metadata

base_model: BAAI/bge-large-en-v1.5
library_name: setfit
metrics:
  - accuracy
pipeline_tag: text-classification
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
widget:
  - text: you're very lucky.
  - text: Show me operating cash flow trends.
  - text: Join data_asset_kpi_is and data_asset_kpi_cf tables.
  - text: Can I have max EBIT_Margin?
  - text: I'm not inclined to generate further data sets.
inference: true
model-index:
  - name: SetFit with BAAI/bge-large-en-v1.5
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: Unknown
          type: unknown
          split: test
        metrics:
          - type: accuracy
            value: 0.9829059829059829
            name: Accuracy

SetFit with BAAI/bge-large-en-v1.5

This is a SetFit model that can be used for Text Classification. This SetFit model uses BAAI/bge-large-en-v1.5 as the Sentence Transformer embedding model. A LogisticRegression instance is used for classification.

The model has been trained using an efficient few-shot learning technique that involves:

Fine-tuning a Sentence Transformer with contrastive learning.
Training a classification head with features from the fine-tuned Sentence Transformer.

Model Details

Model Description

Model Type: SetFit
Sentence Transformer body: BAAI/bge-large-en-v1.5
Classification head: a LogisticRegression instance
Maximum Sequence Length: 512 tokens
Number of Classes: 7 classes

Model Sources

Repository: SetFit on GitHub
Paper: Efficient Few-Shot Learning Without Prompts
Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts

Model Labels

Label	Examples
Lookup_1	'Analyze product category revenue impact.' 'Analyze Product-wise Financial Performance Metrics.' 'Get M&A deal size by company.'
Aggregation	'Group the products by color and find the average price for each color.' 'Get me count Product.' 'Show me forecast accuracy and group by version.'
Lookup	'What are the products with a price below 20?' 'Can you get me the products that are out of stock?' 'Get me the list of employees who joined the company after January 2023.'
Viewtables	'What are the different types of tables that can be found within the starhub_data_asset database?' 'What is the complete list of tables in the starhub_data_asset database that can be accessed without needing to perform any table joining operations?' 'What is the list of tables that a new user should familiarize themselves with when accessing the starhub_data_asset database?'
Tablejoin	'Can you join the Products and Orders tables to track revenue by product category?' 'Could you combine table data from Orders and Products to identify which products were ordered most frequently?' 'Show me a join of key performance metrics and cash flow tables.'
Generalreply	"Oh, I'm a big fan of indie rock. What about you? What's your favorite type of music?" 'It was pretty good! How about yours?' "Oh, that's a tough question! I have a few favorites, but if I had to pick just one, it would be The Shawshank Redemption. What about you, what's your favorite movie?"
Rejection	"I don't need to filter this data set." "Let's not generate more data entries." "Please don't filter the list."

Evaluation

Metrics

Label	Accuracy
all	0.9829

Uses

Direct Use for Inference

First install the SetFit library:

pip install setfit

Then you can load this model and run inference.

from setfit import SetFitModel

# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("nazhan/bge-large-en-v1.5-brahmaputra-iter-9-2nd-1-epoch")
# Run inference
preds = model("you're very lucky.")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	2	8.8397	53

Label	Training Sample Count
Tablejoin	129
Rejection	69
Aggregation	282
Lookup	64
Generalreply	69
Viewtables	76
Lookup_1	147

Training Hyperparameters

batch_size: (16, 16)
num_epochs: (1, 1)
max_steps: -1
sampling_strategy: oversampling
body_learning_rate: (2e-05, 1e-05)
head_learning_rate: 0.01
loss: CosineSimilarityLoss
distance_metric: cosine_distance
margin: 0.25
end_to_end: False
use_amp: False
warmup_proportion: 0.1
seed: 42
eval_max_steps: -1
load_best_model_at_end: True

