tfa_output_2025_m02_d07_t07h_45m_38s

brando/tfa_output_2025_m02_d07_t07h_45m_38s

tfa_output_2025_m02_d07_t07h_45m_38s is a text generation model from brando. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

7% of all-time downloads

All-time downloads

176

Public

Parameters

494M

1000 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors2 GB · 98%

At a glance

Task: Text Generation
Library: transformers
License: apache-2.0
Model type: qwen2
Access: Public
Created: Feb 7, 2025
Updated: Feb 7, 2025
SHA: 6c98816a

Try a prompt

Base models

Qwen/Qwen2.5-0.5B

Model card

From the Hugging Face model README

tfa_output_2025_m02_d07_t07h_45m_38s

This model is a fine-tuned version of Qwen/Qwen2.5-0.5B on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.1965

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-06
train_batch_size: 2
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
optimizer: Use OptimizerNames.PAGED_ADAMW with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant_with_warmup
lr_scheduler_warmup_ratio: 0.05
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0	0	1.3072
4.0374	0.0030	1	1.3072
3.7206	0.0060	2	1.3073
3.6304	0.0090	3	1.3075
3.9205	0.0119	4	1.3072
3.8914	0.0149	5	1.3074
3.7914	0.0179	6	1.3071
3.6888	0.0209	7	1.3073
3.9573	0.0239	8	1.3068
3.9216	0.0269	9	1.3068
3.8295	0.0299	10	1.3065
3.7775	0.0328	11	1.3061
4.1608	0.0358	12	1.3056
3.8315	0.0388	13	1.3047
3.8961	0.0418	14	1.3041
3.5064	0.0448	15	1.3034
3.8623	0.0478	16	1.3029
3.7882	0.0507	17	1.3022
3.9906	0.0537	18	1.3004
3.8721	0.0567	19	1.2990
3.8715	0.0597	20	1.2982
3.7604	0.0627	21	1.2970
3.7259	0.0657	22	1.2961
3.769	0.0687	23	1.2948
3.9388	0.0716	24	1.2935
3.8075	0.0746	25	1.2921
3.9561	0.0776	26	1.2913
3.8021	0.0806	27	1.2904
3.658	0.0836	28	1.2892
3.7469	0.0866	29	1.2883
3.9257	0.0896	30	1.2873
3.7349	0.0925	31	1.2864
3.7425	0.0955	32	1.2854
3.3611	0.0985	33	1.2843
3.5493	0.1015	34	1.2833
3.596	0.1045	35	1.2828
3.8972	0.1075	36	1.2816
3.9669	0.1104	37	1.2808
4.0005	0.1134	38	1.2800
3.6185	0.1164	39	1.2785
4.0852	0.1194	40	1.2776
3.452	0.1224	41	1.2769
4.017	0.1254	42	1.2761
3.8406	0.1284	43	1.2753
3.5601	0.1313	44	1.2746
3.7764	0.1343	45	1.2731
3.8586	0.1373	46	1.2722
3.2432	0.1403	47	1.2715
3.5002	0.1433	48	1.2706
3.4933	0.1463	49	1.2701
3.5798	0.1493	50	1.2688
3.6943	0.1522	51	1.2681
3.3713	0.1552	52	1.2675
3.6274	0.1582	53	1.2666
3.5537	0.1612	54	1.2653
3.5242	0.1642	55	1.2646
3.6243	0.1672	56	1.2637
3.4449	0.1701	57	1.2630
3.6649	0.1731	58	1.2621
3.643	0.1761	59	1.2615
3.5039	0.1791	60	1.2607
3.7135	0.1821	61	1.2595
3.8718	0.1851	62	1.2587
3.4509	0.1881	63	1.2581
3.7153	0.1910	64	1.2569
3.6279	0.1940	65	1.2564
3.1831	0.1970	66	1.2557
3.6647	0.2	67	1.2548
3.8362	0.2030	68	1.2543
3.7985	0.2060	69	1.2533
3.6422	0.2090	70	1.2525
3.4649	0.2119	71	1.2522
3.645	0.2149	72	1.2518
3.6387	0.2179	73	1.2508
3.6069	0.2209	74	1.2500
3.297	0.2239	75	1.2492
3.2928	0.2269	76	1.2487
3.4727	0.2299	77	1.2482
3.2704	0.2328	78	1.2473
3.4458	0.2358	79	1.2467
3.492	0.2388	80	1.2458
3.5288	0.2418	81	1.2453
3.6266	0.2448	82	1.2447
3.6181	0.2478	83	1.2442
3.4847	0.2507	84	1.2434
3.7349	0.2537	85	1.2431
3.7247	0.2567	86	1.2424
3.3359	0.2597	87	1.2419
