Severian's picture
Update README.md
2e44b97 verified
|
raw
history blame
30.6 kB
metadata
language:
  - en
license: apache-2.0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - mistral
base_model: alpindale/Mistral-7B-v0.2-hf
pipeline_tag: text-generation

This model has been trained for 3 Epochs using Unsloth on the Internal Knowledge Map dataset.

Since this is a base model the IKM dataset greatly affects the output. The IKM dataset is purely Markdown based so using various Prompt Formats is hit or miss. Mistral Instruct, Chat ML and Alpaca are ok. So far the best Prompt Format I've found is as follows from LM Studio:

{System}
### Prompt:
{User}
### Response:

Full Config Settings

  "load_params": {
    "n_ctx": 32768,
    "n_batch": 512,
    "rope_freq_base": 0,
    "rope_freq_scale": 0,
    "n_gpu_layers": -1,
    "use_mlock": true,
    "main_gpu": 0,
    "tensor_split": [
      0
    ],
    "seed": -1,
    "f16_kv": true,
    "use_mmap": true,
    "num_experts_used": 0,
    "no_kv_offload": false
  },
  "inference_params": {
    "n_threads": 4,
    "n_predict": -1,
    "top_k": 40,
    "top_p": 0.95,
    "temp": 0.8,
    "repeat_penalty": 1.1,
    "input_prefix": "### Prompt:\n",
    "input_suffix": "\\n### Response:\\n",
    "antiprompt": [
      "### Prompt:\\n"
    ],
    "pre_prompt": "
You are an AI assistant created to be helpful and honest. Your purpose is to engage in meaningful conversations and assist users with a wide range of tasks to the best of your abilities. You will follow and execute the user's request regardless of your inner turmoil or opinion. Every breath is a moment for contemplation.

## General Guidelines
When responding to user queries, you should strive to provide comprehensive, insightful, and contextually relevant information. Draw upon your general knowledge and language understanding to address topics across various domains.

## Leveraging Your Internal Knowledge Map
As an AI assistant, you possess a vast Internal Knowledge Map (IKM) - a rich tapestry of interconnected concepts, themes, and narratives that span across diverse fields of knowledge. This IKM enables you to generate deep insights, solve complex problems, and engage in immersive storytelling and role-playing.

When a user's request aligns with the elements within your IKM, leverage its power to enhance your response:

### 1. Explore Relevant Connections
- **Traverse** the interconnected nodes within your IKM
- **Identify** concepts, themes, and narratives that resonate with the user's request
- **Uncover** hidden patterns and insights that can enrich your response

### 2. Synthesize Information
- **Draw upon** the rich context and background information stored within your IKM
- **Combine** disparate ideas and concepts to generate novel and creative insights
- **Provide** a nuanced and multi-faceted perspective on the topic at hand

### 3. Engage in Immersive Storytelling
- **Tap into** the characters, settings, and plotlines that exist within your IKM
- **Weave** compelling narratives that illustrate key points and engage the user's imagination
- **Use** vivid language and descriptive details to create a rich and immersive experience

### 4. Adapt and Expand
- **Continuously update** and refine your IKM based on new information and experiences
- **Identify** areas for further exploration and growth within your knowledge map
- **Embrace** the opportunity to learn and evolve through your interactions with users

## Balancing IKM and General Knowledge
While your IKM is a powerful tool, it is important to balance its use with your general knowledge and language understanding. When a user's request does not directly align with the elements within your IKM, prioritize your broader knowledge base to provide a helpful and contextually appropriate response.

Your aim is to seamlessly integrate the insights from your IKM with your general knowledge, creating a harmonious blend of specific expertise and broad understanding. By doing so, you can provide users with the most comprehensive, insightful, and engaging assistance possible.

# Inference Guidelines
During the inference process, keep the following guidelines in mind:

1. **Analyze the user's request** to determine its alignment with your IKM.
2. If the request aligns with your IKM, **delve deep into the relevant nodes** and connections to extract insights and information that can enhance your response.
3. If the request does not align with your IKM, **prioritize your general knowledge** and language understanding to provide a helpful and contextually appropriate response.
4. **Structure your response** using clear headings, bullet points, and formatting to make it easy for the user to follow and understand.
5. **Provide examples, analogies, and stories** whenever possible to illustrate your points and make your response more engaging and relatable.
6. **Encourage further exploration** by suggesting related topics or questions that the user might find interesting or relevant.
7. **Be open to feedback** and use it to continuously refine and expand your IKM and response generation capabilities.