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0000	1	0.23	-
0.0014	50	0.196	-
0.0028	100	0.1679	-
0.0043	150	0.156	-
0.0057	200	0.2	-
0.0071	250	0.0765	-
0.0085	300	0.167	-
0.0100	350	0.1154	-
0.0114	400	0.0625	-
0.0128	450	0.0666	-
0.0142	500	0.0515	-
0.0157	550	0.0178	-
0.0171	600	0.0068	-
0.0185	650	0.0174	-
0.0199	700	0.0136	-
0.0214	750	0.0066	-
0.0228	800	0.0052	-
0.0242	850	0.0045	-
0.0256	900	0.003	-
0.0271	950	0.0031	-
0.0285	1000	0.0035	-
0.0299	1050	0.0032	-
0.0313	1100	0.0031	-
0.0328	1150	0.0029	-
0.0342	1200	0.0023	-
0.0356	1250	0.0012	-
0.0370	1300	0.0025	-
0.0385	1350	0.0019	-
0.0399	1400	0.0023	-
0.0413	1450	0.0016	-
0.0427	1500	0.0018	-
0.0441	1550	0.0019	-
0.0456	1600	0.0012	-
0.0470	1650	0.0012	-
0.0484	1700	0.0013	-
0.0498	1750	0.0011	-
0.0513	1800	0.001	-
0.0527	1850	0.0013	-
0.0541	1900	0.0014	-
0.0555	1950	0.0008	-
0.0570	2000	0.0009	-
0.0584	2050	0.0009	-
0.0598	2100	0.0009	-
0.0612	2150	0.0012	-
0.0627	2200	0.0008	-
0.0641	2250	0.0011	-
0.0655	2300	0.0006	-
0.0669	2350	0.0011	-
0.0684	2400	0.0007	-
0.0698	2450	0.0009	-
0.0712	2500	0.0007	-
0.0726	2550	0.0005	-
0.0741	2600	0.0006	-
0.0755	2650	0.0007	-
0.0769	2700	0.0008	-
0.0783	2750	0.0007	-
0.0798	2800	0.0007	-
0.0812	2850	0.0007	-
0.0826	2900	0.0008	-
0.0840	2950	0.0006	-
0.0855	3000	0.0006	-
0.0869	3050	0.0006	-
0.0883	3100	0.0005	-
0.0897	3150	0.0007	-
0.0911	3200	0.0005	-
0.0926	3250	0.0007	-
0.0940	3300	0.0007	-
0.0954	3350	0.0006	-
0.0968	3400	0.0007	-
0.0983	3450	0.0005	-
0.0997	3500	0.0005	-
0.1011	3550	0.0005	-
0.1025	3600	0.0004	-
0.1040	3650	0.0003	-
0.1054	3700	0.0005	-
0.1068	3750	0.0004	-
0.1082	3800	0.0005	-
0.1097	3850	0.0004	-
0.1111	3900	0.0004	-
0.1125	3950	0.0003	-
0.1139	4000	0.0004	-
0.1154	4050	0.0003	-
0.1168	4100	0.1163	-
0.1182	4150	0.0054	-
0.1196	4200	0.0317	-
0.1211	4250	0.0009	-
0.1225	4300	0.0005	-
0.1239	4350	0.0008	-
0.1253	4400	0.0007	-
0.1268	4450	0.0004	-
0.1282	4500	0.0006	-
0.1296	4550	0.0004	-
0.1310	4600	0.0003	-
0.1324	4650	0.0004	-
0.1339	4700	0.0005	-
0.1353	4750	0.0003	-
0.1367	4800	0.0004	-
0.1381	4850	0.0004	-
0.1396	4900	0.0002	-
0.1410	4950	0.0005	-
0.1424	5000	0.0003	-
0.1438	5050	0.0004	-
0.1453	5100	0.0004	-
0.1467	5150	0.0003	-
0.1481	5200	0.0003	-
0.1495	5250	0.0003	-
0.1510	5300	0.0005	-
0.1524	5350	0.0004	-
0.1538	5400	0.0002	-
0.1552	5450	0.0003	-
0.1567	5500	0.0003	-
0.1581	5550	0.0002	-
0.1595	5600	0.0002	-
0.1609	5650	0.0003	-
0.1624	5700	0.0003	-
0.1638	5750	0.0003	-
0.1652	5800	0.0002	-
0.1666	5850	0.0003	-
0.1681	5900	0.0003	-
0.1695	5950	0.0003	-
0.1709	6000	0.0002	-
0.1723	6050	0.0002	-
0.1737	6100	0.0002	-
