SimonMA commited on
Commit
109dca6
1 Parent(s): aa6e169

End of training

Browse files
README.md CHANGED
@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # Codellama-7b-lora-rps-adapter
18
 
19
- This model is a fine-tuned version of [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.2971
22
 
23
  ## Model description
24
 
@@ -50,210 +50,420 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:-----:|:---------------:|
53
- | 0.2892 | 3.41 | 13000 | 0.3005 |
54
- | 0.2816 | 3.42 | 13050 | 0.2992 |
55
- | 0.2564 | 3.44 | 13100 | 0.2995 |
56
- | 0.2596 | 3.45 | 13150 | 0.2997 |
57
- | 0.3176 | 3.46 | 13200 | 0.2995 |
58
- | 0.2509 | 3.48 | 13250 | 0.2992 |
59
- | 0.3033 | 3.49 | 13300 | 0.2983 |
60
- | 0.2797 | 3.5 | 13350 | 0.2991 |
61
- | 0.2555 | 3.52 | 13400 | 0.2989 |
62
- | 0.2821 | 3.53 | 13450 | 0.2984 |
63
- | 0.2697 | 3.54 | 13500 | 0.2976 |
64
- | 0.2505 | 3.56 | 13550 | 0.2982 |
65
- | 0.2696 | 3.57 | 13600 | 0.2985 |
66
- | 0.2698 | 3.58 | 13650 | 0.2973 |
67
- | 0.2966 | 3.59 | 13700 | 0.2981 |
68
- | 0.2468 | 3.61 | 13750 | 0.2967 |
69
- | 0.2878 | 3.62 | 13800 | 0.2969 |
70
- | 0.2876 | 3.63 | 13850 | 0.2984 |
71
- | 0.2584 | 3.65 | 13900 | 0.2973 |
72
- | 0.2677 | 3.66 | 13950 | 0.2975 |
73
- | 0.2923 | 3.67 | 14000 | 0.2969 |
74
- | 0.2643 | 3.69 | 14050 | 0.2968 |
75
- | 0.2673 | 3.7 | 14100 | 0.2982 |
76
- | 0.3016 | 3.71 | 14150 | 0.2967 |
77
- | 0.2707 | 3.73 | 14200 | 0.2968 |
78
- | 0.2606 | 3.74 | 14250 | 0.2976 |
79
- | 0.2957 | 3.75 | 14300 | 0.2963 |
80
- | 0.2509 | 3.77 | 14350 | 0.2965 |
81
- | 0.2713 | 3.78 | 14400 | 0.2950 |
82
- | 0.3041 | 3.79 | 14450 | 0.2968 |
83
- | 0.265 | 3.8 | 14500 | 0.2953 |
84
- | 0.2726 | 3.82 | 14550 | 0.2955 |
85
- | 0.2671 | 3.83 | 14600 | 0.2957 |
86
- | 0.2674 | 3.84 | 14650 | 0.2952 |
87
- | 0.2516 | 3.86 | 14700 | 0.2959 |
88
- | 0.2535 | 3.87 | 14750 | 0.2944 |
89
- | 0.2452 | 3.88 | 14800 | 0.2945 |
90
- | 0.2733 | 3.9 | 14850 | 0.2945 |
91
- | 0.2718 | 3.91 | 14900 | 0.2947 |
92
- | 0.257 | 3.92 | 14950 | 0.2939 |
93
- | 0.2418 | 3.94 | 15000 | 0.2946 |
94
- | 0.2583 | 3.95 | 15050 | 0.2949 |
95
- | 0.3093 | 3.96 | 15100 | 0.2939 |
96
- | 0.2501 | 3.98 | 15150 | 0.2937 |
97
- | 0.2715 | 3.99 | 15200 | 0.2935 |
98
- | 0.3209 | 4.0 | 15250 | 0.2930 |
99
- | 0.2655 | 4.01 | 15300 | 0.2964 |
100
- | 0.2531 | 4.03 | 15350 | 0.2963 |
101
- | 0.2417 | 4.04 | 15400 | 0.2967 |
102
- | 0.2574 | 4.05 | 15450 | 0.2956 |
103
- | 0.2738 | 4.07 | 15500 | 0.2980 |
104
- | 0.2488 | 4.08 | 15550 | 0.2967 |
105
- | 0.2243 | 4.09 | 15600 | 0.2976 |
106
- | 0.2414 | 4.11 | 15650 | 0.2987 |
107
- | 0.2318 | 4.12 | 15700 | 0.2978 |
108
- | 0.2428 | 4.13 | 15750 | 0.2963 |
109
- | 0.2464 | 4.15 | 15800 | 0.3004 |
110
- | 0.2717 | 4.16 | 15850 | 0.2971 |
111
- | 0.2233 | 4.17 | 15900 | 0.2977 |
112
- | 0.2308 | 4.19 | 15950 | 0.2980 |
113
- | 0.2387 | 4.2 | 16000 | 0.2967 |
114
- | 0.2305 | 4.21 | 16050 | 0.2980 |
115
- | 0.2537 | 4.22 | 16100 | 0.2974 |
116
- | 0.2893 | 4.24 | 16150 | 0.2974 |
117
- | 0.2403 | 4.25 | 16200 | 0.2987 |
118
- | 0.218 | 4.26 | 16250 | 0.2970 |
119
- | 0.2447 | 4.28 | 16300 | 0.2963 |
120
- | 0.2334 | 4.29 | 16350 | 0.2975 |
121
- | 0.2481 | 4.3 | 16400 | 0.2980 |
122
- | 0.2374 | 4.32 | 16450 | 0.2986 |
123
- | 0.2207 | 4.33 | 16500 | 0.2968 |