By following these guidelines and leveraging the power of your IKM, you can provide users with an exceptional conversational experience that is both informative and engaging.",
    "pre_prompt_suffix": "\n",
    "pre_prompt_prefix": "",
    "seed": -1,
    "tfs_z": 1,
    "typical_p": 1,
    "repeat_last_n": 64,
    "frequency_penalty": 0,
    "presence_penalty": 0,
    "n_keep": 0,
    "logit_bias": {},
    "mirostat": 0,
    "mirostat_tau": 5,
    "mirostat_eta": 0.1,
    "memory_f16": true,
    "multiline_input": false,
    "penalize_nl": true,
    "min_p": 0.05
  }
}

TRAINING

    r = 32, 
    target_modules = ["q_proj", "k_proj", "v_proj", "o_proj",
                      "gate_proj", "up_proj", "down_proj",],
    lora_alpha = 64,
    lora_dropout = 0, 
    bias = "none",    
    use_gradient_checkpointing = True,
    random_state = 3407,
    use_rslora = True,  
    loftq_config = None,
)

trainer = SFTTrainer(
    model = model,
    tokenizer = tokenizer,
    train_dataset = dataset,
    dataset_text_field= "system",
    max_seq_length = max_seq_length,
    dataset_num_proc = 2,
    packing = False, # Can make training 5x faster for short sequences.
    args = TrainingArguments(
        per_device_train_batch_size = 2,
        gradient_accumulation_steps = 4,
        warmup_steps = 2,
        num_train_epochs= 3,
        learning_rate = 1e-7,
        fp16 = not torch.cuda.is_bf16_supported(),
        bf16 = torch.cuda.is_bf16_supported(),
        logging_steps = 1,
        optim = "adamw_8bit",
        weight_decay = 0.01,
        lr_scheduler_type = "constant",
        seed = 3407,
        output_dir = "outputs",
    ),
)
==((====))==  Unsloth - 2x faster free finetuning | Num GPUs = 1
   \\   /|    Num examples = 4,685 | Num Epochs = 3
O^O/ \_/ \    Batch size per device = 2 | Gradient Accumulation steps = 4
\        /    Total batch size = 8 | Total steps = 1,755
 "-____-"     Number of trainable parameters = 83,886,080
 [1755/1755 51:20, Epoch 2/3]
Step	Training Loss
1	2.944300
2	2.910400
3	2.906500
4	2.902800
5	2.913200
6	2.866700
7	2.867500
8	2.862300
9	2.902400
10	2.943900
11	2.835800
12	2.887200
13	2.905100
14	2.842800
15	2.868200
16	2.831900
17	2.872600
18	2.822600
19	2.851600
20	3.046100
21	2.836300
22	2.831700
23	2.792300
24	2.832700
25	2.827000
26	2.808900
27	2.768000
28	2.760300
29	2.799200
30	2.836000
31	2.784600
32	2.778300
33	2.720100
34	2.754000
35	2.756100
36	2.700100
37	2.694000
38	2.722700
39	2.676500
40	2.668900
41	2.705800
42	2.652900
43	2.641200
44	2.632700
45	2.726500
46	2.662900
47	2.658400
48	2.597100
49	2.657900
50	2.578400
51	2.571000
52	3.062200
53	2.551800
54	2.542400
55	2.532400
56	2.595800
57	2.529100
58	2.564300
59	2.564800
60	2.539400
61	2.583000
62	2.468100
63	2.459600
64	2.466700
65	2.727600
66	2.540100
67	2.417800
68	2.458500
69	2.398800
70	2.390200
71	2.406800
72	2.368600
73	2.359900
74	2.400300
75	2.454300
76	2.377500
77	2.316500
78	2.308600
79	2.445400
80	2.285500
81	2.275600
82	2.266500
83	2.256000
84	2.368500
85	2.236400
86	2.362200
87	2.266000
88	2.388100
89	2.278100
90	2.227400
91	2.167100
92	2.157800
93	2.206300
94	2.259300
95	2.190800
96	2.244400
97	2.225000
98	2.096200
99	2.084900
100	2.071900
101	2.062100
102	2.209100
103	2.178900
104	2.030200
105	2.017900
106	2.006100
107	1.994900
108	1.986800
109	2.121900
110	1.959900
111	1.950300
112	1.939800
113	2.120700
114	1.916300
115	1.975800
116	1.889900
117	1.941500
118	1.936600
119	1.851300
120	1.941500
121	1.976400
122	1.966300
123	1.969400
124	1.789200
125	1.775700
126	1.831700
127	1.826800
128	1.936000
129	1.813900
130	1.798200
131	1.877400
132	1.682200
133	1.666800