0.1752	6150	0.0002	-
0.1766	6200	0.0003	-
0.1780	6250	0.0002	-
0.1794	6300	0.0003	-
0.1809	6350	0.0002	-
0.1823	6400	0.0003	-
0.1837	6450	0.0003	-
0.1851	6500	0.0002	-
0.1866	6550	0.0002	-
0.1880	6600	0.0004	-
0.1894	6650	0.0002	-
0.1908	6700	0.0002	-
0.1923	6750	0.0002	-
0.1937	6800	0.0002	-
0.1951	6850	0.0002	-
0.1965	6900	0.0002	-
0.1980	6950	0.0002	-
0.1994	7000	0.0002	-
0.2008	7050	0.0002	-
0.2022	7100	0.0002	-
0.2037	7150	0.0003	-
0.2051	7200	0.0002	-
0.2065	7250	0.0002	-
0.2079	7300	0.0002	-
0.2094	7350	0.0002	-
0.2108	7400	0.0002	-
0.2122	7450	0.0002	-
0.2136	7500	0.0002	-
0.2151	7550	0.0002	-
0.2165	7600	0.0002	-
0.2179	7650	0.0002	-
0.2193	7700	0.0002	-
0.2207	7750	0.0002	-
0.2222	7800	0.0001	-
0.2236	7850	0.0002	-
0.2250	7900	0.0002	-
0.2264	7950	0.0002	-
0.2279	8000	0.0002	-
0.2293	8050	0.0002	-
0.2307	8100	0.0002	-
0.2321	8150	0.0002	-
0.2336	8200	0.0002	-
0.2350	8250	0.0004	-
0.2364	8300	0.0001	-
0.2378	8350	0.0002	-
0.2393	8400	0.0001	-
0.2407	8450	0.0002	-
0.2421	8500	0.0001	-
0.2435	8550	0.0002	-
0.2450	8600	0.0002	-
0.2464	8650	0.0002	-
0.2478	8700	0.0001	-
0.2492	8750	0.0001	-
0.2507	8800	0.0001	-
0.2521	8850	0.0002	-
0.2535	8900	0.0002	-
0.2549	8950	0.0002	-
0.2564	9000	0.0002	-
0.2578	9050	0.0001	-
0.2592	9100	0.0001	-
0.2606	9150	0.0003	-
0.2620	9200	0.0001	-
0.2635	9250	0.0001	-
0.2649	9300	0.0002	-
0.2663	9350	0.0001	-
0.2677	9400	0.0001	-
0.2692	9450	0.0001	-
0.2706	9500	0.0002	-
0.2720	9550	0.0002	-
0.2734	9600	0.0002	-
0.2749	9650	0.0001	-
0.2763	9700	0.0002	-
0.2777	9750	0.0001	-
0.2791	9800	0.0001	-
0.2806	9850	0.0001	-
0.2820	9900	0.0002	-
0.2834	9950	0.0002	-
0.2848	10000	0.0001	-
0.2863	10050	0.0001	-
0.2877	10100	0.0001	-
0.2891	10150	0.0002	-
0.2905	10200	0.0001	-
0.2920	10250	0.0002	-
0.2934	10300	0.0001	-
0.2948	10350	0.0002	-
0.2962	10400	0.0001	-
0.2977	10450	0.0001	-
0.2991	10500	0.0001	-
0.3005	10550	0.0001	-
0.3019	10600	0.0001	-
0.3033	10650	0.0001	-
0.3048	10700	0.0001	-
0.3062	10750	0.0001	-
0.3076	10800	0.0001	-
0.3090	10850	0.0001	-
0.3105	10900	0.0001	-
0.3119	10950	0.0001	-
0.3133	11000	0.0001	-
0.3147	11050	0.0001	-
0.3162	11100	0.0001	-
0.3176	11150	0.0001	-
0.3190	11200	0.0001	-
0.3204	11250	0.0001	-
0.3219	11300	0.0001	-
0.3233	11350	0.0001	-
0.3247	11400	0.0002	-
0.3261	11450	0.0001	-
0.3276	11500	0.0001	-
0.3290	11550	0.0001	-
0.3304	11600	0.0001	-
0.3318	11650	0.0001	-
0.3333	11700	0.0002	-
0.3347	11750	0.0001	-
0.3361	11800	0.0001	-
0.3375	11850	0.0001	-
0.3390	11900	0.0002	-
0.3404	11950	0.0001	-
0.3418	12000	0.0001	-
0.3432	12050	0.0002	-
0.3447	12100	0.0001	-
0.3461	12150	0.0001	-
