SimonMA commited on
Commit
cbe60e7
1 Parent(s): 6b09ece

End of training

Browse files
README.md CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.2953
22
 
23
  ## Model description
24
 
@@ -50,169 +50,176 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:------:|:-----:|:---------------:|
53
- | 0.1975 | 2.4942 | 13000 | 0.2857 |
54
- | 0.1754 | 2.5038 | 13050 | 0.2851 |
55
- | 0.1716 | 2.5134 | 13100 | 0.2843 |
56
- | 0.1896 | 2.5230 | 13150 | 0.2843 |
57
- | 0.172 | 2.5326 | 13200 | 0.2849 |
58
- | 0.1967 | 2.5422 | 13250 | 0.2805 |
59
- | 0.1778 | 2.5518 | 13300 | 0.2820 |
60
- | 0.2003 | 2.5614 | 13350 | 0.2818 |
61
- | 0.1669 | 2.5710 | 13400 | 0.2818 |
62
- | 0.1713 | 2.5806 | 13450 | 0.2819 |
63
- | 0.1813 | 2.5902 | 13500 | 0.2826 |
64
- | 0.2075 | 2.5998 | 13550 | 0.2810 |
65
- | 0.1683 | 2.6094 | 13600 | 0.2830 |
66
- | 0.1985 | 2.6190 | 13650 | 0.2819 |
67
- | 0.1759 | 2.6285 | 13700 | 0.2840 |
68
- | 0.1854 | 2.6381 | 13750 | 0.2821 |
69
- | 0.1922 | 2.6477 | 13800 | 0.2824 |
70
- | 0.1707 | 2.6573 | 13850 | 0.2828 |
71
- | 0.1759 | 2.6669 | 13900 | 0.2811 |
72
- | 0.1747 | 2.6765 | 13950 | 0.2814 |
73
- | 0.1965 | 2.6861 | 14000 | 0.2837 |
74
- | 0.1917 | 2.6957 | 14050 | 0.2821 |
75
- | 0.186 | 2.7053 | 14100 | 0.2832 |
76
- | 0.1878 | 2.7149 | 14150 | 0.2823 |
77
- | 0.1906 | 2.7245 | 14200 | 0.2792 |
78
- | 0.1551 | 2.7341 | 14250 | 0.2793 |
79
- | 0.2018 | 2.7437 | 14300 | 0.2779 |
80
- | 0.1939 | 2.7533 | 14350 | 0.2799 |
81
- | 0.1659 | 2.7629 | 14400 | 0.2785 |
82
- | 0.1845 | 2.7724 | 14450 | 0.2783 |
83
- | 0.1727 | 2.7820 | 14500 | 0.2780 |
84
- | 0.1793 | 2.7916 | 14550 | 0.2787 |
85
- | 0.1753 | 2.8012 | 14600 | 0.2780 |
86
- | 0.1857 | 2.8108 | 14650 | 0.2781 |
87
- | 0.1759 | 2.8204 | 14700 | 0.2776 |
88
- | 0.1925 | 2.8300 | 14750 | 0.2769 |
89
- | 0.1666 | 2.8396 | 14800 | 0.2780 |
90
- | 0.2118 | 2.8492 | 14850 | 0.2762 |
91
- | 0.169 | 2.8588 | 14900 | 0.2779 |
92
- | 0.1604 | 2.8684 | 14950 | 0.2765 |
93
- | 0.1746 | 2.8780 | 15000 | 0.2788 |
94
- | 0.1795 | 2.8876 | 15050 | 0.2771 |
95
- | 0.1661 | 2.8972 | 15100 | 0.2799 |
96
- | 0.1893 | 2.9068 | 15150 | 0.2781 |
97
- | 0.1665 | 2.9163 | 15200 | 0.2763 |
98
- | 0.1781 | 2.9259 | 15250 | 0.2768 |
99
- | 0.1634 | 2.9355 | 15300 | 0.2774 |
100
- | 0.1713 | 2.9451 | 15350 | 0.2774 |
101