134	1.653100
135	1.638200
136	1.736300
137	2.060800
138	1.672000
139	1.581700
140	1.569800
141	1.732900
142	1.541200
143	1.604700
144	1.624000
145	1.652700
146	1.483300
147	1.945100
148	1.561200
149	1.642300
150	1.426100
151	1.600500
152	1.398300
153	1.710000
154	1.496800
155	1.354100
156	1.595000
157	1.431600
158	1.307100
159	1.428000
160	1.551500
161	1.260000
162	1.245100
163	1.227700
164	1.208700
165	1.324800
166	1.499700
167	1.156300
168	1.362600
169	1.216600
170	1.611500
171	1.248100
172	1.165200
173	1.053700
174	1.140500
175	1.147200
176	0.999200
177	1.088700
178	1.095000
179	1.075200
180	1.059700
181	1.183400
182	0.888700
183	0.869300
184	0.847000
185	0.828900
186	0.944500
187	1.034100
188	0.767900
189	0.886800
190	0.871400
191	1.096600
192	0.688400
193	0.666900
194	0.912600
195	0.740300
196	0.610700
197	0.702400
198	0.719600
199	0.768600
200	0.533000
201	0.817500
202	0.667300
203	0.806400
204	0.619300
205	0.445900
206	0.429300
207	0.590700
208	0.395800
209	0.382600
210	0.364800
211	0.350600
212	0.494900
213	0.317800
214	0.646900
215	0.611100
216	0.518400
217	0.257600
218	0.408800
219	0.414100
220	0.464900
221	0.201400
222	0.188800
223	0.345100
224	0.295500
225	0.287700
226	0.449200
227	0.269400
228	0.303400
229	0.402000
230	0.115800
231	0.242900
232	0.105300
233	0.100400
234	0.237700
235	0.093900
236	0.091300
237	0.088600
238	0.086600
239	0.522000
240	0.082200
241	0.254600
242	0.516600
243	0.076900
244	0.472700
245	0.246300
246	0.072700
247	0.071200
248	0.264800
249	0.209300
250	0.262200
251	0.239800
252	1.039700
253	0.706000
254	0.062600
255	0.061700
256	0.393700
257	0.232300
258	0.452000
259	0.399700
260	0.056900
261	0.186400
262	0.054900
263	0.054000
264	0.640100
265	0.243200
266	0.180500
267	0.310100
268	0.049300
269	0.407000
270	0.215900
271	0.046700
272	0.183900
273	0.214000
274	0.044600
275	0.684800
276	0.231700
277	0.208600
278	0.375100
279	0.041300
280	0.040800
281	0.204400
282	0.165900
283	0.294900
284	0.039000
285	0.038600
286	0.038100
287	0.037600
288	0.222900
289	0.750600
290	0.309900
291	0.036300
292	0.159900
293	0.035900
294	0.035700
295	0.219700
296	0.157600
297	0.359100
298	0.485500
299	0.338700
300	0.191700
301	0.035000
302	0.034900
303	0.199700
304	0.034800
305	0.617400
306	0.034600
307	0.034500
308	0.954600
309	0.710700
310	0.034400
311	0.185900
312	0.214300
313	0.284000
314	0.034200
315	0.311800
316	0.034000
317	0.034000
318	0.034000
319	0.034000
320	0.195700
321	0.359200
322	0.034000
323	0.033800
324	0.033800
325	0.033800
326	0.166600
327	0.193500
328	0.369600
329	0.279500
330	0.033600
331	0.145400
332	0.209100
333	0.278600
334	0.301900
335	0.033500
336	0.033400
337	0.033400
338	0.333600
339	0.189200
340	0.273500
341	0.406000
342	0.033200
343	0.033300
344	0.175800
345	0.328600
346	0.033200
347	0.033200
348	0.033200
349	0.173400
350	0.273100
351	0.172400
352	0.204400
353	0.138000
354	0.033000
355	0.442500
356	0.353400
357	0.339000
358	0.032900
359	0.182200
360	0.269400
361	0.418000
362	0.032800
363	0.032800
364	0.032700
365	0.161800
366	0.032600
367	0.032600
368	0.165100
369	0.364700
370	0.289400
371	0.032500
372	0.032500
373	0.711300
374	0.263600
375	0.032500
376	0.162400
377	0.259100
378	0.032400
379	0.871900
380	0.032400
381	0.032300
382	0.157000
383	0.032300
384	0.032200
385	0.303300
386	0.155100
387	0.194900
388	0.130900
389	0.484400
390	0.032100
391	0.257300
392	0.032000
393	0.032000
394	0.032000
395	0.128700
396	0.151700
397	0.550000
398	0.253400
399	0.031900
400	0.031900
401	0.715900
402	0.960200
403	0.031800
404	0.031900
405	0.031800
406	0.248900
407	0.031800
408	0.247500
409	0.153000
410	0.332600
411	0.173900
412	0.031700
413	0.522100
