learning_rate: 5e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 2.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.6488	0.0091	200	1.6336
1.6233	0.0182	400	1.5885
1.5410	0.0274	600	1.5403
1.4897	0.0365	800	1.5139
1.5266	0.0456	1000	1.4763
1.4467	0.0547	1200	1.4595
1.4198	0.0639	1400	1.4323
1.3921	0.0730	1600	1.4208
1.3304	0.0821	1800	1.4136
1.4402	0.0912	2000	1.3943
1.3559	0.1004	2200	1.3858
1.3961	0.1095	2400	1.3780
1.3254	0.1186	2600	1.3727
1.3572	0.1277	2800	1.3589
1.3505	0.1369	3000	1.3510
1.3653	0.1460	3200	1.3483
1.3475	0.1551	3400	1.3461
1.3137	0.1642	3600	1.3385
1.2586	0.1734	3800	1.3367
1.3001	0.1825	4000	1.3355
1.2693	0.1916	4200	1.3244
1.2862	0.2007	4400	1.3244
1.2662	0.2099	4600	1.3213
1.2722	0.2190	4800	1.3140
1.2846	0.2281	5000	1.3200
1.3175	0.2372	5200	1.3131
1.2471	0.2464	5400	1.3083
1.3032	0.2555	5600	1.3040
1.3352	0.2646	5800	1.3020
1.2884	0.2737	6000	1.2999
1.2797	0.2829	6200	1.2991
1.2288	0.2920	6400	1.2956
1.3199	0.3011	6600	1.2957
1.2344	0.3102	6800	1.2916
1.3403	0.3194	7000	1.2880
1.2506	0.3285	7200	1.2868
1.2460	0.3376	7400	1.2864
1.2465	0.3467	7600	1.2875
1.2151	0.3559	7800	1.2839
1.1610	0.3650	8000	1.2805
1.2468	0.3741	8200	1.2797
1.2222	0.3832	8400	1.2787
1.3738	0.3924	8600	1.2742
1.2964	0.4015	8800	1.2758
1.2431	0.4106	9000	1.2741
1.2991	0.4197	9200	1.2727
1.2796	0.4289	9400	1.2714
1.2258	0.4380	9600	1.2721
1.2744	0.4471	9800	1.2675
1.2123	0.4562	10000	1.2704
1.2420	0.4654	10200	1.2641
1.2299	0.4745	10400	1.2634
1.2399	0.4836	10600	1.2643
1.1950	0.4927	10800	1.2643
1.2583	0.5019	11000	1.2601
1.2270	0.5110	11200	1.2594
1.2840	0.5201	11400	1.2620
1.2499	0.5292	11600	1.2594
1.2344	0.5384	11800	1.2571
1.2208	0.5475	12000	1.2566
1.2130	0.5566	12200	1.2569
1.2775	0.5657	12400	1.2544
1.1494	0.5749	12600	1.2565
1.2251	0.5840	12800	1.2547
1.1800	0.5931	13000	1.2546
1.2082	0.6022	13200	1.2572
1.3139	0.6114	13400	1.2519
1.2370	0.6205	13600	1.2481
1.3063	0.6296	13800	1.2507
1.2561	0.6387	14000	1.2488
1.2776	0.6479	14200	1.2464
1.2259	0.6570	14400	1.2473
1.2012	0.6661	14600	1.2459
1.2441	0.6752	14800	1.2456
1.2536	0.6844	15000	1.2434
1.1914	0.6935	15200	1.2436
1.2660	0.7026	15400	1.2416
1.2109	0.7117	15600	1.2430
1.2659	0.7209	15800	1.2414
1.2276	0.7300	16000	1.2428
1.2342	0.7391	16200	1.2411
1.2172	0.7482	16400	1.2438
1.1921	0.7574	16600	1.2412
1.1912	0.7665	16800	1.2405
1.2400	0.7756	17000	1.2398
1.2125	0.7847	17200	1.2401
1.2058	0.7939	17400	1.2395
1.2236	0.8030	17600	1.2377
1.1780	0.8121	17800	1.2360
1.2691	0.8212	18000	1.2341
1.1868	0.8304	18200	1.2345
1.1969	0.8395	18400	1.2339
1.2250	0.8486	18600	1.2326
1.2049	0.8577	18800	1.2343
1.1888	0.8669	19000	1.2331
1.2316	0.8760	19200	1.2332
1.1834	0.8851	19400	1.2302
1.1908	0.8942	19600	1.2324
1.1418	0.9034	19800	1.2341
1.2006	0.9125	20000	1.2339
1.2495	0.9216	20200	1.2314
1.1748	0.9307	20400	1.2300
1.2592	0.9399	20600	1.2282
1.2270	0.9490	20800	1.2289
1.2260	0.9581	21000	1.2286
1.2126	0.9672	21200	1.2274
1.2802	0.9764	21400	1.2273
1.1139	0.9855	21600	1.2283
1.2185	0.9946	21800	1.2279
1.2269	1.0037	22000	1.2260
1.2784	1.0128	22200	1.2269
1.1738	1.0219	22400	1.2244
1.1731	1.0311	22600	1.2265
1.2123	1.0402	22800	1.2277