- | 0.1676 | 2.9547 | 15400 | 0.2774 |
102
- | 0.1927 | 2.9643 | 15450 | 0.2758 |
103
- | 0.1667 | 2.9739 | 15500 | 0.2753 |
104
- | 0.1791 | 2.9835 | 15550 | 0.2755 |
105
- | 0.1817 | 2.9931 | 15600 | 0.2751 |
106
- | 0.1526 | 3.0027 | 15650 | 0.2775 |
107
- | 0.128 | 3.0123 | 15700 | 0.2942 |
108
- | 0.1235 | 3.0219 | 15750 | 0.2959 |
109
- | 0.1385 | 3.0315 | 15800 | 0.2932 |
110
- | 0.1259 | 3.0411 | 15850 | 0.2946 |
111
- | 0.1148 | 3.0507 | 15900 | 0.2958 |
112
- | 0.121 | 3.0602 | 15950 | 0.2957 |
113
- | 0.1137 | 3.0698 | 16000 | 0.2982 |
114
- | 0.1181 | 3.0794 | 16050 | 0.2982 |
115
- | 0.1185 | 3.0890 | 16100 | 0.2949 |
116
- | 0.1254 | 3.0986 | 16150 | 0.2965 |
117
- | 0.1261 | 3.1082 | 16200 | 0.2965 |
118
- | 0.1202 | 3.1178 | 16250 | 0.3008 |
119
- | 0.1151 | 3.1274 | 16300 | 0.2980 |
120
- | 0.1284 | 3.1370 | 16350 | 0.2976 |
121
- | 0.1353 | 3.1466 | 16400 | 0.2961 |
122
- | 0.1149 | 3.1562 | 16450 | 0.2995 |
123
- | 0.1254 | 3.1658 | 16500 | 0.3002 |
124
- | 0.1318 | 3.1754 | 16550 | 0.2975 |
125
- | 0.1289 | 3.1850 | 16600 | 0.2955 |
126
- | 0.1286 | 3.1946 | 16650 | 0.3016 |
127
- | 0.1104 | 3.2041 | 16700 | 0.2981 |
128
- | 0.1087 | 3.2137 | 16750 | 0.2984 |
129
- | 0.1325 | 3.2233 | 16800 | 0.2953 |
130
- | 0.113 | 3.2329 | 16850 | 0.2972 |
131
- | 0.1335 | 3.2425 | 16900 | 0.2984 |
132
- | 0.1189 | 3.2521 | 16950 | 0.2981 |
133
- | 0.1177 | 3.2617 | 17000 | 0.3003 |
134
- | 0.1065 | 3.2713 | 17050 | 0.2980 |
135
- | 0.1262 | 3.2809 | 17100 | 0.2970 |
136
- | 0.1248 | 3.2905 | 17150 | 0.2972 |
137
- | 0.1229 | 3.3001 | 17200 | 0.2961 |
138
- | 0.1339 | 3.3097 | 17250 | 0.2953 |
139
- | 0.1216 | 3.3193 | 17300 | 0.2984 |
140
- | 0.1239 | 3.3289 | 17350 | 0.2974 |
141
- | 0.1182 | 3.3384 | 17400 | 0.2956 |
142
- | 0.1237 | 3.3480 | 17450 | 0.2967 |
143
- | 0.1208 | 3.3576 | 17500 | 0.2973 |
144
- | 0.1378 | 3.3672 | 17550 | 0.2994 |
145
- | 0.1199 | 3.3768 | 17600 | 0.2975 |
146
- | 0.1295 | 3.3864 | 17650 | 0.2990 |
147
- | 0.127 | 3.3960 | 17700 | 0.2985 |
148
- | 0.129 | 3.4056 | 17750 | 0.3004 |
149
- | 0.1227 | 3.4152 | 17800 | 0.2993 |
150
- | 0.1188 | 3.4248 | 17850 | 0.2994 |
151
- | 0.1243 | 3.4344 | 17900 | 0.2992 |
152
- | 0.1246 | 3.4440 | 17950 | 0.2973 |
153
- | 0.1252 | 3.4536 | 18000 | 0.2989 |
154
- | 0.128 | 3.4632 | 18050 | 0.2976 |
155
- | 0.1359 | 3.4728 | 18100 | 0.2966 |