3.3628	0.2627	88	1.2408
3.6579	0.2657	89	1.2408
3.601	0.2687	90	1.2406
3.1941	0.2716	91	1.2399
3.5671	0.2746	92	1.2395
3.7115	0.2776	93	1.2385
3.532	0.2806	94	1.2381
3.5191	0.2836	95	1.2374
3.6731	0.2866	96	1.2371
3.7962	0.2896	97	1.2367
3.7644	0.2925	98	1.2361
3.4904	0.2955	99	1.2356
3.5935	0.2985	100	1.2354
3.577	0.3015	101	1.2346
3.693	0.3045	102	1.2344
3.6223	0.3075	103	1.2340
3.4485	0.3104	104	1.2334
3.4748	0.3134	105	1.2329
3.4188	0.3164	106	1.2324
3.5004	0.3194	107	1.2321
3.6142	0.3224	108	1.2317
3.3817	0.3254	109	1.2313
3.5531	0.3284	110	1.2311
3.1087	0.3313	111	1.2306
3.3683	0.3343	112	1.2304
3.8721	0.3373	113	1.2298
3.7024	0.3403	114	1.2293
3.5345	0.3433	115	1.2289
3.573	0.3463	116	1.2287
3.5846	0.3493	117	1.2284
3.5404	0.3522	118	1.2282
3.5606	0.3552	119	1.2280
3.5055	0.3582	120	1.2274
3.4956	0.3612	121	1.2270
3.608	0.3642	122	1.2268
3.2361	0.3672	123	1.2265
3.488	0.3701	124	1.2265
3.2155	0.3731	125	1.2260
3.3639	0.3761	126	1.2256
3.3634	0.3791	127	1.2256
3.4846	0.3821	128	1.2254
3.5508	0.3851	129	1.2252
3.5719	0.3881	130	1.2246
3.3178	0.3910	131	1.2247
3.4262	0.3940	132	1.2243
3.4895	0.3970	133	1.2239
3.5872	0.4	134	1.2234
3.4766	0.4030	135	1.2233
3.3568	0.4060	136	1.2230
3.5747	0.4090	137	1.2230
2.9403	0.4119	138	1.2226
3.3463	0.4149	139	1.2223
3.3048	0.4179	140	1.2217
3.2987	0.4209	141	1.2218
3.4811	0.4239	142	1.2216
3.64	0.4269	143	1.2211
3.1703	0.4299	144	1.2206
3.2906	0.4328	145	1.2205
3.6134	0.4358	146	1.2199
3.348	0.4388	147	1.2197
3.2428	0.4418	148	1.2198
3.573	0.4448	149	1.2197
3.6921	0.4478	150	1.2191
3.5082	0.4507	151	1.2191
3.3445	0.4537	152	1.2189
3.3521	0.4567	153	1.2187
3.4538	0.4597	154	1.2183
3.3225	0.4627	155	1.2179
3.6838	0.4657	156	1.2179
3.3113	0.4687	157	1.2177
3.4141	0.4716	158	1.2175
2.8407	0.4746	159	1.2173
3.3262	0.4776	160	1.2168
3.6585	0.4806	161	1.2167
3.4489	0.4836	162	1.2166
3.6269	0.4866	163	1.2162
3.3826	0.4896	164	1.2160
3.4506	0.4925	165	1.2159
3.2749	0.4955	166	1.2151
3.7262	0.4985	167	1.2151
3.4615	0.5015	168	1.2147
3.5982	0.5045	169	1.2149
3.5301	0.5075	170	1.2142
3.1629	0.5104	171	1.2145
3.3415	0.5134	172	1.2140
3.2653	0.5164	173	1.2139
3.2757	0.5194	174	1.2137
3.3495	0.5224	175	1.2136
3.4542	0.5254	176	1.2135
3.5153	0.5284	177	1.2130
3.2836	0.5313	178	1.2126
3.2877	0.5343	179	1.2123
3.4662	0.5373	180	1.2125
3.0825	0.5403	181	1.2123
3.381	0.5433	182	1.2121
3.3843	0.5463	183	1.2118
3.0211	0.5493	184	1.2116
3.2045	0.5522	185	1.2113
3.515	0.5552	186	1.2111
3.3176	0.5582	187	1.2113
3.5145	0.5612	188	1.2109
3.135	0.5642	189	1.2106
3.5442	0.5672	190	1.2107
3.3991	0.5701	191	1.2106
3.2577	0.5731	192	1.2103
3.286	0.5761	193	1.2102
3.4492	0.5791	194	1.2097
3.7012	0.5821	195	1.2098
3.2023	0.5851	196	1.2097
3.207	0.5881	197	1.2097
3.3281	0.5910	198	1.2091
3.3071	0.5940	199	1.2091
3.39	0.5970	200	1.2091
3.2437	0.6	201	1.2090
3.2771	0.6030	202	1.2089
3.4758	0.6060	203	1.2085
3.2785	0.6090	204	1.2082
3.524	0.6119	205	1.2084
3.3163	0.6149	206	1.2082
3.3725	0.6179	207	1.2078
3.4803	0.6209	208	1.2078
3.1456	0.6239	209	1.2080
3.2719	0.6269	210	1.2079
3.4017	0.6299	211	1.2074
3.3843	0.6328	212	1.2073
3.5353	0.6358	213	1.2070
3.2673	0.6388	214	1.2072
3.2824	0.6418	215	1.2070