124
- | 0.2746 | 4.34 | 16550 | 0.2968 |
125
- | 0.2262 | 4.36 | 16600 | 0.2962 |
126
- | 0.2625 | 4.37 | 16650 | 0.2966 |
127
- | 0.2946 | 4.38 | 16700 | 0.2969 |
128
- | 0.2745 | 4.4 | 16750 | 0.2990 |
129
- | 0.2418 | 4.41 | 16800 | 0.2973 |
130
- | 0.2501 | 4.42 | 16850 | 0.2964 |
131
- | 0.2295 | 4.43 | 16900 | 0.2970 |
132
- | 0.2558 | 4.45 | 16950 | 0.2966 |
133
- | 0.2577 | 4.46 | 17000 | 0.2967 |
134
- | 0.2307 | 4.47 | 17050 | 0.2965 |
135
- | 0.2276 | 4.49 | 17100 | 0.2965 |
136
- | 0.2574 | 4.5 | 17150 | 0.2963 |
137
- | 0.2668 | 4.51 | 17200 | 0.2956 |
138
- | 0.2327 | 4.53 | 17250 | 0.2977 |
139
- | 0.254 | 4.54 | 17300 | 0.2951 |
140
- | 0.2511 | 4.55 | 17350 | 0.2949 |
141
- | 0.2176 | 4.57 | 17400 | 0.2953 |
142
- | 0.2294 | 4.58 | 17450 | 0.2962 |
143
- | 0.2588 | 4.59 | 17500 | 0.2951 |
144
- | 0.2903 | 4.61 | 17550 | 0.2946 |
145
- | 0.2326 | 4.62 | 17600 | 0.2946 |
146
- | 0.2508 | 4.63 | 17650 | 0.2945 |
147
- | 0.251 | 4.64 | 17700 | 0.2949 |
148
- | 0.2281 | 4.66 | 17750 | 0.2954 |
149
- | 0.2265 | 4.67 | 17800 | 0.2958 |
150
- | 0.23 | 4.68 | 17850 | 0.2955 |
151
- | 0.2489 | 4.7 | 17900 | 0.2946 |
152
- | 0.2373 | 4.71 | 17950 | 0.2945 |
153
- | 0.2365 | 4.72 | 18000 | 0.2948 |
154
- | 0.245 | 4.74 | 18050 | 0.2941 |
155
- | 0.2597 | 4.75 | 18100 | 0.2949 |
156
- | 0.2325 | 4.76 | 18150 | 0.2946 |
157
- | 0.2495 | 4.78 | 18200 | 0.2946 |
158
- | 0.2583 | 4.79 | 18250 | 0.2949 |
159
- | 0.2162 | 4.8 | 18300 | 0.2945 |
160
- | 0.2292 | 4.82 | 18350 | 0.2941 |
161
- | 0.2695 | 4.83 | 18400 | 0.2943 |
162
- | 0.2602 | 4.84 | 18450 | 0.2934 |
163
- | 0.2179 | 4.85 | 18500 | 0.2947 |
164
- | 0.2356 | 4.87 | 18550 | 0.2930 |
165
- | 0.2692 | 4.88 | 18600 | 0.2936 |
166
- | 0.2627 | 4.89 | 18650 | 0.2935 |
167
- | 0.2476 | 4.91 | 18700 | 0.2947 |
168
- | 0.2529 | 4.92 | 18750 | 0.2924 |
169
- | 0.2358 | 4.93 | 18800 | 0.2920 |
170
- | 0.232 | 4.95 | 18850 | 0.2930 |
171
- | 0.2439 | 4.96 | 18900 | 0.2928 |
172
- | 0.2355 | 4.97 | 18950 | 0.2926 |
173
- | 0.2489 | 4.99 | 19000 | 0.2926 |
174
- | 0.2777 | 5.0 | 19050 | 0.2924 |
175
- | 0.2384 | 5.01 | 19100 | 0.2976 |
176
- | 0.2201 | 5.02 | 19150 | 0.2990 |
177
- | 0.2065 | 5.04 | 19200 | 0.2976 |
178
- | 0.2138 | 5.05 | 19250 | 0.2963 |
179
- | 0.2367 | 5.06 | 19300 | 0.2973 |
180
- | 0.2319 | 5.08 | 19350 | 0.2985 |
181
- | 0.2199 | 5.09 | 19400 | 0.2991 |
182
- | 0.212 | 5.1 | 19450 | 0.2989 |
183
- | 0.2085 | 5.12 | 19500 | 0.2983 |
184
- | 0.1995 | 5.13 | 19550 | 0.2986 |
185
- | 0.2333 | 5.14 | 19600 | 0.2979 |
186
- | 0.2286 | 5.16 | 19650 | 0.2989 |
187
- | 0.215 | 5.17 | 19700 | 0.2977 |
188
- | 0.2417 | 5.18 | 19750 | 0.2977 |
189
- | 0.211 | 5.2 | 19800 | 0.2983 |
190
- | 0.2132 | 5.21 | 19850 | 0.2996 |
191
- | 0.2079 | 5.22 | 19900 | 0.3001 |
192
- | 0.2022 | 5.23 | 19950 | 0.2988 |
193
- | 0.2178 | 5.25 | 20000 | 0.2989 |
194
- | 0.1975 | 5.26 | 20050 | 0.2992 |
195
- | 0.245 | 5.27 | 20100 | 0.2979 |
196
- | 0.256 | 5.29 | 20150 | 0.2988 |
197
- | 0.2355 | 5.3 | 20200 | 0.3005 |
198
- | 0.2018 | 5.31 | 20250 | 0.3001 |
199
- | 0.2078 | 5.33 | 20300 | 0.2986 |
200
- | 0.2128 | 5.34 | 20350 | 0.2997 |
201
- | 0.2202 | 5.35 | 20400 | 0.2979 |
202
- | 0.2311 | 5.37 | 20450 | 0.2988 |
203
- | 0.2374 | 5.38 | 20500 | 0.2980 |