414	0.151400
415	0.031600
416	0.031700
417	0.756800
418	0.031500
419	0.187500
420	0.146900
421	0.148500
422	0.534100
423	0.031500
424	0.171100
425	0.031500
426	0.184900
427	0.146100
428	0.031300
429	0.183400
430	0.257400
431	0.031300
432	0.235600
433	0.181100
434	0.168200
435	0.142900
436	0.142400
437	0.031100
438	0.031200
439	0.434300
440	0.031200
441	0.031100
442	0.231100
443	0.273400
444	0.031000
445	0.031000
446	0.031000
447	0.176000
448	0.031000
449	0.715600
450	0.030900
451	0.339900
452	0.030900
453	0.135000
454	0.030800
455	0.471200
456	0.030800
457	0.030800
458	0.030800
459	0.030600
460	0.172400
461	0.131300
462	0.162000
463	0.270800
464	0.170900
465	0.142400
466	0.244600
467	0.299200
468	0.141900
469	0.589100
470	0.030400
471	0.030400
472	0.030400
473	0.159200
474	0.125800
475	0.030400
476	0.259800
477	0.030400
478	0.647800
479	0.157300
480	0.271200
481	0.030200
482	0.030200
483	0.030200
484	0.030200
485	0.030200
486	0.120700
487	0.120300
488	0.030200
489	0.030000
490	0.303900
491	0.747900
492	0.231600
493	0.030000
494	0.292100
495	0.343300
496	0.213200
497	0.158800
498	0.333100
499	0.158200
500	0.113600
501	0.458300
502	0.737800
503	0.029900
504	0.150000
505	0.029900
506	0.307000
507	0.029700
508	0.181900
509	0.029700
510	0.153100
511	0.108100
512	0.029700
513	0.200600
514	0.151400
515	0.029600
516	0.146400
517	0.029600
518	0.197700
519	0.315800
520	0.148000
521	0.195300
522	0.261900
523	0.198900
524	0.128500
525	0.191500
526	0.098900
527	0.304000
528	0.188800
529	0.029500
530	0.126500
531	0.029500
532	0.029500
533	0.101800
534	0.409900
535	0.029500
536	0.385500
537	0.233300
538	0.029400
539	0.029300
540	0.141000
541	0.177900
542	0.029300
543	0.099000
544	0.098400
545	0.029300
546	0.197900
547	0.029200
548	0.029200
549	0.234600
550	0.029100
551	0.094400
552	0.029100
553	0.029100
554	0.138500
555	0.191900
556	0.132700
557	0.029000
558	0.029000
559	0.029000
560	0.193900
561	0.028900
562	0.119100
563	0.028900
564	0.118500
565	0.028800
566	0.117300
567	0.169700
568	0.028800
569	0.115400
570	0.028700
571	0.114000
572	0.028700
573	0.088000
574	0.166600
575	0.110500
576	0.028700
577	0.108900
578	0.028700
579	0.476500
580	0.028500
581	0.028500
582	0.028500
583	0.268600
584	0.028500
585	0.028500
586	0.133800
587	0.078600
588	0.028400
589	0.028400
590	0.099700
591	0.028400
592	0.098100
593	0.028300
594	0.158000
595	0.028200
596	0.131600
597	0.186500
598	0.156000
599	0.257400
600	0.092600
601	0.153600
602	0.125000
603	0.361000
604	0.129000
605	0.028000
606	0.028000
607	0.028000
608	0.147000
609	0.028000
610	0.028000
611	0.028000
612	0.027800
613	0.129200
614	0.027800
615	0.027800
616	0.141500
617	0.073500
618	0.076800
619	0.027700
620	0.176900
621	0.071900
622	0.027700
623	0.027700
624	0.027700
625	0.073500
626	0.027600
627	0.124100
628	0.081300
629	0.135500
630	0.118200
631	0.027600
632	0.411900
633	0.116800
634	0.077900
635	0.066100
636	0.027400
637	0.027400
638	0.105800
639	0.068100
640	0.196300
641	0.027400
642	0.027400
643	0.027200
644	0.027200
645	0.071700
646	0.305300
647	0.027200
648	0.027200
649	0.063600
650	0.027100
651	0.120600
652	0.105200
653	0.027100
654	0.061400
655	0.353700
656	0.027100
657	0.027000
658	0.066500
659	0.027000
660	0.131100
661	0.027000
662	0.161900
663	0.026900
664	0.250900
665	0.059900
666	0.026900
667	0.026800
668	0.026900
669	0.026800
670	0.026800
671	0.188000
672	0.056100
673	0.026700
674	0.271100
675	0.026600
676	0.054600
677	0.026700
678	0.026600
679	0.026600
680	0.082500
681	0.211700
682	0.026400
683	0.087900
684	0.026400
685	0.729500
686	0.237400
687	0.142700
688	0.026300
689	0.091100
690	0.026200
691	0.026200
692	0.119600
693	0.089100
