Training Loss	Epoch	Step	Validation Loss	Accuracy
2.1877	0.0	200	2.1894	0.5763
1.612	0.01	400	1.5928	0.6109
1.2645	0.01	600	1.2604	0.6379
1.0711	0.01	800	1.0720	0.6547
0.953	0.02	1000	0.9513	0.6628
0.9024	0.02	1200	0.8965	0.6678
0.8682	0.02	1400	0.8618	0.6712
0.8366	0.03	1600	0.8343	0.6741
0.8127	0.03	1800	0.8146	0.6763
0.7916	0.03	2000	0.7940	0.6784
0.781	0.04	2200	0.7815	0.6799
0.7647	0.04	2400	0.7692	0.6813
0.7617	0.04	2600	0.7589	0.6825
0.7523	0.05	2800	0.7466	0.6842
0.7394	0.05	3000	0.7373	0.6852
0.7297	0.05	3200	0.7279	0.6864
0.712	0.06	3400	0.7206	0.6871
0.716	0.06	3600	0.7120	0.6884
0.6994	0.06	3800	0.7044	0.6893
0.6885	0.07	4000	0.6969	0.6903
0.6887	0.07	4200	0.6916	0.6908
0.6812	0.07	4400	0.6840	0.6917
0.6799	0.08	4600	0.6774	0.6927
0.6672	0.08	4800	0.6718	0.6935
0.6658	0.08	5000	0.6653	0.6939
0.6455	0.09	5200	0.6609	0.6948
0.661	0.09	5400	0.6569	0.6953
0.648	0.09	5600	0.6505	0.6960
0.6453	0.1	5800	0.6458	0.6967
0.6374	0.1	6000	0.6407	0.6973
0.6351	0.1	6200	0.6363	0.6977
0.6273	0.11	6400	0.6328	0.6983
0.6234	0.11	6600	0.6292	0.6987
0.6204	0.12	6800	0.6247	0.6992
0.6179	0.12	7000	0.6217	0.6994
0.6122	0.12	7200	0.6169	0.7001
0.6096	0.13	7400	0.6132	0.7006
0.6046	0.13	7600	0.6101	0.7011
0.5997	0.13	7800	0.6072	0.7016
0.5988	0.14	8000	0.6047	0.7015
0.5995	0.14	8200	0.6011	0.7022
0.6017	0.14	8400	0.5985	0.7024
0.5962	0.15	8600	0.5944	0.7028
0.5857	0.15	8800	0.5919	0.7034
0.5829	0.15	9000	0.5903	0.7034
0.5862	0.16	9200	0.5856	0.7040
0.5786	0.16	9400	0.5834	0.7044
0.5785	0.16	9600	0.5813	0.7044
0.5819	0.17	9800	0.5788	0.7049
0.5804	0.17	10000	0.5768	0.7051
0.5755	0.17	10200	0.5748	0.7053
0.57	0.18	10400	0.5728	0.7057
0.567	0.18	10600	0.5699	0.7059
0.5629	0.18	10800	0.5672	0.7063
0.5615	0.19	11000	0.5648	0.7066
0.5628	0.19	11200	0.5633	0.7067
0.5628	0.19	11400	0.5610	0.7070
0.5551	0.2	11600	0.5588	0.7075
0.5572	0.2	11800	0.5558	0.7078
0.5543	0.2	12000	0.5559	0.7076
0.5512	0.21	12200	0.5536	0.7080
0.5491	0.21	12400	0.5517	0.7081
0.5455	0.21	12600	0.5494	0.7085
0.5494	0.22	12800	0.5480	0.7085
0.5438	0.22	13000	0.5461	0.7087
0.5492	0.22	13200	0.5449	0.7090
0.5385	0.23	13400	0.5432	0.7092
0.5399	0.23	13600	0.5411	0.7094
0.5416	0.23	13800	0.5406	0.7095
0.5316	0.24	14000	0.5379	0.7099
0.5305	0.24	14200	0.5367	0.7102
0.5349	0.24	14400	0.5337	0.7106
0.5313	0.25	14600	0.5329	0.7104
0.5336	0.25	14800	0.5324	0.7107
0.529	0.25	15000	0.5306	0.7107
0.5283	0.26	15200	0.5291	0.7109