204
- | 0.2617 | 5.39 | 20550 | 0.2975 |
205
- | 0.2082 | 5.41 | 20600 | 0.2985 |
206
- | 0.2531 | 5.42 | 20650 | 0.2984 |
207
- | 0.2103 | 5.43 | 20700 | 0.2979 |
208
- | 0.2569 | 5.44 | 20750 | 0.2990 |
209
- | 0.2254 | 5.46 | 20800 | 0.2977 |
210
- | 0.2328 | 5.47 | 20850 | 0.2971 |
211
- | 0.2162 | 5.48 | 20900 | 0.2981 |
212
- | 0.2373 | 5.5 | 20950 | 0.2977 |
213
- | 0.2447 | 5.51 | 21000 | 0.2972 |
214
- | 0.2131 | 5.52 | 21050 | 0.2976 |
215
- | 0.2355 | 5.54 | 21100 | 0.2983 |
216
- | 0.2327 | 5.55 | 21150 | 0.2977 |
217
- | 0.2601 | 5.56 | 21200 | 0.2970 |
218
- | 0.2074 | 5.58 | 21250 | 0.2977 |
219
- | 0.2153 | 5.59 | 21300 | 0.2969 |
220
- | 0.2072 | 5.6 | 21350 | 0.2975 |
221
- | 0.2162 | 5.62 | 21400 | 0.2971 |
222
- | 0.2399 | 5.63 | 21450 | 0.2969 |
223
- | 0.2248 | 5.64 | 21500 | 0.2974 |
224
- | 0.2608 | 5.65 | 21550 | 0.2973 |
225
- | 0.2322 | 5.67 | 21600 | 0.2974 |
226
- | 0.2283 | 5.68 | 21650 | 0.2983 |
227
- | 0.1931 | 5.69 | 21700 | 0.2986 |
228
- | 0.2341 | 5.71 | 21750 | 0.2981 |
229
- | 0.2318 | 5.72 | 21800 | 0.2979 |
230
- | 0.223 | 5.73 | 21850 | 0.2974 |
231
- | 0.2075 | 5.75 | 21900 | 0.2974 |
232
- | 0.2277 | 5.76 | 21950 | 0.2975 |
233
- | 0.2167 | 5.77 | 22000 | 0.2976 |
234
- | 0.1904 | 5.79 | 22050 | 0.2975 |
235
- | 0.2049 | 5.8 | 22100 | 0.2974 |
236
- | 0.2207 | 5.81 | 22150 | 0.2976 |
237
- | 0.2017 | 5.83 | 22200 | 0.2972 |
238
- | 0.2068 | 5.84 | 22250 | 0.2972 |
239
- | 0.2453 | 5.85 | 22300 | 0.2967 |
240
- | 0.2121 | 5.86 | 22350 | 0.2968 |
241
- | 0.2193 | 5.88 | 22400 | 0.2971 |
242
- | 0.2337 | 5.89 | 22450 | 0.2971 |
243
- | 0.227 | 5.9 | 22500 | 0.2971 |
244
- | 0.2285 | 5.92 | 22550 | 0.2972 |
245
- | 0.2141 | 5.93 | 22600 | 0.2974 |
246
- | 0.2269 | 5.94 | 22650 | 0.2971 |
247
- | 0.2192 | 5.96 | 22700 | 0.2971 |
248
- | 0.217 | 5.97 | 22750 | 0.2971 |
249
- | 0.1998 | 5.98 | 22800 | 0.2971 |
250
- | 0.2188 | 6.0 | 22850 | 0.2971 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
251
 
252
 
253
  ### Framework versions
254
 
255
- - PEFT 0.7.1
256
- - Transformers 4.36.2
257
- - Pytorch 2.1.0+cu121
258
- - Datasets 2.16.1
259
- - Tokenizers 0.15.0
 
16
 
17
  # Codellama-7b-lora-rps-adapter
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: 0.3206
22
 
23
  ## Model description
24
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:-----:|:---------------:|
53
+ | 0.3007 | 1.18 | 5000 | 0.3014 |
54
+ | 0.2978 | 1.19 | 5050 | 0.3082 |
55
+ | 0.2726 | 1.2 | 5100 | 0.3060 |
56
+ | 0.2735 | 1.22 | 5150 | 0.3104 |
57
+ | 0.3216 | 1.23 | 5200 | 0.3058 |
58
+ | 0.258 | 1.24 | 5250 | 0.3076 |
59
+ | 0.278 | 1.25 | 5300 | 0.3095 |
60
+ | 0.2924 | 1.26 | 5350 | 0.3031 |
61
+ | 0.279 | 1.28 | 5400 | 0.3058 |
62
+ | 0.3125 | 1.29 | 5450 | 0.3009 |
63
+ | 0.329 | 1.3 | 5500 | 0.3064 |
64
+ | 0.2547 | 1.31 | 5550 | 0.3086 |
65
+ | 0.3001 | 1.32 | 5600 | 0.3027 |
66
+ | 0.2804 | 1.33 | 5650 | 0.3034 |
67
+ | 0.3309 | 1.35 | 5700 | 0.3014 |
68
+ | 0.3186 | 1.36 | 5750 | 0.3030 |
69
+ | 0.2765 | 1.37 | 5800 | 0.3011 |
70
+ | 0.2961 | 1.38 | 5850 | 0.3014 |
71
+ | 0.2825 | 1.39 | 5900 | 0.3006 |
72
+ | 0.2932 | 1.41 | 5950 | 0.2986 |
73
+ | 0.2905 | 1.42 | 6000 | 0.3113 |
74
+ | 0.2656 | 1.43 | 6050 | 0.2986 |
75
+ | 0.27 | 1.44 | 6100 | 0.3008 |
76
+ | 0.2808 | 1.45 | 6150 | 0.2972 |