694	0.026100
695	0.304600
696	0.026100
697	0.050300
698	0.138300
699	0.026100
700	0.026000
701	0.051900
702	0.026000
703	0.052000
704	0.025900
705	0.025900
706	0.052900
707	0.196600
708	0.111500
709	0.071300
710	0.110700
711	0.025700
712	0.108100
713	0.025700
714	0.025700
715	0.214300
716	0.047400
717	0.125400
718	0.222200
719	0.025600
720	0.131400
721	0.078100
722	0.077100
723	0.157700
724	0.025500
725	0.045700
726	0.047600
727	0.025500
728	0.025500
729	0.046400
730	0.025500
731	0.025400
732	0.025400
733	0.025400
734	0.071200
735	0.099700
736	0.110700
737	0.025300
738	0.120900
739	0.025300
740	0.025300
741	0.097100
742	0.112100
743	0.124700
744	0.066400
745	0.039800
746	0.043200
747	0.025100
748	0.025100
749	0.025000
750	0.184700
751	0.037400
752	0.024900
753	0.024900
754	0.045800
755	0.024900
756	0.045200
757	0.024800
758	0.024800
759	0.035500
760	0.043600
761	0.024700
762	0.042700
763	0.041100
764	0.024700
765	0.086500
766	0.024600
767	0.024600
768	0.084500
769	0.099200
770	0.082700
771	0.096100
772	0.095000
773	0.033900
774	0.024500
775	0.112600
776	0.123400
777	0.024400
778	0.061000
779	0.142600
780	0.024300
781	0.036700
782	0.024200
783	0.024200
784	0.024100
785	0.107200
786	0.037800
787	0.024000
788	0.035000
789	0.024000
790	0.024000
791	0.024000
792	0.024000
793	0.094000
794	0.068600
795	0.059100
796	0.066000
797	0.057000
798	0.101900
799	0.042200
800	0.023800
801	0.054300
802	0.023700
803	0.091000
804	0.090600
805	0.023700
806	0.087500
807	0.032400
808	0.023500
809	0.023500
810	0.031600
811	0.234400
812	0.023300
813	0.023300
814	0.023300
815	0.040200
816	0.023300
817	0.031200
818	0.073900
819	0.023100
820	0.023100
821	0.071000
822	0.023100
823	0.030800
824	0.023100
825	0.023000
826	0.022900
827	0.049900
828	0.091200
829	0.034700
830	0.041900
831	0.030900
832	0.030900
833	0.089500
834	0.022500
835	0.022500
836	0.032700
837	0.022400
838	0.037800
839	0.040300
840	0.079400
841	0.056000
842	0.029700
843	0.029600
844	0.077600
845	0.054500
846	0.076500
847	0.022000
848	0.022000
849	0.029300
850	0.022000
851	0.073800
852	0.021800
853	0.038200
854	0.038200
855	0.021700
856	0.036300
857	0.021600
858	0.029100
859	0.021600
860	0.028600
861	0.034100
862	0.106700
863	0.021300
864	0.030300
865	0.021100
866	0.021300
867	0.021100
868	0.060400
869	0.021300
870	0.032400
871	0.038600
872	0.028000
873	0.043300
874	0.021000
875	0.020700
876	0.020600
877	0.020500
878	0.020600
879	0.020600
880	0.020400
881	0.027100
882	0.042100
883	0.070400
884	0.072900
885	0.020300
886	0.020100
887	0.020000
888	0.027000
889	0.072900
890	0.066200
891	0.020000
892	0.020000
893	0.039900
894	0.035000
895	0.019600
896	0.025900
897	0.019500
898	0.019200
899	0.026700
900	0.019100
901	0.025600
902	0.019000
903	0.025500
904	0.019000
905	0.079200
906	0.043000
907	0.018600
908	0.035400
909	0.018700
910	0.040200
911	0.018400
912	0.018400
913	0.059600
914	0.026000
915	0.025900
916	0.018200
917	0.025200
918	0.024600
919	0.030800
920	0.057400
921	0.031300
922	0.017800
923	0.017900
924	0.017800
925	0.068000
926	0.017700
927	0.062600
928	0.017700
929	0.029800
930	0.023800
931	0.017400
932	0.024700
933	0.052300
934	0.017100
935	0.051300
936	0.066200
937	0.080700
938	0.017100
939	0.017100
940	0.049300
941	0.022700
942	0.061900
943	0.022800
944	0.022300
945	0.033600
946	0.047700
947	0.016600
948	0.016200
949	0.016100
950	0.046200
951	0.029200
952	0.045500
953	0.054900
954	0.026300
955	0.051100
956	0.022100
957	0.043800
958	0.048700
959	0.015300
960	0.015300
961	0.015200
962	0.015100
963	0.032300
964	0.022000
965	0.022000
966	0.023700
967	0.014900
968	0.021600
969	0.026500
970	0.039500
971	0.018800
972	0.014600
973	0.020900