0.5241	0.26	15400	0.5277	0.7111
0.5298	0.26	15600	0.5265	0.7113
0.5199	0.27	15800	0.5255	0.7113
0.5303	0.27	16000	0.5237	0.7116
0.5184	0.27	16200	0.5228	0.7118
0.5171	0.28	16400	0.5206	0.7122
0.525	0.28	16600	0.5205	0.7122
0.5191	0.28	16800	0.5191	0.7123
0.5161	0.29	17000	0.5182	0.7124
0.5205	0.29	17200	0.5160	0.7126
0.5157	0.29	17400	0.5156	0.7128
0.5071	0.3	17600	0.5140	0.7129
0.5151	0.3	17800	0.5129	0.7130
0.5127	0.3	18000	0.5124	0.7130
0.5098	0.31	18200	0.5112	0.7133
0.5099	0.31	18400	0.5104	0.7134
0.5056	0.31	18600	0.5084	0.7135
0.5093	0.32	18800	0.5078	0.7138
0.5033	0.32	19000	0.5069	0.7139
0.5013	0.32	19200	0.5063	0.7139
0.5087	0.33	19400	0.5049	0.7140
0.5041	0.33	19600	0.5037	0.7144
0.4994	0.34	19800	0.5035	0.7144
0.5025	0.34	20000	0.5027	0.7144
0.5005	0.34	20200	0.5020	0.7144
0.4972	0.35	20400	0.5012	0.7147
0.5047	0.35	20600	0.5005	0.7145
0.4986	0.35	20800	0.4995	0.7148
0.497	0.36	21000	0.4982	0.7150
0.4986	0.36	21200	0.4971	0.7151
0.4918	0.36	21400	0.4967	0.7152
0.5001	0.37	21600	0.4961	0.7153
0.4934	0.37	21800	0.4952	0.7154
0.4948	0.37	22000	0.4947	0.7155
0.4878	0.38	22200	0.4930	0.7157
0.4913	0.38	22400	0.4926	0.7157
0.487	0.38	22600	0.4921	0.7158
0.4919	0.39	22800	0.4913	0.7158
0.4904	0.39	23000	0.4907	0.7160
0.4863	0.39	23200	0.4903	0.7161
0.4858	0.4	23400	0.4896	0.7160
0.487	0.4	23600	0.4891	0.7163
0.4869	0.4	23800	0.4879	0.7163
0.4851	0.41	24000	0.4869	0.7164
0.4903	0.41	24200	0.4867	0.7164
0.4845	0.41	24400	0.4856	0.7166
0.4797	0.42	24600	0.4852	0.7168
0.4799	0.42	24800	0.4850	0.7168
0.4751	0.42	25000	0.4843	0.7168
0.4745	0.43	25200	0.4836	0.7170
0.4811	0.43	25400	0.4827	0.7170
0.4805	0.43	25600	0.4828	0.7171
0.483	0.44	25800	0.4821	0.7171
0.4825	0.44	26000	0.4815	0.7172
0.4749	0.44	26200	0.4803	0.7173
0.477	0.45	26400	0.4796	0.7174
0.476	0.45	26600	0.4792	0.7176
0.4776	0.45	26800	0.4790	0.7175
0.4811	0.46	27000	0.4780	0.7177
0.4761	0.46	27200	0.4776	0.7177
0.4727	0.46	27400	0.4771	0.7178
0.4737	0.47	27600	0.4761	0.7179
0.4722	0.47	27800	0.4760	0.7180
0.4713	0.47	28000	0.4753	0.7182
0.4711	0.48	28200	0.4747	0.7182
0.4738	0.48	28400	0.4750	0.7182
0.4764	0.48	28600	0.4738	0.7183
0.4725	0.49	28800	0.4727	0.7184
0.468	0.49	29000	0.4728	0.7184
0.4727	0.49	29200	0.4719	0.7185
0.4662	0.5	29400	0.4721	0.7186
0.4655	0.5	29600	0.4711	0.7186
0.4759	0.5	29800	0.4709	0.7187
0.4647	0.51	30000	0.4706	0.7187
0.4738	0.51	30200	0.4703	0.7187