156
- | 0.1194 | 3.4823 | 18150 | 0.2959 |
157
- | 0.1213 | 3.4919 | 18200 | 0.2964 |
158
- | 0.1161 | 3.5015 | 18250 | 0.2965 |
159
- | 0.1209 | 3.5111 | 18300 | 0.2974 |
160
- | 0.1255 | 3.5207 | 18350 | 0.2955 |
161
- | 0.1319 | 3.5303 | 18400 | 0.2965 |
162
- | 0.118 | 3.5399 | 18450 | 0.2990 |
163
- | 0.1317 | 3.5495 | 18500 | 0.2964 |
164
- | 0.1302 | 3.5591 | 18550 | 0.2956 |
165
- | 0.1289 | 3.5687 | 18600 | 0.2968 |
166
- | 0.1363 | 3.5783 | 18650 | 0.2959 |
167
- | 0.1301 | 3.5879 | 18700 | 0.2954 |
168
- | 0.123 | 3.5975 | 18750 | 0.2969 |
169
- | 0.1189 | 3.6071 | 18800 | 0.2969 |
170
- | 0.1151 | 3.6167 | 18850 | 0.2951 |
171
- | 0.1296 | 3.6262 | 18900 | 0.2963 |
172
- | 0.1264 | 3.6358 | 18950 | 0.2958 |
173
- | 0.1151 | 3.6454 | 19000 | 0.2967 |
174
- | 0.1193 | 3.6550 | 19050 | 0.2974 |
175
- | 0.13 | 3.6646 | 19100 | 0.2962 |
176
- | 0.1324 | 3.6742 | 19150 | 0.2956 |
177
- | 0.1126 | 3.6838 | 19200 | 0.2975 |
178
- | 0.1223 | 3.6934 | 19250 | 0.2965 |
179
- | 0.1257 | 3.7030 | 19300 | 0.2970 |
180
- | 0.1236 | 3.7126 | 19350 | 0.2976 |
181
- | 0.1255 | 3.7222 | 19400 | 0.2970 |
182
- | 0.1174 | 3.7318 | 19450 | 0.2974 |
183
- | 0.1256 | 3.7414 | 19500 | 0.2966 |
184
- | 0.1131 | 3.7510 | 19550 | 0.2971 |
185
- | 0.1296 | 3.7606 | 19600 | 0.2961 |
186
- | 0.1291 | 3.7701 | 19650 | 0.2947 |
187
- | 0.1232 | 3.7797 | 19700 | 0.2951 |
188
- | 0.1257 | 3.7893 | 19750 | 0.2958 |
189
- | 0.1123 | 3.7989 | 19800 | 0.2954 |
190
- | 0.1234 | 3.8085 | 19850 | 0.2952 |
191
- | 0.1224 | 3.8181 | 19900 | 0.2951 |
192
- | 0.1125 | 3.8277 | 19950 | 0.2960 |
193
- | 0.1349 | 3.8373 | 20000 | 0.2951 |
194
- | 0.1274 | 3.8469 | 20050 | 0.2950 |
195
- | 0.1169 | 3.8565 | 20100 | 0.2948 |
196
- | 0.1202 | 3.8661 | 20150 | 0.2953 |
197
- | 0.1239 | 3.8757 | 20200 | 0.2960 |
198
- | 0.1237 | 3.8853 | 20250 | 0.2956 |
199
- | 0.1126 | 3.8949 | 20300 | 0.2957 |
200
- | 0.121 | 3.9045 | 20350 | 0.2956 |
201
- | 0.1319 | 3.9140 | 20400 | 0.2953 |
202
- | 0.1274 | 3.9236 | 20450 | 0.2952 |
203
- | 0.116 | 3.9332 | 20500 | 0.2951 |
204
- | 0.1189 | 3.9428 | 20550 | 0.2953 |
205
- | 0.1224 | 3.9524 | 20600 | 0.2956 |
206
- | 0.1133 | 3.9620 | 20650 | 0.2958 |
207
- | 0.1216 | 3.9716 | 20700 | 0.2956 |
208
- | 0.1229 | 3.9812 | 20750 | 0.2954 |
209
- | 0.1228 | 3.9908 | 20800 | 0.2953 |
 
