 sc = 1/4 fl = 1/3 sg_left = sg - (sg × sc) - (sg × (1 - sc) × fl) sg_left = 36 - (36 × 1/4) - (36 × (1 - 1/4) × 1/3) sg_left = 36 - 9 - 6 sg_left = 21 \boxed{21}`	`Let’s think through this step by step sg = 36 sc = 1/4 fl = 1/3 sg_left = sg - (sg × sc) - (sg × (1 - sc) × fl) sg_left = 36 - (36 × 1/4) - (36 × (1 - 1/4) × 1/3) sg_left = 36 - 9 - 6 sg_left = 21 \boxed{21}`
`Let’s think through this step by step d1 = 125 miles d2 = 223 miles d3 = 493 - (125 + 223) d3 = 145 miles \boxed{145}`	`Let’s think through this step by step d1 = 125 miles d2 = 223 miles d3 = 493 - (125 + 223) d3 = 145 miles \boxed{145}`
`Let’s think through this step by step Total workdays = 2 weeks × 5 days/week = 10 days Paid vacation days = 6 days Unpaid vacation days = 10 - 6 = 4 days Total pay = 15 × 8 = $120/day Missed pay = 4 × 120 = $480 \boxed{480}`	`Let’s think through this step by step Total workdays = 2 weeks × 5 days/week = 10 days Paid vacation days = 6 days Unpaid vacation days = 10 - 6 = 4 days Total pay = 15 × 8 = $120/day Missed pay = 4 × 120 = $480 \boxed{480}`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim"
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
learning_rate: 2e-05
num_train_epochs: 20
warmup_ratio: 0.1
fp16: True
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 2e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 20
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.1
warmup_steps: 0
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
save_safetensors: True
save_on_each_node: False
save_only_model: False
restore_callback_states_from_checkpoint: False
no_cuda: False
use_cpu: False
use_mps_device: False
seed: 42
data_seed: None
jit_mode_eval: False
use_ipex: False
bf16: False
fp16: True
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: None
local_rank: 0
ddp_backend: None
tpu_num_cores: None
tpu_metrics_debug: False
debug: []
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_prefetch_factor: None
past_index: -1
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: False
ignore_data_skip: False
fsdp: []
fsdp_min_num_params: 0
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
tp_size: 0
fsdp_transformer_layer_cls_to_wrap: None
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch
optim_args: None
adafactor: False
group_by_length: False
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
dataloader_pin_memory: True
dataloader_persistent_workers: False
skip_memory_metrics: True
use_legacy_prediction_loop: False
push_to_hub: False
resume_from_checkpoint: None
hub_model_id: None
hub_strategy: every_save
hub_private_repo: None
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
include_for_metrics: []
eval_do_concat_batches: True
fp16_backend: auto
push_to_hub_model_id: None
push_to_hub_organization: None
mp_parameters:
auto_find_batch_size: False
full_determinism: False
torchdynamo: None
ray_scope: last
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
include_tokens_per_second: False
include_num_input_tokens_seen: False
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss	sts-dev_spearman_cosine	sts-test_spearman_cosine
-1	-1	-	-	0.8671	-
0.3953	100	0.0422	0.0031	0.8701	-
0.7905	200	0.0105	0.0017	0.8727	-
1.1858	300	0.0041	0.0016	0.8728	-
1.5810	400	0.0016	0.0011	0.8730	-
1.9763	500	0.0039	0.0021	0.8731	-
2.3715	600	0.0014	0.0020	0.8741	-
2.7668	700	0.0014	0.0017	0.8744	-
3.1621	800	0.0019	0.0009	0.8742	-
3.5573	900	0.0012	0.0011	0.8754	-
3.9526	1000	0.0016	0.0015	0.8760	-
4.3478	1100	0.0021	0.0011	0.8763	-
4.7431	1200	0.0006	0.0009	0.8753	-
5.1383	1300	0.0004	0.0009	0.8753	-
5.5336	1400	0.0008	0.0008	0.8751	-
5.9289	1500	0.0004	0.0004	0.8743	-
6.3241	1600	0.0009	0.0008	0.8758	-
6.7194	1700	0.0005	0.0009	0.8747	-
7.1146	1800	0.0004	0.0006	0.8742	-
7.5099	1900	0.0003	0.0010	0.8748	-
7.9051	2000	0.0006	0.0008	0.8742	-
8.3004	2100	0.0005	0.0007	0.8744	-
8.6957	2200	0.0003	0.0006	0.8748	-
9.0909	2300	0.0005	0.0012	0.8749	-
9.4862	2400	0.0007	0.0006	0.8762	-
9.8814	2500	0.0003	0.0009	0.8762	-
10.2767	2600	0.0004	0.0007	0.8759	-
10.6719	2700	0.0005	0.0005	0.8760	-
11.0672	2800	0.0005	0.0007	0.8754	-
11.4625	2900	0.0002	0.0008	0.8749	-
11.8577	3000	0.0002	0.0007	0.8749	-
12.2530	3100	0.0003	0.0007	0.8752	-
12.6482	3200	0.0004	0.0008	0.8760	-
13.0435	3300	0.0002	0.0008	0.8767	-
13.4387	3400	0.0002	0.0007	0.8763	-
13.8340	3500	0.0002	0.0007	0.8763	-
14.2292	3600	0.0001	0.0007	0.8764	-
14.6245	3700	0.0003	0.0006	0.8765	-
15.0198	3800	0.0002	0.0005	0.8757	-
15.4150	3900	0.0002	0.0004	0.8760	-
15.8103	4000	0.0002	0.0005	0.8765	-
16.2055	4100	0.0002	0.0005	0.8757	-
16.6008	4200	0.0002	0.0006	0.8758	-
16.9960	4300	0.0002	0.0006	0.8758	-
17.3913	4400	0.0001	0.0005	0.8761	-
17.7866	4500	0.0002	0.0005	0.8765	-
18.1818	4600	0.0001	0.0005	0.8767	-
18.5771	4700	0.0004	0.0004	0.8765	-
18.9723	4800	0.0002	0.0004	0.8765	-
19.3676	4900	0.0001	0.0004	0.8765	-
19.7628	5000	0.0001	0.0004	0.8765	-
-1	-1	-	-	-	0.8765

Framework Versions

Python: 3.11.11
Sentence Transformers: 3.4.1
Transformers: 4.51.1
PyTorch: 2.5.1+cu124
Accelerate: 1.3.0
Datasets: 3.5.0
Tokenizers: 0.21.0

Citation

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}