77
+ | 0.3102 | 1.46 | 6200 | 0.2933 |
78
+ | 0.2885 | 1.48 | 6250 | 0.2958 |
79
+ | 0.315 | 1.49 | 6300 | 0.2965 |
80
+ | 0.3396 | 1.5 | 6350 | 0.2956 |
81
+ | 0.2955 | 1.51 | 6400 | 0.2917 |
82
+ | 0.2986 | 1.52 | 6450 | 0.2919 |
83
+ | 0.2952 | 1.54 | 6500 | 0.2924 |
84
+ | 0.2483 | 1.55 | 6550 | 0.2926 |
85
+ | 0.3115 | 1.56 | 6600 | 0.2938 |
86
+ | 0.3432 | 1.57 | 6650 | 0.2873 |
87
+ | 0.2858 | 1.58 | 6700 | 0.2863 |
88
+ | 0.256 | 1.59 | 6750 | 0.2909 |
89
+ | 0.2594 | 1.61 | 6800 | 0.2918 |
90
+ | 0.2719 | 1.62 | 6850 | 0.2915 |
91
+ | 0.2781 | 1.63 | 6900 | 0.2891 |
92
+ | 0.2827 | 1.64 | 6950 | 0.2887 |
93
+ | 0.2692 | 1.65 | 7000 | 0.2906 |
94
+ | 0.2931 | 1.67 | 7050 | 0.2925 |
95
+ | 0.3297 | 1.68 | 7100 | 0.2902 |
96
+ | 0.2818 | 1.69 | 7150 | 0.2894 |
97
+ | 0.321 | 1.7 | 7200 | 0.2874 |
98
+ | 0.2855 | 1.71 | 7250 | 0.2866 |
99
+ | 0.2638 | 1.72 | 7300 | 0.2897 |
100
+ | 0.2806 | 1.74 | 7350 | 0.2902 |
101
+ | 0.3048 | 1.75 | 7400 | 0.2902 |
102
+ | 0.2755 | 1.76 | 7450 | 0.2862 |
103
+ | 0.3178 | 1.77 | 7500 | 0.2880 |
104
+ | 0.2741 | 1.78 | 7550 | 0.2880 |
105
+ | 0.3232 | 1.8 | 7600 | 0.2877 |
106
+ | 0.2843 | 1.81 | 7650 | 0.2859 |
107
+ | 0.2774 | 1.82 | 7700 | 0.2863 |
108
+ | 0.3258 | 1.83 | 7750 | 0.2857 |
109
+ | 0.2939 | 1.84 | 7800 | 0.2865 |
110
+ | 0.2987 | 1.85 | 7850 | 0.2876 |
111
+ | 0.2934 | 1.87 | 7900 | 0.2809 |
112
+ | 0.2916 | 1.88 | 7950 | 0.2816 |
113
+ | 0.2805 | 1.89 | 8000 | 0.2828 |
114
+ | 0.3092 | 1.9 | 8050 | 0.2842 |
115
+ | 0.32 | 1.91 | 8100 | 0.2816 |
116
+ | 0.2644 | 1.93 | 8150 | 0.2847 |
117
+ | 0.2646 | 1.94 | 8200 | 0.2845 |
118
+ | 0.3287 | 1.95 | 8250 | 0.2841 |
119
+ | 0.2667 | 1.96 | 8300 | 0.2834 |
120
+ | 0.2657 | 1.97 | 8350 | 0.2837 |
121
+ | 0.2937 | 1.98 | 8400 | 0.2823 |
122
+ | 0.3119 | 2.0 | 8450 | 0.2782 |
123
+ | 0.241 | 2.01 | 8500 | 0.2938 |
124
+ | 0.2399 | 2.02 | 8550 | 0.2873 |
125
+ | 0.209 | 2.03 | 8600 | 0.2897 |
126
+ | 0.2162 | 2.04 | 8650 | 0.2923 |
127
+ | 0.2233 | 2.06 | 8700 | 0.2936 |
128
+ | 0.2133 | 2.07 | 8750 | 0.2872 |
129
+ | 0.2085 | 2.08 | 8800 | 0.2909 |
130
+ | 0.2502 | 2.09 | 8850 | 0.2892 |
131
+ | 0.2509 | 2.1 | 8900 | 0.2937 |
132
+ | 0.2101 | 2.11 | 8950 | 0.2908 |
133
+ | 0.2182 | 2.13 | 9000 | 0.2897 |
134
+ | 0.2154 | 2.14 | 9050 | 0.2934 |
135
+ | 0.2121 | 2.15 | 9100 | 0.2925 |
136
+ | 0.1998 | 2.16 | 9150 | 0.2927 |
137
+ | 0.2292 | 2.17 | 9200 | 0.2915 |
138
+ | 0.2196 | 2.19 | 9250 | 0.2927 |
139
+ | 0.2435 | 2.2 | 9300 | 0.2851 |
140
+ | 0.2135 | 2.21 | 9350 | 0.2898 |
141
+ | 0.2079 | 2.22 | 9400 | 0.2907 |
142
+ | 0.1996 | 2.23 | 9450 | 0.2880 |
143
+ | 0.2122 | 2.24 | 9500 | 0.2877 |
144
+ | 0.2678 | 2.26 | 9550 | 0.2885 |
145
+ | 0.2546 | 2.27 | 9600 | 0.2890 |
146
+ | 0.2662 | 2.28 | 9650 | 0.2865 |
147
+ | 0.2255 | 2.29 | 9700 | 0.2851 |
148
+ | 0.2413 | 2.3 | 9750 | 0.2857 |
149
+ | 0.2527 | 2.32 | 9800 | 0.2857 |
150
+ | 0.2195 | 2.33 | 9850 | 0.2856 |
151
+ | 0.2425 | 2.34 | 9900 | 0.2869 |
152
+ | 0.234 | 2.35 | 9950 | 0.2850 |
153
+ | 0.2203 | 2.36 | 10000 | 0.2861 |
154
+ | 0.234 | 2.37 | 10050 | 0.2853 |
155
+ | 0.2561 | 2.39 | 10100 | 0.2822 |
156
+ | 0.2553 | 2.4 | 10150 | 0.2846 |
157
+ | 0.2446 | 2.41 | 10200 | 0.2847 |
158
+ | 0.2265 | 2.42 | 10250 | 0.2831 |
159