 
 
 
 
 
 
210
 
211
 
212
  ### Framework versions
213
 
214
  - PEFT 0.12.0
215
  - Transformers 4.44.2
216
- - Pytorch 2.3.1+cu121
217
  - Datasets 2.21.0
218
  - Tokenizers 0.19.1
 
18
 
19
  This model is a fine-tuned version of [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.2938
22
 
23
  ## Model description
24
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:------:|:-----:|:---------------:|
53
+ | 0.1795 | 2.4565 | 13000 | 0.2835 |
54
+ | 0.2185 | 2.4660 | 13050 | 0.2829 |
55
+ | 0.1948 | 2.4754 | 13100 | 0.2828 |
56
+ | 0.1612 | 2.4849 | 13150 | 0.2845 |
57
+ | 0.2074 | 2.4943 | 13200 | 0.2827 |
58
+ | 0.1684 | 2.5038 | 13250 | 0.2830 |
59
+ | 0.2004 | 2.5132 | 13300 | 0.2826 |
60
+ | 0.2073 | 2.5227 | 13350 | 0.2817 |
61
+ | 0.1693 | 2.5321 | 13400 | 0.2837 |
62
+ | 0.187 | 2.5416 | 13450 | 0.2826 |
63
+ | 0.1777 | 2.5510 | 13500 | 0.2829 |
64
+ | 0.1765 | 2.5605 | 13550 | 0.2847 |
65
+ | 0.1831 | 2.5699 | 13600 | 0.2837 |
66
+ | 0.1866 | 2.5794 | 13650 | 0.2818 |
67
+ | 0.1718 | 2.5888 | 13700 | 0.2815 |
68
+ | 0.197 | 2.5983 | 13750 | 0.2809 |
69
+ | 0.1847 | 2.6077 | 13800 | 0.2830 |
70
+ | 0.1868 | 2.6172 | 13850 | 0.2833 |
71
+ | 0.1825 | 2.6266 | 13900 | 0.2824 |
72
+ | 0.1887 | 2.6361 | 13950 | 0.2822 |
73
+ | 0.1747 | 2.6455 | 14000 | 0.2817 |
74
+ | 0.201 | 2.6550 | 14050 | 0.2800 |
75
+ | 0.163 | 2.6644 | 14100 | 0.2810 |
76
+ | 0.1754 | 2.6738 | 14150 | 0.2791 |
77
+ | 0.1724 | 2.6833 | 14200 | 0.2820 |
78
+ | 0.184 | 2.6927 | 14250 | 0.2798 |
79
+ | 0.1743 | 2.7022 | 14300 | 0.2804 |
80
+ | 0.194 | 2.7116 | 14350 | 0.2799 |
81
+ | 0.1736 | 2.7211 | 14400 | 0.2814 |
82
+ | 0.1837 | 2.7305 | 14450 | 0.2783 |
83
+ | 0.1809 | 2.7400 | 14500 | 0.2808 |
84
+ | 0.187 | 2.7494 | 14550 | 0.2796 |
85
+ | 0.1858 | 2.7589 | 14600 | 0.2773 |
86
+ | 0.1946 | 2.7683 | 14650 | 0.2783 |
87
+ | 0.1878 | 2.7778 | 14700 | 0.2779 |
88
+ | 0.1824 | 2.7872 | 14750 | 0.2778 |
89
+ | 0.1829 | 2.7967 | 14800 | 0.2782 |
90
+ | 0.1962 | 2.8061 | 14850 | 0.2787 |
91
+ | 0.1802 | 2.8156 | 14900 | 0.2769 |
92
+ | 0.1768 | 2.8250 | 14950 | 0.2771 |
93
+ | 0.1765 | 2.8345 | 15000 | 0.2788 |
94
+ | 0.1884 | 2.8439 | 15050 | 0.2787 |
95
+ | 0.2086 | 2.8534 | 15100 | 0.2769 |
96
+ | 0.1665 | 2.8628 | 15150 | 0.2784 |
97
+ | 0.1569 | 2.8723 | 15200 | 0.2776 |
98
+ | 0.1683 | 2.8817 | 15250 | 0.2763 |
99
+ | 0.1658 | 2.8912 | 15300 | 0.2774 |
100
+ | 0.1846 | 2.9006 | 15350 | 0.2772 |
101
+ | 0.1937 | 2.9101 | 15400 | 0.2758 |