0.3475	12200	0.0001	-
0.3489	12250	0.0003	-
0.3503	12300	0.0003	-
0.3518	12350	0.0003	-
0.3532	12400	0.0269	-
0.3546	12450	0.0475	-
0.3560	12500	0.0004	-
0.3575	12550	0.0003	-
0.3589	12600	0.0005	-
0.3603	12650	0.0003	-
0.3617	12700	0.0001	-
0.3632	12750	0.0002	-
0.3646	12800	0.0003	-
0.3660	12850	0.0002	-
0.3674	12900	0.0001	-
0.3689	12950	0.0004	-
0.3703	13000	0.0002	-
0.3717	13050	0.0002	-
0.3731	13100	0.0003	-
0.3746	13150	0.0002	-
0.3760	13200	0.0003	-
0.3774	13250	0.0003	-
0.3788	13300	0.0001	-
0.3803	13350	0.0002	-
0.3817	13400	0.0002	-
0.3831	13450	0.0002	-
0.3845	13500	0.0002	-
0.3860	13550	0.0002	-
0.3874	13600	0.0002	-
0.3888	13650	0.0001	-
0.3902	13700	0.0001	-
0.3916	13750	0.0002	-
0.3931	13800	0.0003	-
0.3945	13850	0.0002	-
0.3959	13900	0.0002	-
0.3973	13950	0.0001	-
0.3988	14000	0.0001	-
0.4002	14050	0.0001	-
0.4016	14100	0.0002	-
0.4030	14150	0.0002	-
0.4045	14200	0.0001	-
0.4059	14250	0.0001	-
0.4073	14300	0.0001	-
0.4087	14350	0.0001	-
0.4102	14400	0.0003	-
0.4116	14450	0.0002	-
0.4130	14500	0.0001	-
0.4144	14550	0.0002	-
0.4159	14600	0.0002	-
0.4173	14650	0.0001	-
0.4187	14700	0.0001	-
0.4201	14750	0.0001	-
0.4216	14800	0.0001	-
0.4230	14850	0.0001	-
0.4244	14900	0.0001	-
0.4258	14950	0.0002	-
0.4273	15000	0.0001	-
0.4287	15050	0.0001	-
0.4301	15100	0.0001	-
0.4315	15150	0.0001	-
0.4329	15200	0.0001	-
0.4344	15250	0.0001	-
0.4358	15300	0.0001	-
0.4372	15350	0.0001	-
0.4386	15400	0.0001	-
0.4401	15450	0.0001	-
0.4415	15500	0.0001	-
0.4429	15550	0.0001	-
0.4443	15600	0.0001	-
0.4458	15650	0.0001	-
0.4472	15700	0.0001	-
0.4486	15750	0.0001	-
0.4500	15800	0.0001	-
0.4515	15850	0.0017	-
0.4529	15900	0.0007	-
0.4543	15950	0.0009	-
0.4557	16000	0.0004	-
0.4572	16050	0.0006	-
0.4586	16100	0.0003	-
0.4600	16150	0.0003	-
0.4614	16200	0.0003	-
0.4629	16250	0.0003	-
0.4643	16300	0.0002	-
0.4657	16350	0.0002	-
0.4671	16400	0.0002	-
0.4686	16450	0.0002	-
0.4700	16500	0.0001	-
0.4714	16550	0.0002	-
0.4728	16600	0.0002	-
0.4743	16650	0.0001	-
0.4757	16700	0.0002	-
0.4771	16750	0.0001	-
0.4785	16800	0.0001	-
0.4799	16850	0.0001	-
0.4814	16900	0.0004	-
0.4828	16950	0.0001	-
0.4842	17000	0.0002	-
0.4856	17050	0.0001	-
0.4871	17100	0.0001	-
0.4885	17150	0.0002	-
0.4899	17200	0.0001	-
0.4913	17250	0.0001	-
0.4928	17300	0.0001	-
0.4942	17350	0.0001	-
0.4956	17400	0.0001	-
0.4970	17450	0.0001	-
0.4985	17500	0.0001	-
0.4999	17550	0.0001	-
0.5013	17600	0.0002	-
0.5027	17650	0.0001	-
0.5042	17700	0.0001	-
0.5056	17750	0.0001	-
0.5070	17800	0.0001	-
0.5084	17850	0.0001	-
0.5099	17900	0.0001	-
0.5113	17950	0.0001	-
0.5127	18000	0.0001	-
0.5141	18050	0.0001	-