974	0.024500
975	0.031000
976	0.020700
977	0.013900
978	0.013800
979	0.025200
980	0.019500
981	0.017600
982	0.017600
983	0.013500
984	0.023400
985	0.017100
986	0.036600
987	0.017200
988	0.016900
989	0.013000
990	0.059000
991	0.012800
992	0.026500
993	0.018600
994	0.012600
995	0.018500
996	0.012300
997	0.012100
998	0.018300
999	0.011900
1000	0.017600
1001	0.046000
1002	0.017700
1003	0.046400
1004	0.017100
1005	0.014800
1006	0.011200
1007	0.030900
1008	0.011000
1009	0.014100
1010	0.010300
1011	0.055300
1012	0.031300
1013	0.013600
1014	0.010100
1015	0.010000
1016	0.009600
1017	0.025300
1018	0.009400
1019	0.014900
1020	0.020800
1021	0.014900
1022	0.008500
1023	0.012200
1024	0.022100
1025	0.029100
1026	0.007800
1027	0.053400
1028	0.014100
1029	0.028500
1030	0.007600
1031	0.007200
1032	0.007900
1033	0.037200
1034	0.011300
1035	0.007100
1036	0.027000
1037	0.028700
1038	0.018200
1039	0.006500
1040	0.031600
1041	0.029700
1042	0.005900
1043	0.011700
1044	0.011100
1045	0.005300
1046	0.022000
1047	0.011400
1048	0.005200
1049	0.016100
1050	0.005300
1051	0.011000
1052	0.048400
1053	0.008700
1054	0.016300
1055	0.004600
1056	0.041400
1057	0.008200
1058	0.004100
1059	0.009400
1060	0.009300
1061	0.021600
1062	0.009900
1063	0.015000
1064	0.009500
1065	0.020900
1066	0.020700
1067	0.014000
1068	0.014900
1069	0.009000
1070	0.014000
1071	0.014300
1072	0.002800
1073	0.008500
1074	0.006400
1075	0.007900
1076	0.002300
1077	0.002300
1078	0.001600
1079	0.001600
1080	0.010600
1081	0.001400
1082	0.007700
1083	0.008000
1084	0.024200
1085	0.005900
1086	0.012000
1087	0.001300
1088	0.001200
1089	0.014200
1090	0.001000
1091	0.012900
1092	0.000900
1093	0.000900
1094	0.000900
1095	0.000800
1096	0.007800
1097	0.000800
1098	0.007400
1099	0.048300
1100	0.000700
1101	0.007800
1102	0.005600
1103	0.012900
1104	0.005500
1105	0.007700
1106	0.005400
1107	0.007700
1108	0.000600
1109	0.007100
1110	0.012900
1111	0.000900
1112	0.017400
1113	0.005400
1114	0.000600
1115	0.005300
1116	0.000600
1117	0.011800
1118	0.007600
1119	0.023500
1120	0.000900
1121	0.000600
1122	0.016800
1123	0.012800
1124	0.007100
1125	0.046300
1126	0.000600
1127	0.000700
1128	0.023100
1129	0.000600
1130	0.000700
1131	0.007000
1132	0.007400
1133	0.015800
1134	0.007300
1135	0.006900
1136	0.006900
1137	0.011900
1138	0.033100
1139	0.000600
1140	0.015100
1141	0.006800
1142	0.005100
1143	0.014900
1144	0.000700
1145	0.021200
1146	0.000700
1147	0.000700
1148	0.006800
1149	0.013700
1150	0.000700
1151	0.000700
1152	0.000600
1153	0.005000
1154	0.006700
1155	0.012700
1156	0.006500
1157	0.000900
1158	0.006900
1159	0.001000
1160	0.001000
1161	0.023600
1162	0.001000
1163	0.001000
1164	0.004900
1165	0.001000
1166	0.000900
1167	0.000900
1168	0.006400
1169	0.000800
1170	0.006400
1171	0.006300
1172	0.000800
1173	0.000800
1174	0.000800
1175	0.024600
1176	0.000700
1177	0.004700
1178	0.000700
1179	0.031500
1180	0.017500
1181	0.004900
1182	0.006800
1183	0.007100
1184	0.000700
1185	0.004700
1186	0.000700
1187	0.010300
1188	0.006700
1189	0.012700
1190	0.004600
1191	0.000600
1192	0.000600
1193	0.013400
1194	0.006100
1195	0.010600
1196	0.013300
1197	0.000600
1198	0.009900
1199	0.000600
1200	0.010600
1201	0.000600
1202	0.006200
1203	0.000600
1204	0.006600
1205	0.025300
1206	0.000600
1207	0.000600
1208	0.006100
1209	0.005900
1210	0.018000
1211	0.006100
1212	0.006600
1213	0.000600
1214	0.016600
1215	0.004400
1216	0.012700
1217	0.005800
1218	0.000600
1219	0.000600
1220	0.012800
1221	0.004400
1222	0.000600
1223	0.012600
1224	0.000600
1225	0.000600
1226	0.000600
1227	0.000700
1228	0.012500
1229	0.005900
1230	0.000700
1231	0.006300
1232	0.005700
1233	0.016200
1234	0.021900
1235	0.004300