102
+ | 0.1819 | 2.9195 | 15450 | 0.2770 |
103
+ | 0.1718 | 2.9289 | 15500 | 0.2745 |
104
+ | 0.1647 | 2.9384 | 15550 | 0.2774 |
105
+ | 0.1565 | 2.9478 | 15600 | 0.2775 |
106
+ | 0.1793 | 2.9573 | 15650 | 0.2770 |
107
+ | 0.198 | 2.9667 | 15700 | 0.2760 |
108
+ | 0.182 | 2.9762 | 15750 | 0.2775 |
109
+ | 0.1586 | 2.9856 | 15800 | 0.2761 |
110
+ | 0.2008 | 2.9951 | 15850 | 0.2748 |
111
+ | 0.1392 | 3.0045 | 15900 | 0.2858 |
112
+ | 0.1225 | 3.0140 | 15950 | 0.2975 |
113
+ | 0.1282 | 3.0234 | 16000 | 0.2953 |
114
+ | 0.1247 | 3.0329 | 16050 | 0.2928 |
115
+ | 0.1178 | 3.0423 | 16100 | 0.2962 |
116
+ | 0.111 | 3.0518 | 16150 | 0.2998 |
117
+ | 0.1197 | 3.0612 | 16200 | 0.2979 |
118
+ | 0.1164 | 3.0707 | 16250 | 0.2964 |
119
+ | 0.1208 | 3.0801 | 16300 | 0.2977 |
120
+ | 0.1351 | 3.0896 | 16350 | 0.2984 |
121
+ | 0.1355 | 3.0990 | 16400 | 0.2973 |
122
+ | 0.1219 | 3.1085 | 16450 | 0.2948 |
123
+ | 0.1241 | 3.1179 | 16500 | 0.2952 |
124
+ | 0.1293 | 3.1274 | 16550 | 0.2976 |
125
+ | 0.1208 | 3.1368 | 16600 | 0.2963 |
126
+ | 0.1327 | 3.1463 | 16650 | 0.2973 |
127
+ | 0.122 | 3.1557 | 16700 | 0.2963 |
128
+ | 0.1269 | 3.1652 | 16750 | 0.2960 |
129
+ | 0.1239 | 3.1746 | 16800 | 0.2954 |
130
+ | 0.1138 | 3.1841 | 16850 | 0.2961 |
131
+ | 0.1226 | 3.1935 | 16900 | 0.2942 |
132
+ | 0.1196 | 3.2029 | 16950 | 0.2971 |
133
+ | 0.1307 | 3.2124 | 17000 | 0.2949 |
134
+ | 0.1166 | 3.2218 | 17050 | 0.2955 |
135
+ | 0.1369 | 3.2313 | 17100 | 0.2986 |
136
+ | 0.1132 | 3.2407 | 17150 | 0.2969 |
137
+ | 0.126 | 3.2502 | 17200 | 0.2944 |
138
+ | 0.1234 | 3.2596 | 17250 | 0.2955 |
139
+ | 0.1237 | 3.2691 | 17300 | 0.2966 |
140
+ | 0.1214 | 3.2785 | 17350 | 0.2943 |
141
+ | 0.1287 | 3.2880 | 17400 | 0.2981 |
142
+ | 0.1286 | 3.2974 | 17450 | 0.2955 |
143
+ | 0.1279 | 3.3069 | 17500 | 0.2952 |
144
+ | 0.1236 | 3.3163 | 17550 | 0.2958 |
145
+ | 0.1242 | 3.3258 | 17600 | 0.2951 |
146
+ | 0.12 | 3.3352 | 17650 | 0.2968 |
147
+ | 0.1188 | 3.3447 | 17700 | 0.2951 |
148
+ | 0.1273 | 3.3541 | 17750 | 0.2968 |
149
+ | 0.1206 | 3.3636 | 17800 | 0.2982 |
150
+ | 0.1281 | 3.3730 | 17850 | 0.2952 |
151
+ | 0.1228 | 3.3825 | 17900 | 0.2964 |
152
+ | 0.1277 | 3.3919 | 17950 | 0.2964 |
153
+ | 0.1347 | 3.4014 | 18000 | 0.2958 |
154
+ | 0.1345 | 3.4108 | 18050 | 0.2942 |
155
+ | 0.1248 | 3.4203 | 18100 | 0.2976 |
156
+ | 0.1388 | 3.4297 | 18150 | 0.2966 |
157
+ | 0.1337 | 3.4392 | 18200 | 0.2942 |
158
+ | 0.1175 | 3.4486 | 18250 | 0.2963 |
159