0.5156	18100	0.0001	-
0.5170	18150	0.0001	-
0.5184	18200	0.0001	-
0.5198	18250	0.0001	-
0.5212	18300	0.0001	-
0.5227	18350	0.0001	-
0.5241	18400	0.0001	-
0.5255	18450	0.0001	-
0.5269	18500	0.0001	-
0.5284	18550	0.0001	-
0.5298	18600	0.0001	-
0.5312	18650	0.0001	-
0.5326	18700	0.0001	-
0.5341	18750	0.0001	-
0.5355	18800	0.0001	-
0.5369	18850	0.0001	-
0.5383	18900	0.0001	-
0.5398	18950	0.0001	-
0.5412	19000	0.0001	-
0.5426	19050	0.0001	-
0.5440	19100	0.0001	-
0.5455	19150	0.0001	-
0.5469	19200	0.0001	-
0.5483	19250	0.0001	-
0.5497	19300	0.0001	-
0.5512	19350	0.0001	-
0.5526	19400	0.0001	-
0.5540	19450	0.0	-
0.5554	19500	0.0001	-
0.5569	19550	0.0001	-
0.5583	19600	0.0001	-
0.5597	19650	0.0001	-
0.5611	19700	0.0001	-
0.5625	19750	0.0001	-
0.5640	19800	0.0001	-
0.5654	19850	0.0001	-
0.5668	19900	0.0001	-
0.5682	19950	0.0001	-
0.5697	20000	0.0001	-
0.5711	20050	0.0001	-
0.5725	20100	0.0001	-
0.5739	20150	0.0001	-
0.5754	20200	0.0	-
0.5768	20250	0.0001	-
0.5782	20300	0.0001	-
0.5796	20350	0.0	-
0.5811	20400	0.0001	-
0.5825	20450	0.0001	-
0.5839	20500	0.0001	-
0.5853	20550	0.0001	-
0.5868	20600	0.0001	-
0.5882	20650	0.0001	-
0.5896	20700	0.0001	-
0.5910	20750	0.0001	-
0.5925	20800	0.0001	-
0.5939	20850	0.0001	-
0.5953	20900	0.0001	-
0.5967	20950	0.0001	-
0.5982	21000	0.0	-
0.5996	21050	0.0001	-
0.6010	21100	0.0001	-
0.6024	21150	0.0001	-
0.6039	21200	0.0001	-
0.6053	21250	0.0002	-
0.6067	21300	0.0001	-
0.6081	21350	0.0001	-
0.6095	21400	0.0001	-
0.6110	21450	0.0001	-
0.6124	21500	0.0001	-
0.6138	21550	0.0001	-
0.6152	21600	0.0001	-
0.6167	21650	0.0001	-
0.6181	21700	0.0001	-
0.6195	21750	0.0001	-
0.6209	21800	0.0001	-
0.6224	21850	0.0	-
0.6238	21900	0.0001	-
0.6252	21950	0.0001	-
0.6266	22000	0.0001	-
0.6281	22050	0.0001	-
0.6295	22100	0.0001	-
0.6309	22150	0.0001	-
0.6323	22200	0.0001	-
0.6338	22250	0.0001	-
0.6352	22300	0.0001	-
0.6366	22350	0.0001	-
0.6380	22400	0.0001	-
0.6395	22450	0.0001	-
0.6409	22500	0.0001	-
0.6423	22550	0.0001	-
0.6437	22600	0.0001	-
0.6452	22650	0.0001	-
0.6466	22700	0.0001	-
0.6480	22750	0.0001	-
0.6494	22800	0.0001	-
0.6508	22850	0.0001	-
0.6523	22900	0.0	-
0.6537	22950	0.0001	-
0.6551	23000	0.0001	-
0.6565	23050	0.0001	-
0.6580	23100	0.0001	-
0.6594	23150	0.0001	-
0.6608	23200	0.0001	-
0.6622	23250	0.0001	-
0.6637	23300	0.0	-
0.6651	23350	0.0001	-
0.6665	23400	0.0001	-
0.6679	23450	0.0001	-
0.6694	23500	0.0	-
0.6708	23550	0.0001	-
0.6722	23600	0.0	-
0.6736	23650	0.0001	-
0.6751	23700	0.0001	-
0.6765	23750	0.0	-
0.6779	23800	0.0001	-
0.6793	23850	0.0001	-
0.6808	23900	0.0001	-
0.6822	23950	0.0001	-
0.6836	24000	0.0	-