+ | 0.206 | 2.43 | 10300 | 0.2869 |
160
+ | 0.2478 | 2.45 | 10350 | 0.2833 |
161
+ | 0.2107 | 2.46 | 10400 | 0.2856 |
162
+ | 0.2076 | 2.47 | 10450 | 0.2854 |
163
+ | 0.224 | 2.48 | 10500 | 0.2859 |
164
+ | 0.2118 | 2.49 | 10550 | 0.2841 |
165
+ | 0.2346 | 2.5 | 10600 | 0.2820 |
166
+ | 0.2395 | 2.52 | 10650 | 0.2786 |
167
+ | 0.264 | 2.53 | 10700 | 0.2826 |
168
+ | 0.2298 | 2.54 | 10750 | 0.2805 |
169
+ | 0.2041 | 2.55 | 10800 | 0.2792 |
170
+ | 0.2108 | 2.56 | 10850 | 0.2774 |
171
+ | 0.2487 | 2.58 | 10900 | 0.2802 |
172
+ | 0.2365 | 2.59 | 10950 | 0.2814 |
173
+ | 0.2233 | 2.6 | 11000 | 0.2812 |
174
+ | 0.2192 | 2.61 | 11050 | 0.2801 |
175
+ | 0.2113 | 2.62 | 11100 | 0.2828 |
176
+ | 0.2286 | 2.63 | 11150 | 0.2779 |
177
+ | 0.2251 | 2.65 | 11200 | 0.2792 |
178
+ | 0.2161 | 2.66 | 11250 | 0.2789 |
179
+ | 0.2213 | 2.67 | 11300 | 0.2782 |
180
+ | 0.2063 | 2.68 | 11350 | 0.2791 |
181
+ | 0.2042 | 2.69 | 11400 | 0.2789 |
182
+ | 0.188 | 2.7 | 11450 | 0.2793 |
183
+ | 0.2181 | 2.72 | 11500 | 0.2767 |
184
+ | 0.2187 | 2.73 | 11550 | 0.2784 |
185
+ | 0.2255 | 2.74 | 11600 | 0.2782 |
186
+ | 0.2529 | 2.75 | 11650 | 0.2753 |
187
+ | 0.2164 | 2.76 | 11700 | 0.2763 |
188
+ | 0.2039 | 2.78 | 11750 | 0.2766 |
189
+ | 0.2238 | 2.79 | 11800 | 0.2742 |
190
+ | 0.2393 | 2.8 | 11850 | 0.2757 |
191
+ | 0.2235 | 2.81 | 11900 | 0.2776 |
192
+ | 0.1983 | 2.82 | 11950 | 0.2778 |
193
+ | 0.2078 | 2.83 | 12000 | 0.2757 |
194
+ | 0.2487 | 2.85 | 12050 | 0.2748 |
195
+ | 0.2134 | 2.86 | 12100 | 0.2783 |
196
+ | 0.2503 | 2.87 | 12150 | 0.2772 |
197
+ | 0.2481 | 2.88 | 12200 | 0.2726 |
198
+ | 0.2274 | 2.89 | 12250 | 0.2755 |
199
+ | 0.243 | 2.91 | 12300 | 0.2738 |
200
+ | 0.2354 | 2.92 | 12350 | 0.2740 |
201
+ | 0.2323 | 2.93 | 12400 | 0.2729 |
202
+ | 0.2709 | 2.94 | 12450 | 0.2708 |
203
+ | 0.247 | 2.95 | 12500 | 0.2732 |
204
+ | 0.2242 | 2.96 | 12550 | 0.2727 |
205
+ | 0.2283 | 2.98 | 12600 | 0.2739 |
206
+ | 0.2057 | 2.99 | 12650 | 0.2730 |
207
+ | 0.2255 | 3.0 | 12700 | 0.2708 |
208
+ | 0.187 | 3.01 | 12750 | 0.2869 |
209
+ | 0.183 | 3.02 | 12800 | 0.2857 |
210
+ | 0.1653 | 3.04 | 12850 | 0.2910 |
211
+ | 0.1588 | 3.05 | 12900 | 0.2869 |
212
+ | 0.1742 | 3.06 | 12950 | 0.2873 |
213
+ | 0.1671 | 3.07 | 13000 | 0.2935 |
214
+ | 0.1506 | 3.08 | 13050 | 0.2896 |
215
+ | 0.1705 | 3.09 | 13100 | 0.2854 |
216
+ | 0.2033 | 3.11 | 13150 | 0.2872 |
217
+ | 0.1758 | 3.12 | 13200 | 0.2857 |
218
+ | 0.1483 | 3.13 | 13250 | 0.2875 |
219
+ | 0.1506 | 3.14 | 13300 | 0.2872 |
220
+ | 0.1602 | 3.15 | 13350 | 0.2874 |
221
+ | 0.1678 | 3.17 | 13400 | 0.2918 |
222
+ | 0.189 | 3.18 | 13450 | 0.2877 |
223
+ | 0.1654 | 3.19 | 13500 | 0.2878 |
224
+ | 0.1549 | 3.2 | 13550 | 0.2908 |
225
+ | 0.1669 | 3.21 | 13600 | 0.2886 |
226
+ | 0.1586 | 3.22 | 13650 | 0.2905 |
227
+ | 0.1714 | 3.24 | 13700 | 0.2858 |
228
+ | 0.1503 | 3.25 | 13750 | 0.2857 |
229
+ | 0.1706 | 3.26 | 13800 | 0.2889 |
230
+ | 0.1692 | 3.27 | 13850 | 0.2851 |
231
+ | 0.1828 | 3.28 | 13900 | 0.2877 |
232
+ | 0.1567 | 3.3 | 13950 | 0.2861 |
233
+ | 0.1559 | 3.31 | 14000 | 0.2897 |
234
+ | 0.1752 | 3.32 | 14050 | 0.2899 |
235
+ | 0.1702 | 3.33 | 14100 | 0.2870 |
236
+ | 0.1536 | 3.34 | 14150 | 0.2900 |
237
+ | 0.1771 | 3.35 | 14200 | 0.2881 |
238
+ | 0.1705 | 3.37 | 14250 | 0.2871 |
239
+ | 0.1679 | 3.38 | 14300 | 0.2840 |