+ | 0.1214 | 3.4580 | 18300 | 0.2969 |
160
+ | 0.1331 | 3.4675 | 18350 | 0.2967 |
161
+ | 0.1274 | 3.4769 | 18400 | 0.2955 |
162
+ | 0.1295 | 3.4864 | 18450 | 0.2963 |
163
+ | 0.1325 | 3.4958 | 18500 | 0.2957 |
164
+ | 0.1199 | 3.5053 | 18550 | 0.2965 |
165
+ | 0.1232 | 3.5147 | 18600 | 0.2941 |
166
+ | 0.11 | 3.5242 | 18650 | 0.2949 |
167
+ | 0.1238 | 3.5336 | 18700 | 0.2947 |
168
+ | 0.13 | 3.5431 | 18750 | 0.2960 |
169
+ | 0.1123 | 3.5525 | 18800 | 0.2955 |
170
+ | 0.1214 | 3.5620 | 18850 | 0.2954 |
171
+ | 0.1206 | 3.5714 | 18900 | 0.2954 |
172
+ | 0.1312 | 3.5809 | 18950 | 0.2933 |
173
+ | 0.1166 | 3.5903 | 19000 | 0.2933 |
174
+ | 0.1261 | 3.5998 | 19050 | 0.2942 |
175
+ | 0.1237 | 3.6092 | 19100 | 0.2956 |
176
+ | 0.1229 | 3.6187 | 19150 | 0.2950 |
177
+ | 0.1264 | 3.6281 | 19200 | 0.2941 |
178
+ | 0.1161 | 3.6376 | 19250 | 0.2949 |
179
+ | 0.1159 | 3.6470 | 19300 | 0.2954 |
180
+ | 0.1176 | 3.6565 | 19350 | 0.2967 |
181
+ | 0.1157 | 3.6659 | 19400 | 0.2959 |
182
+ | 0.1209 | 3.6754 | 19450 | 0.2952 |
183
+ | 0.1146 | 3.6848 | 19500 | 0.2956 |
184
+ | 0.115 | 3.6943 | 19550 | 0.2950 |
185
+ | 0.1285 | 3.7037 | 19600 | 0.2938 |
186
+ | 0.1174 | 3.7132 | 19650 | 0.2950 |
187
+ | 0.1279 | 3.7226 | 19700 | 0.2951 |
188
+ | 0.1156 | 3.7320 | 19750 | 0.2951 |
189
+ | 0.121 | 3.7415 | 19800 | 0.2950 |
190
+ | 0.1146 | 3.7509 | 19850 | 0.2958 |
191
+ | 0.1254 | 3.7604 | 19900 | 0.2965 |
192
+ | 0.1232 | 3.7698 | 19950 | 0.2944 |
193
+ | 0.1165 | 3.7793 | 20000 | 0.2960 |
194
+ | 0.1173 | 3.7887 | 20050 | 0.2970 |
195
+ | 0.119 | 3.7982 | 20100 | 0.2963 |
196
+ | 0.13 | 3.8076 | 20150 | 0.2952 |
197
+ | 0.1229 | 3.8171 | 20200 | 0.2954 |
198
+ | 0.1157 | 3.8265 | 20250 | 0.2957 |
199
+ | 0.1176 | 3.8360 | 20300 | 0.2944 |
200
+ | 0.1226 | 3.8454 | 20350 | 0.2940 |
201
+ | 0.1147 | 3.8549 | 20400 | 0.2944 |
202
+ | 0.1285 | 3.8643 | 20450 | 0.2944 |
203
+ | 0.1241 | 3.8738 | 20500 | 0.2939 |
204
+ | 0.119 | 3.8832 | 20550 | 0.2941 |
205
+ | 0.1119 | 3.8927 | 20600 | 0.2946 |
206
+ | 0.1159 | 3.9021 | 20650 | 0.2944 |
207
+ | 0.1282 | 3.9116 | 20700 | 0.2943 |
208
+ | 0.1202 | 3.9210 | 20750 | 0.2939 |
209
+ | 0.1202 | 3.9305 | 20800 | 0.2940 |
210
+ | 0.1264 | 3.9399 | 20850 | 0.2941 |
211
+ | 0.13 | 3.9494 | 20900 | 0.2940 |
212
+ | 0.1146 | 3.9588 | 20950 | 0.2938 |
213
+ | 0.1222 | 3.9683 | 21000 | 0.2937 |
214
+ | 0.1225 | 3.9777 | 21050 | 0.2937 |
215
+ | 0.1189 | 3.9872 | 21100 | 0.2938 |
216
+ | 0.1181 | 3.9966 | 21150 | 0.2938 |
217
 