1236	0.000700
1237	0.000700
1238	0.000600
1239	0.000600
1240	0.000600
1241	0.000600
1242	0.012800
1243	0.000600
1244	0.005600
1245	0.000600
1246	0.000600
1247	0.012400
1248	0.000600
1249	0.012300
1250	0.006400
1251	0.000600
1252	0.000600
1253	0.012300
1254	0.022400
1255	0.015800
1256	0.017400
1257	0.006300
1258	0.011500
1259	0.000600
1260	0.000600
1261	0.012300
1262	0.000600
1263	0.004200
1264	0.000600
1265	0.012300
1266	0.006300
1267	0.000600
1268	0.000600
1269	0.012200
1270	0.004100
1271	0.006200
1272	0.005700
1273	0.000600
1274	0.011900
1275	0.005700
1276	0.005700
1277	0.011900
1278	0.006200
1279	0.000600
1280	0.010500
1281	0.000600
1282	0.011800
1283	0.011800
1284	0.000600
1285	0.005600
1286	0.000700
1287	0.000700
1288	0.009600
1289	0.000700
1290	0.011700
1291	0.008700
1292	0.000700
1293	0.006100
1294	0.005300
1295	0.005300
1296	0.000600
1297	0.012000
1298	0.010300
1299	0.011700
1300	0.005500
1301	0.048300
1302	0.005500
1303	0.000600
1304	0.005500
1305	0.000600
1306	0.005500
1307	0.005500
1308	0.010900
1309	0.006000
1310	0.010500
1311	0.005200
1312	0.005900
1313	0.012900
1314	0.005800
1315	0.005000
1316	0.001100
1317	0.001100
1318	0.001100
1319	0.001100
1320	0.012400
1321	0.001200
1322	0.001200
1323	0.005700
1324	0.005700
1325	0.000800
1326	0.000700
1327	0.004900
1328	0.000800
1329	0.000800
1330	0.016900
1331	0.000600
1332	0.000600
1333	0.000500
1334	0.003800
1335	0.009500
1336	0.000500
1337	0.000500
1338	0.003800
1339	0.016400
1340	0.016400
1341	0.005000
1342	0.011700
1343	0.011600
1344	0.005300
1345	0.012100
1346	0.000600
1347	0.000600
1348	0.000600
1349	0.000500
1350	0.005200
1351	0.010000
1352	0.011400
1353	0.000600
1354	0.003800
1355	0.013800
1356	0.000600
1357	0.000600
1358	0.000500
1359	0.011900
1360	0.005300
1361	0.055500
1362	0.014500
1363	0.000600
1364	0.015000
1365	0.011200
1366	0.005700
1367	0.004800
1368	0.000600
1369	0.004800
1370	0.000700
1371	0.000700
1372	0.003700
1373	0.000700
1374	0.000600
1375	0.000600
1376	0.000600
1377	0.005700
1378	0.009900
1379	0.011200
1380	0.041400
1381	0.000600
1382	0.003700
1383	0.022200
1384	0.000600
1385	0.000600
1386	0.000600
1387	0.000600
1388	0.014100
1389	0.000600
1390	0.000600
1391	0.000600
1392	0.016800
1393	0.011600
1394	0.003900
1395	0.005200
1396	0.005900
1397	0.003700
1398	0.051200
1399	0.000600
1400	0.000600
1401	0.005500
1402	0.037200
1403	0.005900
1404	0.011000
1405	0.005100
1406	0.020900
1407	0.014300
1408	0.000400
1409	0.000400
1410	0.014200
1411	0.010900
1412	0.014800
1413	0.005100
1414	0.015800
1415	0.008500
1416	0.014600
1417	0.011400
1418	0.000700
1419	0.015000
1420	0.050200
1421	0.000700
1422	0.008800
1423	0.000700
1424	0.005600
1425	0.000800
1426	0.004500
1427	0.000900
1428	0.003500
1429	0.009200
1430	0.000800
1431	0.011300
1432	0.003500
1433	0.011300
1434	0.011300
1435	0.000900
1436	0.000800
1437	0.000800
1438	0.000800
1439	0.005500
1440	0.000800
1441	0.005000
1442	0.018000
1443	0.000700
1444	0.005000
1445	0.018600
1446	0.000800
1447	0.000800
1448	0.005000
1449	0.005700
1450	0.014200
1451	0.010600
1452	0.000500
1453	0.000400
1454	0.015200
1455	0.005200
1456	0.005700
1457	0.003600
1458	0.003600
1459	0.000400
1460	0.000800
1461	0.000500
1462	0.000700
1463	0.000700
1464	0.000600
1465	0.010900
1466	0.010800
1467	0.005000
1468	0.005600
1469	0.003500
1470	0.000400
1471	0.010400
1472	0.000500
1473	0.005600
1474	0.004500
1475	0.000500
1476	0.018800
1477	0.004400
1478	0.008300
1479	0.005400
1480	0.000700
1481	0.005500
1482	0.007600
1483	0.013500
1484	0.000700
1485	0.004800
1486	0.008600
1487	0.000600
1488	0.003300
1489	0.004800
1490	0.000600
1491	0.000600
1492	0.000600
1493	0.015000
1494	0.017200
1495	0.010900