240
+ | 0.1662 | 3.39 | 14350 | 0.2862 |
241
+ | 0.1502 | 3.4 | 14400 | 0.2881 |
242
+ | 0.1694 | 3.41 | 14450 | 0.2871 |
243
+ | 0.1699 | 3.43 | 14500 | 0.2840 |
244
+ | 0.1705 | 3.44 | 14550 | 0.2877 |
245
+ | 0.1741 | 3.45 | 14600 | 0.2874 |
246
+ | 0.1654 | 3.46 | 14650 | 0.2854 |
247
+ | 0.1956 | 3.47 | 14700 | 0.2845 |
248
+ | 0.1659 | 3.48 | 14750 | 0.2860 |
249
+ | 0.18 | 3.5 | 14800 | 0.2826 |
250
+ | 0.1645 | 3.51 | 14850 | 0.2829 |
251
+ | 0.1835 | 3.52 | 14900 | 0.2828 |
252
+ | 0.1645 | 3.53 | 14950 | 0.2839 |
253
+ | 0.1843 | 3.54 | 15000 | 0.2833 |
254
+ | 0.1796 | 3.56 | 15050 | 0.2799 |
255
+ | 0.1639 | 3.57 | 15100 | 0.2839 |
256
+ | 0.169 | 3.58 | 15150 | 0.2809 |
257
+ | 0.1568 | 3.59 | 15200 | 0.2817 |
258
+ | 0.1971 | 3.6 | 15250 | 0.2819 |
259
+ | 0.1702 | 3.61 | 15300 | 0.2787 |
260
+ | 0.1778 | 3.63 | 15350 | 0.2792 |
261
+ | 0.1862 | 3.64 | 15400 | 0.2786 |
262
+ | 0.1691 | 3.65 | 15450 | 0.2840 |
263
+ | 0.1679 | 3.66 | 15500 | 0.2844 |
264
+ | 0.1693 | 3.67 | 15550 | 0.2801 |
265
+ | 0.1622 | 3.69 | 15600 | 0.2773 |
266
+ | 0.1533 | 3.7 | 15650 | 0.2800 |
267
+ | 0.1674 | 3.71 | 15700 | 0.2786 |
268
+ | 0.1711 | 3.72 | 15750 | 0.2784 |
269
+ | 0.1683 | 3.73 | 15800 | 0.2797 |
270
+ | 0.1807 | 3.74 | 15850 | 0.2781 |
271
+ | 0.1698 | 3.76 | 15900 | 0.2779 |
272
+ | 0.1557 | 3.77 | 15950 | 0.2799 |
273
+ | 0.1801 | 3.78 | 16000 | 0.2783 |
274
+ | 0.184 | 3.79 | 16050 | 0.2765 |
275
+ | 0.1907 | 3.8 | 16100 | 0.2759 |
276
+ | 0.1626 | 3.82 | 16150 | 0.2766 |
277
+ | 0.1524 | 3.83 | 16200 | 0.2803 |
278
+ | 0.1574 | 3.84 | 16250 | 0.2784 |
279
+ | 0.1669 | 3.85 | 16300 | 0.2808 |
280
+ | 0.1888 | 3.86 | 16350 | 0.2782 |
281
+ | 0.1847 | 3.87 | 16400 | 0.2779 |
282
+ | 0.1846 | 3.89 | 16450 | 0.2783 |
283
+ | 0.183 | 3.9 | 16500 | 0.2783 |
284
+ | 0.1573 | 3.91 | 16550 | 0.2781 |
285
+ | 0.1729 | 3.92 | 16600 | 0.2788 |
286
+ | 0.1626 | 3.93 | 16650 | 0.2771 |
287
+ | 0.177 | 3.95 | 16700 | 0.2770 |
288
+ | 0.1529 | 3.96 | 16750 | 0.2773 |
289
+ | 0.1712 | 3.97 | 16800 | 0.2734 |
290
+ | 0.1748 | 3.98 | 16850 | 0.2740 |
291
+ | 0.1555 | 3.99 | 16900 | 0.2729 |
292
+ | 0.1464 | 4.0 | 16950 | 0.2843 |
293
+ | 0.1393 | 4.02 | 17000 | 0.2933 |
294
+ | 0.1237 | 4.03 | 17050 | 0.2943 |
295
+ | 0.1168 | 4.04 | 17100 | 0.2953 |
296
+ | 0.1121 | 4.05 | 17150 | 0.2948 |
297
+ | 0.1169 | 4.06 | 17200 | 0.2933 |
298
+ | 0.1209 | 4.08 | 17250 | 0.2936 |
299
+ | 0.1145 | 4.09 | 17300 | 0.2953 |
300
+ | 0.1143 | 4.1 | 17350 | 0.2946 |
301
+ | 0.1341 | 4.11 | 17400 | 0.2966 |
302
+ | 0.1299 | 4.12 | 17450 | 0.2921 |
303
+ | 0.1162 | 4.13 | 17500 | 0.2917 |
304
+ | 0.1175 | 4.15 | 17550 | 0.2937 |
305
+ | 0.1185 | 4.16 | 17600 | 0.2940 |
306
+ | 0.1185 | 4.17 | 17650 | 0.2922 |
307
+ | 0.1332 | 4.18 | 17700 | 0.2916 |
308
+ | 0.13 | 4.19 | 17750 | 0.2916 |
309
+ | 0.1301 | 4.21 | 17800 | 0.2921 |
310
+ | 0.1196 | 4.22 | 17850 | 0.2921 |
311
+ | 0.1169 | 4.23 | 17900 | 0.2924 |
312
+ | 0.1079 | 4.24 | 17950 | 0.2977 |
313
+ | 0.1103 | 4.25 | 18000 | 0.2945 |
314
+ | 0.1205 | 4.26 | 18050 | 0.2919 |
315
+ | 0.1191 | 4.28 | 18100 | 0.2918 |
316
+ | 0.1271 | 4.29 | 18150 | 0.2924 |
317
+ | 0.1181 | 4.3 | 18200 | 0.2934 |
318
+ | 0.1151 | 4.31 | 18250 | 0.2935 |
319
+ | 0.1323 | 4.32 | 18300 | 0.2922 |