218
 
219
  ### Framework versions
220
 
221
  - PEFT 0.12.0
222
  - Transformers 4.44.2
223
+ - Pytorch 2.4.0+cu121
224
  - Datasets 2.21.0
225
  - Tokenizers 0.19.1
adapter_config.json CHANGED
@@ -21,12 +21,12 @@
21
  "revision": null,
22
  "target_modules": [
23
  "q_proj",
24
- "v_proj",
25
- "up_proj",
26
  "o_proj",
27
- "k_proj",
28
  "down_proj",
29
- "gate_proj"
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
21
  "revision": null,
22
  "target_modules": [
23
  "q_proj",
 
 
24
  "o_proj",
25
+ "up_proj",
26
  "down_proj",
27
+ "k_proj",
28
+ "gate_proj",
29
+ "v_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e60e7dad8f622e1f7b8f479a1503a619945de512d8cdaa0355818d6d2dd3f074
3
  size 2332095256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cd009a8257e9b9b5fa6ac606fdd53693a69e452d0478fe887e1ab9a883915bb
3
  size 2332095256
runs/Sep02_06-31-53_127b607224fc/events.out.tfevents.1725258724.127b607224fc.1097.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dbfc07d8abc9d88b1b5909f077f3bb573c8e7d25cfb69f890fe2818bf337f01
3
+ size 140783
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:456334575237d727227a0b4fc8a586c5cd0f18ae5d588a52aa6f356fc5d53410
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61c807f9b2a369f918ad5be9d53dedd123954997deba0bbf897ff305686599c6
3
  size 5496