1.2025	1.0493	23000	1.2258
1.1571	1.0584	23200	1.2282
1.2365	1.0676	23400	1.2239
1.2074	1.0767	23600	1.2241
1.2161	1.0858	23800	1.2243
1.1620	1.0949	24000	1.2236
1.1873	1.1041	24200	1.2234
1.2166	1.1132	24400	1.2215
1.2030	1.1223	24600	1.2252
1.2377	1.1314	24800	1.2226
1.1019	1.1406	25000	1.2231
1.1518	1.1497	25200	1.2218
1.1767	1.1588	25400	1.2222
1.1636	1.1679	25600	1.2218
1.1781	1.1771	25800	1.2182
1.2452	1.1862	26000	1.2189
1.1345	1.1953	26200	1.2202
1.1484	1.2044	26400	1.2191
1.1758	1.2136	26600	1.2189
1.2341	1.2227	26800	1.2198
1.1707	1.2318	27000	1.2182
1.1659	1.2409	27200	1.2188
1.1724	1.2501	27400	1.2174
1.1910	1.2592	27600	1.2180
1.2170	1.2683	27800	1.2190
1.1742	1.2774	28000	1.2173
1.2326	1.2866	28200	1.2160
1.2562	1.2957	28400	1.2168
1.2909	1.3048	28600	1.2165
1.2050	1.3139	28800	1.2149
1.1748	1.3231	29000	1.2148
1.2576	1.3322	29200	1.2143
1.1741	1.3413	29400	1.2162
1.1516	1.3504	29600	1.2148
1.1671	1.3596	29800	1.2139
1.1986	1.3687	30000	1.2138
1.1732	1.3778	30200	1.2137
1.1638	1.3869	30400	1.2139
1.1912	1.3961	30600	1.2131
1.1784	1.4052	30800	1.2130
1.2396	1.4143	31000	1.2126
1.1685	1.4234	31200	1.2136
1.1804	1.4326	31400	1.2121
1.1612	1.4417	31600	1.2128
1.1808	1.4508	31800	1.2130
1.2270	1.4599	32000	1.2119
1.1435	1.4691	32200	1.2097
1.2396	1.4782	32400	1.2112
1.1820	1.4873	32600	1.2120
1.2462	1.4964	32800	1.2104
1.2212	1.5056	33000	1.2110
1.2230	1.5147	33200	1.2113
1.1986	1.5238	33400	1.2116
1.1560	1.5329	33600	1.2106
1.1886	1.5421	33800	1.2107
1.1942	1.5512	34000	1.2095
1.1993	1.5603	34200	1.2091
1.1347	1.5694	34400	1.2100
1.1856	1.5786	34600	1.2108
1.2310	1.5877	34800	1.2083
1.1439	1.5968	35000	1.2096
1.1951	1.6059	35200	1.2088
1.1219	1.6151	35400	1.2094
1.1995	1.6242	35600	1.2085
1.2054	1.6333	35800	1.2078
1.2018	1.6424	36000	1.2085
1.2098	1.6516	36200	1.2088
1.2095	1.6607	36400	1.2093
1.1676	1.6698	36600	1.2075
1.2269	1.6789	36800	1.2078
1.2036	1.6881	37000	1.2069
1.1355	1.6972	37200	1.2082
1.1892	1.7063	37400	1.2075
1.1503	1.7154	37600	1.2079
1.2011	1.7246	37800	1.2079
1.1578	1.7337	38000	1.2069
1.2129	1.7428	38200	1.2065
1.1861	1.7519	38400	1.2061
1.1666	1.7611	38600	1.2065
1.1726	1.7702	38800	1.2069
1.1537	1.7793	39000	1.2070
1.1758	1.7884	39200	1.2062
1.2147	1.7976	39400	1.2059
1.1239	1.8067	39600	1.2067
1.1779	1.8158	39800	1.2061
1.2168	1.8249	40000	1.2059
1.1668	1.8341	40200	1.2059
1.1950	1.8432	40400	1.2056
1.1701	1.8523	40600	1.2055
1.1515	1.8614	40800	1.2058
1.1966	1.8706	41000	1.2058
1.1048	1.8797	41200	1.2054
1.2088	1.8888	41400	1.2048
1.1656	1.8979	41600	1.2059
1.2078	1.9071	41800	1.2053
1.1824	1.9162	42000	1.2054
1.2179	1.9253	42200	1.2047
1.1417	1.9344	42400	1.2053
1.1582	1.9436	42600	1.2054
1.1408	1.9527	42800	1.2049
1.1519	1.9618	43000	1.2051
1.1383	1.9709	43200	1.2051
1.2222	1.9801	43400	1.2047
1.2054	1.9892	43600	1.2046
1.2109	1.9983	43800	1.2046
1.1753	2.0	43838	1.2046

Framework versions

Transformers 5.15.0
Pytorch 2.13.0+cu130
Datasets 5.0.1
Tokenizers 0.22.2

jeanmidev/trackmania-tmnf-full-2026-08-13

trackmania-tmnf-full-2026-08-13

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

jeanmidev/
trackmania-tmnf-full-2026-08-13