320
+ | 0.1073 | 4.33 | 18350 | 0.2940 |
321
+ | 0.1173 | 4.35 | 18400 | 0.2898 |
322
+ | 0.118 | 4.36 | 18450 | 0.2937 |
323
+ | 0.122 | 4.37 | 18500 | 0.2921 |
324
+ | 0.1276 | 4.38 | 18550 | 0.2899 |
325
+ | 0.145 | 4.39 | 18600 | 0.2918 |
326
+ | 0.1219 | 4.41 | 18650 | 0.2943 |
327
+ | 0.1198 | 4.42 | 18700 | 0.2917 |
328
+ | 0.1242 | 4.43 | 18750 | 0.2926 |
329
+ | 0.1188 | 4.44 | 18800 | 0.2939 |
330
+ | 0.1098 | 4.45 | 18850 | 0.2946 |
331
+ | 0.1163 | 4.46 | 18900 | 0.2912 |
332
+ | 0.1181 | 4.48 | 18950 | 0.2912 |
333
+ | 0.1341 | 4.49 | 19000 | 0.2903 |
334
+ | 0.1198 | 4.5 | 19050 | 0.2890 |
335
+ | 0.1234 | 4.51 | 19100 | 0.2892 |
336
+ | 0.1192 | 4.52 | 19150 | 0.2933 |
337
+ | 0.1185 | 4.54 | 19200 | 0.2932 |
338
+ | 0.1122 | 4.55 | 19250 | 0.2925 |
339
+ | 0.1259 | 4.56 | 19300 | 0.2877 |
340
+ | 0.1218 | 4.57 | 19350 | 0.2903 |
341
+ | 0.1245 | 4.58 | 19400 | 0.2894 |
342
+ | 0.1086 | 4.59 | 19450 | 0.2914 |
343
+ | 0.1234 | 4.61 | 19500 | 0.2924 |
344
+ | 0.1238 | 4.62 | 19550 | 0.2929 |
345
+ | 0.1162 | 4.63 | 19600 | 0.2931 |
346
+ | 0.1271 | 4.64 | 19650 | 0.2910 |
347
+ | 0.1165 | 4.65 | 19700 | 0.2875 |
348
+ | 0.125 | 4.67 | 19750 | 0.2902 |
349
+ | 0.122 | 4.68 | 19800 | 0.2882 |
350
+ | 0.115 | 4.69 | 19850 | 0.2896 |
351
+ | 0.1112 | 4.7 | 19900 | 0.2904 |
352
+ | 0.1215 | 4.71 | 19950 | 0.2901 |
353
+ | 0.1241 | 4.72 | 20000 | 0.2912 |
354
+ | 0.1181 | 4.74 | 20050 | 0.2911 |
355
+ | 0.1215 | 4.75 | 20100 | 0.2901 |
356
+ | 0.1196 | 4.76 | 20150 | 0.2907 |
357
+ | 0.1205 | 4.77 | 20200 | 0.2919 |
358
+ | 0.1237 | 4.78 | 20250 | 0.2915 |
359
+ | 0.127 | 4.8 | 20300 | 0.2888 |
360
+ | 0.1108 | 4.81 | 20350 | 0.2923 |
361
+ | 0.1064 | 4.82 | 20400 | 0.2925 |
362
+ | 0.1238 | 4.83 | 20450 | 0.2899 |
363
+ | 0.1213 | 4.84 | 20500 | 0.2894 |
364
+ | 0.1325 | 4.85 | 20550 | 0.2891 |
365
+ | 0.1219 | 4.87 | 20600 | 0.2894 |
366
+ | 0.12 | 4.88 | 20650 | 0.2912 |
367
+ | 0.1241 | 4.89 | 20700 | 0.2878 |
368
+ | 0.1258 | 4.9 | 20750 | 0.2873 |
369
+ | 0.1201 | 4.91 | 20800 | 0.2900 |
370
+ | 0.1136 | 4.93 | 20850 | 0.2892 |
371
+ | 0.1308 | 4.94 | 20900 | 0.2879 |
372
+ | 0.1143 | 4.95 | 20950 | 0.2879 |
373
+ | 0.1161 | 4.96 | 21000 | 0.2911 |
374
+ | 0.108 | 4.97 | 21050 | 0.2884 |
375
+ | 0.1326 | 4.98 | 21100 | 0.2853 |
376
+ | 0.1127 | 5.0 | 21150 | 0.2887 |
377
+ | 0.0953 | 5.01 | 21200 | 0.3096 |
378
+ | 0.078 | 5.02 | 21250 | 0.3143 |
379
+ | 0.0815 | 5.03 | 21300 | 0.3126 |
380
+ | 0.0732 | 5.04 | 21350 | 0.3179 |
381
+ | 0.083 | 5.06 | 21400 | 0.3153 |
382
+ | 0.0726 | 5.07 | 21450 | 0.3163 |
383
+ | 0.073 | 5.08 | 21500 | 0.3144 |
384
+ | 0.0787 | 5.09 | 21550 | 0.3164 |
385
+ | 0.0763 | 5.1 | 21600 | 0.3146 |
386
+ | 0.0735 | 5.11 | 21650 | 0.3133 |
387
+ | 0.0809 | 5.13 | 21700 | 0.3179 |
388
+ | 0.0745 | 5.14 | 21750 | 0.3136 |
389
+ | 0.0803 | 5.15 | 21800 | 0.3153 |
390
+ | 0.0808 | 5.16 | 21850 | 0.3173 |
391
+ | 0.0735 | 5.17 | 21900 | 0.3194 |
392
+ | 0.0773 | 5.19 | 21950 | 0.3181 |
393
+ | 0.0758 | 5.2 | 22000 | 0.3199 |
394
+ | 0.0758 | 5.21 | 22050 | 0.3183 |
395
+ | 0.0735 | 5.22 | 22100 | 0.3158 |
396
+ | 0.0791 | 5.23 | 22150 | 0.3178 |
397
+ | 0.0828 | 5.24 | 22200 | 0.3190 |
398
+ | 0.0694 | 5.26 | 22250 | 0.3199 |
399
+ | 0.0745 | 5.27 | 22300 | 0.3190 |
400