3.3562	0.6448	216	1.2069
3.1972	0.6478	217	1.2069
3.3425	0.6507	218	1.2067
3.1529	0.6537	219	1.2066
3.0392	0.6567	220	1.2062
2.9891	0.6597	221	1.2063
3.451	0.6627	222	1.2059
3.19	0.6657	223	1.2061
3.2682	0.6687	224	1.2057
3.4182	0.6716	225	1.2055
3.4638	0.6746	226	1.2054
3.2297	0.6776	227	1.2053
3.3207	0.6806	228	1.2051
3.2218	0.6836	229	1.2051
3.2048	0.6866	230	1.2049
3.1883	0.6896	231	1.2050
3.5168	0.6925	232	1.2048
3.4838	0.6955	233	1.2047
3.148	0.6985	234	1.2050
3.35	0.7015	235	1.2045
3.156	0.7045	236	1.2043
3.2269	0.7075	237	1.2045
3.1877	0.7104	238	1.2039
3.4361	0.7134	239	1.2041
3.2583	0.7164	240	1.2039
3.3384	0.7194	241	1.2037
3.235	0.7224	242	1.2038
3.2664	0.7254	243	1.2037
3.1289	0.7284	244	1.2033
3.4714	0.7313	245	1.2035
3.4815	0.7343	246	1.2035
3.5291	0.7373	247	1.2033
3.2485	0.7403	248	1.2032
3.3338	0.7433	249	1.2028
3.0806	0.7463	250	1.2030
3.3287	0.7493	251	1.2027
3.4036	0.7522	252	1.2025
3.2587	0.7552	253	1.2024
2.8553	0.7582	254	1.2025
3.3085	0.7612	255	1.2022
3.0679	0.7642	256	1.2023
3.2612	0.7672	257	1.2022
3.5312	0.7701	258	1.2021
3.2655	0.7731	259	1.2018
3.054	0.7761	260	1.2018
3.306	0.7791	261	1.2017
3.2836	0.7821	262	1.2015
2.992	0.7851	263	1.2014
3.2031	0.7881	264	1.2013
3.4771	0.7910	265	1.2013
3.2433	0.7940	266	1.2011
3.0587	0.7970	267	1.2012
3.0495	0.8	268	1.2012
3.3093	0.8030	269	1.2008
3.3915	0.8060	270	1.2010
3.345	0.8090	271	1.2008
3.1808	0.8119	272	1.2006
3.209	0.8149	273	1.2007
3.0482	0.8179	274	1.2004
2.9668	0.8209	275	1.2006
3.0532	0.8239	276	1.2008
3.3684	0.8269	277	1.2004
3.2661	0.8299	278	1.2003
3.0364	0.8328	279	1.2003
3.4541	0.8358	280	1.2002
3.3404	0.8388	281	1.2001
3.4284	0.8418	282	1.1999
3.4654	0.8448	283	1.1997
3.0229	0.8478	284	1.2000
3.2988	0.8507	285	1.1999
3.3894	0.8537	286	1.1995
3.2594	0.8567	287	1.1995
3.2245	0.8597	288	1.1995
3.0186	0.8627	289	1.1991
3.0315	0.8657	290	1.1990
2.8311	0.8687	291	1.1990
3.1816	0.8716	292	1.1988
3.3245	0.8746	293	1.1987
3.434	0.8776	294	1.1988
3.09	0.8806	295	1.1986
3.4151	0.8836	296	1.1983
3.2193	0.8866	297	1.1984
3.3492	0.8896	298	1.1985
3.1033	0.8925	299	1.1983
3.3869	0.8955	300	1.1984
3.2651	0.8985	301	1.1981
3.3921	0.9015	302	1.1981
3.3988	0.9045	303	1.1981
3.3168	0.9075	304	1.1983
3.173	0.9104	305	1.1980
3.1127	0.9134	306	1.1981
2.9588	0.9164	307	1.1979
3.1549	0.9194	308	1.1978
3.1344	0.9224	309	1.1978
3.0571	0.9254	310	1.1977
3.299	0.9284	311	1.1976
3.3548	0.9313	312	1.1975
3.1675	0.9343	313	1.1975
3.2788	0.9373	314	1.1972
3.1682	0.9403	315	1.1975
3.6201	0.9433	316	1.1973
2.9316	0.9463	317	1.1973
3.2871	0.9493	318	1.1970
3.0758	0.9522	319	1.1973
3.0506	0.9552	320	1.1972
3.0749	0.9582	321	1.1971
3.0325	0.9612	322	1.1969
3.0342	0.9642	323	1.1969
3.2879	0.9672	324	1.1969
2.9969	0.9701	325	1.1967
3.4164	0.9731	326	1.1967
3.3712	0.9761	327	1.1966
3.1877	0.9791	328	1.1967
3.3259	0.9821	329	1.1968
3.2571	0.9851	330	1.1965
3.0292	0.9881	331	1.1968
3.2312	0.9910	332	1.1966
3.3412	0.9940	333	1.1965
3.2653	0.9970	334	1.1966
3.3735	1.0	335	1.1965

Framework versions

Transformers 4.48.0
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0

Task: Text Generation
Library: transformers
Type: qwen2
License: apache-2.0
Created: Feb 7, 2025
Updated: Feb 7, 2025