0.4751	0.51	30400	0.4694	0.7190
0.4677	0.52	30600	0.4690	0.7189
0.4605	0.52	30800	0.4687	0.7189
0.466	0.52	31000	0.4686	0.7189
0.4626	0.53	31200	0.4678	0.7191
0.4616	0.53	31400	0.4672	0.7192
0.4698	0.53	31600	0.4665	0.7192
0.4599	0.54	31800	0.4664	0.7193
0.4618	0.54	32000	0.4660	0.7192
0.459	0.55	32200	0.4659	0.7192
0.4608	0.55	32400	0.4654	0.7194
0.4623	0.55	32600	0.4651	0.7194
0.4654	0.56	32800	0.4646	0.7196
0.4585	0.56	33000	0.4638	0.7195
0.4597	0.56	33200	0.4636	0.7196
0.4568	0.57	33400	0.4631	0.7198
0.4634	0.57	33600	0.4630	0.7197
0.4648	0.57	33800	0.4624	0.7197
0.4609	0.58	34000	0.4621	0.7198
0.4619	0.58	34200	0.4620	0.7197
0.4603	0.58	34400	0.4614	0.7199
0.4566	0.59	34600	0.4611	0.7199
0.4581	0.59	34800	0.4604	0.7201
0.4583	0.59	35000	0.4599	0.7202
0.4607	0.6	35200	0.4597	0.7202
0.4533	0.6	35400	0.4592	0.7202
0.4619	0.6	35600	0.4591	0.7202
0.46	0.61	35800	0.4585	0.7203
0.4516	0.61	36000	0.4582	0.7203
0.457	0.61	36200	0.4582	0.7203
0.4544	0.62	36400	0.4576	0.7204
0.4515	0.62	36600	0.4569	0.7205
0.4573	0.62	36800	0.4568	0.7206
0.4517	0.63	37000	0.4565	0.7206
0.4529	0.63	37200	0.4559	0.7207
0.4562	0.63	37400	0.4560	0.7207
0.4586	0.64	37600	0.4556	0.7207
0.4561	0.64	37800	0.4549	0.7208
0.4566	0.64	38000	0.4548	0.7207
0.4487	0.65	38200	0.4545	0.7207
0.452	0.65	38400	0.4542	0.7209
0.4529	0.65	38600	0.4540	0.7209
0.4473	0.66	38800	0.4542	0.7209
0.4479	0.66	39000	0.4533	0.7210
0.4494	0.66	39200	0.4530	0.7211
0.4502	0.67	39400	0.4527	0.7211
0.4496	0.67	39600	0.4523	0.7211
0.4492	0.67	39800	0.4520	0.7213
0.4491	0.68	40000	0.4518	0.7211
0.4499	0.68	40200	0.4514	0.7212
0.4477	0.68	40400	0.4514	0.7213
0.4448	0.69	40600	0.4511	0.7213
0.4526	0.69	40800	0.4506	0.7214
0.4425	0.69	41000	0.4504	0.7214
0.4506	0.7	41200	0.4501	0.7214
0.4492	0.7	41400	0.4498	0.7216
0.4481	0.7	41600	0.4495	0.7215
0.451	0.71	41800	0.4494	0.7216
0.4479	0.71	42000	0.4493	0.7215
0.4546	0.71	42200	0.4489	0.7216
0.4439	0.72	42400	0.4489	0.7217
0.4454	0.72	42600	0.4487	0.7217
0.4508	0.72	42800	0.4484	0.7217
0.448	0.73	43000	0.4483	0.7217
0.447	0.73	43200	0.4479	0.7217
0.4508	0.73	43400	0.4477	0.7217
0.4397	0.74	43600	0.4473	0.7218
0.4453	0.74	43800	0.4473	0.7219
0.4479	0.74	44000	0.4469	0.7219
0.4421	0.75	44200	0.4466	0.7220
0.4479	0.75	44400	0.4464	0.7220
0.4492	0.75	44600	0.4463	0.7220
0.4466	0.76	44800	0.4460	0.7221
0.4543	0.76	45000	0.4458	0.7221
0.4452	0.77	45200	0.4456	0.7221
0.4456	0.77	45400	0.4454	0.7221