0.6850	24050	0.0001	-
0.6865	24100	0.0	-
0.6879	24150	0.0001	-
0.6893	24200	0.0001	-
0.6907	24250	0.0001	-
0.6921	24300	0.0001	-
0.6936	24350	0.0	-
0.6950	24400	0.0001	-
0.6964	24450	0.0001	-
0.6978	24500	0.0001	-
0.6993	24550	0.0001	-
0.7007	24600	0.0	-
0.7021	24650	0.0	-
0.7035	24700	0.0001	-
0.7050	24750	0.0001	-
0.7064	24800	0.0001	-
0.7078	24850	0.0001	-
0.7092	24900	0.0001	-
0.7107	24950	0.0001	-
0.7121	25000	0.0001	-
0.7135	25050	0.0001	-
0.7149	25100	0.0001	-
0.7164	25150	0.0001	-
0.7178	25200	0.0001	-
0.7192	25250	0.0001	-
0.7206	25300	0.0001	-
0.7221	25350	0.0001	-
0.7235	25400	0.0001	-
0.7249	25450	0.0001	-
0.7263	25500	0.0001	-
0.7278	25550	0.0	-
0.7292	25600	0.0	-
0.7306	25650	0.0	-
0.7320	25700	0.0001	-
0.7335	25750	0.0001	-
0.7349	25800	0.0001	-
0.7363	25850	0.0001	-
0.7377	25900	0.0	-
0.7391	25950	0.0	-
0.7406	26000	0.0001	-
0.7420	26050	0.0001	-
0.7434	26100	0.0	-
0.7448	26150	0.0	-
0.7463	26200	0.0001	-
0.7477	26250	0.0	-
0.7491	26300	0.0	-
0.7505	26350	0.0	-
0.7520	26400	0.0001	-
0.7534	26450	0.0	-
0.7548	26500	0.0001	-
0.7562	26550	0.0001	-
0.7577	26600	0.0001	-
0.7591	26650	0.0001	-
0.7605	26700	0.0	-
0.7619	26750	0.0001	-
0.7634	26800	0.0001	-
0.7648	26850	0.0001	-
0.7662	26900	0.0	-
0.7676	26950	0.0001	-
0.7691	27000	0.0	-
0.7705	27050	0.0	-
0.7719	27100	0.0001	-
0.7733	27150	0.0	-
0.7748	27200	0.0	-
0.7762	27250	0.0001	-
0.7776	27300	0.0001	-
0.7790	27350	0.0001	-
0.7804	27400	0.0001	-
0.7819	27450	0.0	-
0.7833	27500	0.0001	-
0.7847	27550	0.0	-
0.7861	27600	0.0	-
0.7876	27650	0.0001	-
0.7890	27700	0.0001	-
0.7904	27750	0.0	-
0.7918	27800	0.0001	-
0.7933	27850	0.0001	-
0.7947	27900	0.0	-
0.7961	27950	0.0	-
0.7975	28000	0.0	-
0.7990	28050	0.0001	-
0.8004	28100	0.0	-
0.8018	28150	0.0001	-
0.8032	28200	0.0001	-
0.8047	28250	0.0	-
0.8061	28300	0.0	-
0.8075	28350	0.0	-
0.8089	28400	0.0001	-
0.8104	28450	0.0	-
0.8118	28500	0.0	-
0.8132	28550	0.0	-
0.8146	28600	0.0	-
0.8161	28650	0.0	-
0.8175	28700	0.0	-
0.8189	28750	0.0001	-
0.8203	28800	0.0	-
0.8218	28850	0.0	-
0.8232	28900	0.0	-
0.8246	28950	0.0001	-
0.8260	29000	0.0	-
0.8274	29050	0.0001	-
0.8289	29100	0.0001	-
0.8303	29150	0.0001	-
0.8317	29200	0.0001	-
0.8331	29250	0.0001	-
0.8346	29300	0.0001	-
0.8360	29350	0.0	-
0.8374	29400	0.0	-
0.8388	29450	0.0001	-
0.8403	29500	0.0001	-
0.8417	29550	0.0001	-
0.8431	29600	0.0001	-
0.8445	29650	0.0001	-
0.8460	29700	0.0	-
0.8474	29750	0.0	-
0.8488	29800	0.0001	-
0.8502	29850	0.0001	-
0.8517	29900	0.0	-
0.8531	29950	0.0001	-
0.8545	30000	0.0001	-
0.8559	30050	0.0001	-
0.8574	30100	0.0001	-
0.8588	30150	0.0	-
0.8602	30200	0.0	-