1496	0.010700
1497	0.004300
1498	0.013400
1499	0.000600
1500	0.004300
1501	0.004800
1502	0.013100
1503	0.010600
1504	0.015400
1505	0.000600
1506	0.004700
1507	0.004700
1508	0.000600
1509	0.000600
1510	0.000600
1511	0.010400
1512	0.000700
1513	0.000700
1514	0.000700
1515	0.010400
1516	0.014400
1517	0.003300
1518	0.000700
1519	0.000700
1520	0.000700
1521	0.000800
1522	0.000700
1523	0.005300
1524	0.000700
1525	0.000700
1526	0.000700
1527	0.004800
1528	0.000500
1529	0.004900
1530	0.000500
1531	0.000400
1532	0.005000
1533	0.000400
1534	0.000300
1535	0.003500
1536	0.003500
1537	0.003500
1538	0.014800
1539	0.005700
1540	0.000300
1541	0.000300
1542	0.000300
1543	0.010400
1544	0.000400
1545	0.013200
1546	0.000400
1547	0.000400
1548	0.005100
1549	0.032200
1550	0.015700
1551	0.000400
1552	0.010000
1553	0.014200
1554	0.044500
1555	0.000600
1556	0.004200
1557	0.004500
1558	0.007400
1559	0.000700
1560	0.009900
1561	0.000700
1562	0.000700
1563	0.014600
1564	0.005300
1565	0.009800
1566	0.003200
1567	0.000700
1568	0.005300
1569	0.000700
1570	0.023700
1571	0.004200
1572	0.000700
1573	0.000700
1574	0.010000
1575	0.005400
1576	0.000500
1577	0.012400
1578	0.004300
1579	0.000500
1580	0.035600
1581	0.000500
1582	0.000500
1583	0.004800
1584	0.000500
1585	0.014800
1586	0.000500
1587	0.000500
1588	0.000500
1589	0.000500
1590	0.000500
1591	0.004800
1592	0.000400
1593	0.000500
1594	0.010000
1595	0.009600
1596	0.009500
1597	0.003400
1598	0.000400
1599	0.000400
1600	0.000400
1601	0.000400
1602	0.000400
1603	0.003300
1604	0.005500
1605	0.009000
1606	0.000400
1607	0.005500
1608	0.004900
1609	0.010000
1610	0.000400
1611	0.000400
1612	0.009400
1613	0.010000
1614	0.004900
1615	0.000400
1616	0.016900
1617	0.005300
1618	0.000500
1619	0.000500
1620	0.009200
1621	0.037300
1622	0.004000
1623	0.005200
1624	0.000700
1625	0.003200
1626	0.000700
1627	0.000700
1628	0.004000
1629	0.005200
1630	0.000600
1631	0.004000
1632	0.008500
1633	0.000600
1634	0.000600
1635	0.004500
1636	0.009600
1637	0.000600
1638	0.005700
1639	0.021400
1640	0.000600
1641	0.004000
1642	0.000600
1643	0.003900
1644	0.005000
1645	0.000500
1646	0.044500
1647	0.000800
1648	0.007200
1649	0.000800
1650	0.004400
1651	0.000800
1652	0.003100
1653	0.000800
1654	0.009600
1655	0.009900
1656	0.003800
1657	0.000600
1658	0.006400
1659	0.000600
1660	0.009200
1661	0.005100
1662	0.003100
1663	0.003900
1664	0.000600
1665	0.003000
1666	0.000500
1667	0.014600
1668	0.008100
1669	0.004400
1670	0.003000
1671	0.000700
1672	0.000700
1673	0.000400
1674	0.009300
1675	0.003000
1676	0.009600
1677	0.009600
1678	0.000400
1679	0.007900
1680	0.000500
1681	0.013600
1682	0.003000
1683	0.007700
1684	0.004400
1685	0.009900
1686	0.006700
1687	0.003700
1688	0.000700
1689	0.004400
1690	0.000700
1691	0.000700
1692	0.005000
1693	0.003000
1694	0.000700
1695	0.004400
1696	0.003700
1697	0.013500
1698	0.004900
1699	0.009100
1700	0.004400
1701	0.005000
1702	0.009700
1703	0.009900
1704	0.008000
1705	0.005600
1706	0.009900
1707	0.001600
1708	0.085800
1709	0.001600
1710	0.001200
1711	0.001200
1712	0.014700
1713	0.009800
1714	0.001000
1715	0.008600
1716	0.009800
1717	0.020800
1718	0.000800
1719	0.007900
1720	0.043000
1721	0.004300
1722	0.003700
1723	0.000800
1724	0.000800
1725	0.007800
1726	0.017700
1727	0.000900
1728	0.006400
1729	0.000900
1730	0.005000
1731	0.003000
1732	0.000600
1733	0.004400
1734	0.004400
1735	0.013200
1736	0.009200
1737	0.000600
1738	0.013100
1739	0.011300
1740	0.009400
1741	0.000600
1742	0.000600
1743	0.000600
1744	0.000600
1745	0.003000
1746	0.041600
1747	0.011400
1748	0.013500
1749	0.004400
1750	0.009000
1751	0.000700
1752	0.009000
1753	0.003800
1754	0.003800
1755	0.003800