0.4455	0.77	45600	0.4452	0.7221
0.4405	0.78	45800	0.4451	0.7221
0.4449	0.78	46000	0.4448	0.7223
0.4433	0.78	46200	0.4447	0.7223
0.445	0.79	46400	0.4447	0.7223
0.447	0.79	46600	0.4444	0.7223
0.4405	0.79	46800	0.4444	0.7222
0.4434	0.8	47000	0.4443	0.7222
0.4385	0.8	47200	0.4440	0.7223
0.442	0.8	47400	0.4439	0.7223
0.4402	0.81	47600	0.4437	0.7224
0.4368	0.81	47800	0.4437	0.7224
0.4392	0.81	48000	0.4435	0.7223
0.439	0.82	48200	0.4434	0.7225
0.4407	0.82	48400	0.4431	0.7225
0.4484	0.82	48600	0.4430	0.7225
0.4419	0.83	48800	0.4430	0.7224
0.4453	0.83	49000	0.4426	0.7225
0.4415	0.83	49200	0.4425	0.7225
0.4424	0.84	49400	0.4425	0.7225
0.4389	0.84	49600	0.4423	0.7226
0.4377	0.84	49800	0.4421	0.7226
0.4388	0.85	50000	0.4420	0.7227
0.4409	0.85	50200	0.4419	0.7225
0.442	0.85	50400	0.4417	0.7227
0.4371	0.86	50600	0.4417	0.7227
0.4384	0.86	50800	0.4415	0.7226
0.4402	0.86	51000	0.4415	0.7227
0.4375	0.87	51200	0.4414	0.7227
0.4367	0.87	51400	0.4413	0.7227
0.4447	0.87	51600	0.4412	0.7227
0.4434	0.88	51800	0.4411	0.7227
0.4357	0.88	52000	0.4411	0.7228
0.4404	0.88	52200	0.4410	0.7228
0.4369	0.89	52400	0.4409	0.7228
0.4348	0.89	52600	0.4409	0.7228
0.4394	0.89	52800	0.4408	0.7227
0.437	0.9	53000	0.4407	0.7227
0.438	0.9	53200	0.4407	0.7228
0.4421	0.9	53400	0.4406	0.7228
0.4421	0.91	53600	0.4405	0.7228
0.4361	0.91	53800	0.4405	0.7228
0.4367	0.91	54000	0.4404	0.7228
0.4371	0.92	54200	0.4403	0.7228
0.4349	0.92	54400	0.4403	0.7229
0.4432	0.92	54600	0.4403	0.7229
0.4355	0.93	54800	0.4402	0.7228
0.4402	0.93	55000	0.4402	0.7229
0.4403	0.93	55200	0.4401	0.7229
0.4445	0.94	55400	0.4401	0.7229
0.4336	0.94	55600	0.4401	0.7228
0.431	0.94	55800	0.4401	0.7229
0.4343	0.95	56000	0.4400	0.7229
0.4298	0.95	56200	0.4400	0.7229
0.43	0.95	56400	0.4400	0.7229
0.4446	0.96	56600	0.4400	0.7229
0.4417	0.96	56800	0.4400	0.7229
0.4431	0.96	57000	0.4400	0.7229
0.4353	0.97	57200	0.4399	0.7229
0.4351	0.97	57400	0.4399	0.7229
0.4398	0.97	57600	0.4399	0.7229
0.4368	0.98	57800	0.4399	0.7229
0.4379	0.98	58000	0.4399	0.7229
0.4353	0.99	58200	0.4399	0.7229
0.4397	0.99	58400	0.4399	0.7229
0.4401	0.99	58600	0.4399	0.7229
0.4366	1.0	58800	0.4399	0.7229
0.434	1.0	59000	0.4399	0.7228

Framework versions

Transformers 4.37.0.dev0
Pytorch 2.1.2+cu121
Datasets 2.15.0
Tokenizers 0.15.0

amazingvince/chess-llama-smol-1024

mini-1024

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

amazingvince/
chess-llama-smol-1024