0.8616	30250	0.0001	-
0.8631	30300	0.0001	-
0.8645	30350	0.0	-
0.8659	30400	0.0	-
0.8673	30450	0.0001	-
0.8687	30500	0.0	-
0.8702	30550	0.0	-
0.8716	30600	0.0	-
0.8730	30650	0.0001	-
0.8744	30700	0.0	-
0.8759	30750	0.0	-
0.8773	30800	0.0001	-
0.8787	30850	0.0001	-
0.8801	30900	0.0	-
0.8816	30950	0.0	-
0.8830	31000	0.0	-
0.8844	31050	0.0001	-
0.8858	31100	0.0001	-
0.8873	31150	0.0001	-
0.8887	31200	0.0	-
0.8901	31250	0.0	-
0.8915	31300	0.0	-
0.8930	31350	0.0001	-
0.8944	31400	0.0	-
0.8958	31450	0.0	-
0.8972	31500	0.0	-
0.8987	31550	0.0001	-
0.9001	31600	0.0	-
0.9015	31650	0.0	-
0.9029	31700	0.0001	-
0.9044	31750	0.0	-
0.9058	31800	0.0	-
0.9072	31850	0.0	-
0.9086	31900	0.0	-
0.9100	31950	0.0001	-
0.9115	32000	0.0001	-
0.9129	32050	0.0	-
0.9143	32100	0.0	-
0.9157	32150	0.0	-
0.9172	32200	0.0	-
0.9186	32250	0.0	-
0.9200	32300	0.0	-
0.9214	32350	0.0	-
0.9229	32400	0.0	-
0.9243	32450	0.0	-
0.9257	32500	0.0	-
0.9271	32550	0.0	-
0.9286	32600	0.0001	-
0.9300	32650	0.0001	-
0.9314	32700	0.0	-
0.9328	32750	0.0001	-
0.9343	32800	0.0	-
0.9357	32850	0.0	-
0.9371	32900	0.0	-
0.9385	32950	0.0	-
0.9400	33000	0.0	-
0.9414	33050	0.0	-
0.9428	33100	0.0	-
0.9442	33150	0.0001	-
0.9457	33200	0.0001	-
0.9471	33250	0.0	-
0.9485	33300	0.0	-
0.9499	33350	0.0	-
0.9514	33400	0.0	-
0.9528	33450	0.0	-
0.9542	33500	0.0001	-
0.9556	33550	0.0	-
0.9570	33600	0.0	-
0.9585	33650	0.0	-
0.9599	33700	0.0	-
0.9613	33750	0.0001	-
0.9627	33800	0.0	-
0.9642	33850	0.0001	-
0.9656	33900	0.0001	-
0.9670	33950	0.0	-
0.9684	34000	0.0	-
0.9699	34050	0.0	-
0.9713	34100	0.0001	-
0.9727	34150	0.0001	-
0.9741	34200	0.0	-
0.9756	34250	0.0	-
0.9770	34300	0.0	-
0.9784	34350	0.0	-
0.9798	34400	0.0	-
0.9813	34450	0.0	-
0.9827	34500	0.0	-
0.9841	34550	0.0	-
0.9855	34600	0.0	-
0.9870	34650	0.0001	-
0.9884	34700	0.0	-
0.9898	34750	0.0	-
0.9912	34800	0.0	-
0.9927	34850	0.0001	-
0.9941	34900	0.0	-
0.9955	34950	0.0	-
0.9969	35000	0.0001	-
0.9983	35050	0.0	-
0.9998	35100	0.0	-
1.0	35108	-	0.03

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.11.9
SetFit: 1.1.0.dev0
Sentence Transformers: 3.0.1
Transformers: 4.44.2
PyTorch: 2.4.0+cu121
Datasets: 2.21.0
Tokenizers: 0.19.1

Citation

BibTeX

@article{https://doi.org/10.48550/arxiv.2209.11055,
    doi = {10.48550/ARXIV.2209.11055},
    url = {https://arxiv.org/abs/2209.11055},
    author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
    keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
    title = {Efficient Few-Shot Learning Without Prompts},
    publisher = {arXiv},
    year = {2022},
    copyright = {Creative Commons Attribution 4.0 International}
}