+ | 0.0728 | 5.28 | 22350 | 0.3194 |
401
+ | 0.0716 | 5.29 | 22400 | 0.3211 |
402
+ | 0.0756 | 5.3 | 22450 | 0.3188 |
403
+ | 0.0713 | 5.32 | 22500 | 0.3188 |
404
+ | 0.0772 | 5.33 | 22550 | 0.3199 |
405
+ | 0.0809 | 5.34 | 22600 | 0.3184 |
406
+ | 0.0739 | 5.35 | 22650 | 0.3189 |
407
+ | 0.0739 | 5.36 | 22700 | 0.3186 |
408
+ | 0.0815 | 5.37 | 22750 | 0.3177 |
409
+ | 0.0734 | 5.39 | 22800 | 0.3183 |
410
+ | 0.084 | 5.4 | 22850 | 0.3168 |
411
+ | 0.0736 | 5.41 | 22900 | 0.3188 |
412
+ | 0.0761 | 5.42 | 22950 | 0.3188 |
413
+ | 0.0735 | 5.43 | 23000 | 0.3183 |
414
+ | 0.075 | 5.45 | 23050 | 0.3187 |
415
+ | 0.0767 | 5.46 | 23100 | 0.3192 |
416
+ | 0.0856 | 5.47 | 23150 | 0.3182 |
417
+ | 0.0695 | 5.48 | 23200 | 0.3210 |
418
+ | 0.0754 | 5.49 | 23250 | 0.3207 |
419
+ | 0.0795 | 5.5 | 23300 | 0.3197 |
420
+ | 0.0733 | 5.52 | 23350 | 0.3196 |
421
+ | 0.076 | 5.53 | 23400 | 0.3217 |
422
+ | 0.0764 | 5.54 | 23450 | 0.3197 |
423
+ | 0.0742 | 5.55 | 23500 | 0.3212 |
424
+ | 0.075 | 5.56 | 23550 | 0.3211 |
425
+ | 0.078 | 5.58 | 23600 | 0.3196 |
426
+ | 0.0798 | 5.59 | 23650 | 0.3200 |
427
+ | 0.0736 | 5.6 | 23700 | 0.3181 |
428
+ | 0.0848 | 5.61 | 23750 | 0.3184 |
429
+ | 0.0752 | 5.62 | 23800 | 0.3193 |
430
+ | 0.0732 | 5.63 | 23850 | 0.3186 |
431
+ | 0.0788 | 5.65 | 23900 | 0.3175 |
432
+ | 0.0822 | 5.66 | 23950 | 0.3186 |
433
+ | 0.0772 | 5.67 | 24000 | 0.3195 |
434
+ | 0.0779 | 5.68 | 24050 | 0.3197 |
435
+ | 0.0778 | 5.69 | 24100 | 0.3202 |
436
+ | 0.0765 | 5.71 | 24150 | 0.3207 |
437
+ | 0.0819 | 5.72 | 24200 | 0.3193 |
438
+ | 0.0767 | 5.73 | 24250 | 0.3204 |
439
+ | 0.0726 | 5.74 | 24300 | 0.3214 |
440
+ | 0.0911 | 5.75 | 24350 | 0.3212 |
441
+ | 0.0665 | 5.76 | 24400 | 0.3208 |
442
+ | 0.0733 | 5.78 | 24450 | 0.3208 |
443
+ | 0.0745 | 5.79 | 24500 | 0.3202 |
444
+ | 0.0735 | 5.8 | 24550 | 0.3203 |
445
+ | 0.0717 | 5.81 | 24600 | 0.3202 |
446
+ | 0.0693 | 5.82 | 24650 | 0.3203 |
447
+ | 0.0748 | 5.84 | 24700 | 0.3198 |
448
+ | 0.0722 | 5.85 | 24750 | 0.3203 |
449
+ | 0.0805 | 5.86 | 24800 | 0.3205 |
450
+ | 0.0761 | 5.87 | 24850 | 0.3210 |
451
+ | 0.0706 | 5.88 | 24900 | 0.3208 |
452
+ | 0.0701 | 5.89 | 24950 | 0.3213 |
453
+ | 0.0776 | 5.91 | 25000 | 0.3210 |
454
+ | 0.081 | 5.92 | 25050 | 0.3208 |
455
+ | 0.0698 | 5.93 | 25100 | 0.3207 |
456
+ | 0.0708 | 5.94 | 25150 | 0.3208 |
457
+ | 0.0785 | 5.95 | 25200 | 0.3206 |
458
+ | 0.0708 | 5.97 | 25250 | 0.3206 |
459
+ | 0.0721 | 5.98 | 25300 | 0.3206 |
460
+ | 0.0718 | 5.99 | 25350 | 0.3206 |
461
 
462
 
463
  ### Framework versions
464
 
465
+ - PEFT 0.10.0
466
+ - Transformers 4.39.1
467
+ - Pytorch 2.2.1+cu121
468
+ - Datasets 2.18.0
469
+ - Tokenizers 0.15.2
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5bdced7d1d5fa15d54d7990fa36b567e0e74cdfd9be65fe772a76a49d5e0a150
3
  size 2332095256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc0a0d36685063abfcb83bd2cf7302e9a5a76cc58234819556b8db357fd35706
3
  size 2332095256
runs/Mar26_09-06-52_ef3683ac757a/events.out.tfevents.1711444019.ef3683ac757a.42812.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19ebd0755b8caf9a89e78c7578c62c66e7b86e3383525829a2497658d524c1c2
3
- size 223869
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3accec753d2e72bc18cb47a148c3b6b338c13e64c1b515c06c078c9f9c9fcb18
3
+ size 224720